Next Article in Journal
Pharmacogenetic Profiling in High-Risk Soft Tissue Sarcomas Treated with Neoadjuvant Chemotherapy
Next Article in Special Issue
Predicting the Risk of Incident Type 2 Diabetes Mellitus in Chinese Elderly Using Machine Learning Techniques
Previous Article in Journal
Interrelationship of Gut Microbiota, Obesity, Body Composition and Insulin Resistance in Asians with Type 2 Diabetes Mellitus
Previous Article in Special Issue
Integrating Coronary Plaque Information from CCTA by ML Predicts MACE in Patients with Suspected CAD
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
JPM
Volume 12
Issue 4
10.3390/jpm12040616
jpm-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles thumb_up
...
Endorse textsms
...
Comment
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Predicting the Need for Therapeutic Intervention and Mortality in Acute Pancreatitis: A Two-Center International Study Using Machine Learning

by
Na Shi
1,†,
Lan Lan
2,*,†,
Jiawei Luo
3,
Ping Zhu
1,
Thomas R. W. Ward
4,
Peter Szatmary
4,
Robert Sutton
4,
Wei Huang
1,4,
John A. Windsor
5,
Xiaobo Zhou
6 and
Qing Xia
1,*
1
Department of Integrated Traditional Chinese and Western Medicine, Sichuan Provincial Pancreatitis Centre and West China-Liverpool Biomedical Research Centre, West China Hospital, Sichuan University, Chengdu 610044, China
2
IT Center, Beijing Tiantan Hospital, Capital Medical University, Beijing 100070, China
3
West China Biomedical Big Data Centre, West China Hospital, Sichuan University, Chengdu 610041, China
4
Liverpool Pancreatitis Study Group, Royal Liverpool University Hospital, Institute of Translational Medicine, University of Liverpool, Liverpool L6 93BX, UK
5
Surgical and Translational Research Centre, Faculty of Medical and Health Sciences, University of Auckland, Auckland 1023, New Zealand
6
School of Biomedical Informatics, University of Texas Health Science Centre at Houston, Houston, TX 77030, USA
*
Authors to whom correspondence should be addressed.
†
Theses authors contributed equally to this study.
J. Pers. Med. 2022, 12(4), 616; https://doi.org/10.3390/jpm12040616
Submission received: 7 March 2022 / Revised: 5 April 2022 / Accepted: 6 April 2022 / Published: 11 April 2022
(This article belongs to the Special Issue Non-communicable Diseases, Big Data and Artificial Intelligence)
Browse Figures
Versions Notes

Abstract

:
Background: Current approaches to predicting intervention needs and mortality have reached 65–85% accuracy, which falls below clinical decision-making requirements in patients with acute pancreatitis (AP). We aimed to accurately predict therapeutic intervention needs and mortality on admission, in AP patients, using machine learning (ML). Methods: Data were obtained from three databases of patients admitted with AP: one retrospective (Chengdu) and two prospective (Liverpool and Chengdu) databases. Intervention and mortality differences, as well as potential predictors, were investigated. Univariate analysis was conducted, followed by a random forest ML algorithm used in multivariate analysis, to identify predictors. The ML performance matrix was applied to evaluate the model’s performance. Results: Three datasets of 2846 patients included 25 potential clinical predictors in the univariate analysis. The top ten identified predictors were obtained by ML models, for predicting interventions and mortality, from the training dataset. The prediction of interventions includes death in non-intervention patients, validated with high accuracy (96%/98%), the area under the receiver-operating-characteristic curve (0.90/0.98), and positive likelihood ratios (22.3/69.8), respectively. The post-test probabilities in the test set were 55.4% and 71.6%, respectively, which were considerably superior to existing prognostic scores. The ML model, for predicting mortality in intervention patients, performed better or equally with prognostic scores. Conclusions: ML, using admission clinical predictors, can accurately predict therapeutic interventions and mortality in patients with AP.

1. Introduction

Acute pancreatitis (AP) is one of the most common admission diagnoses relating to an acute gastrointestinal pathology. Approximately 25% of patients with AP develop infected pancreatic necrosis (IPN) and/or organ failure (OF), with mortality rates of 20–50% [1,2]. While the outcome of patients with AP has improved over recent decades, AP incidence and associated disability remain high [3], and specific drug therapies remain unavailable [4]. One of the challenges of therapeutic trials for AP is the inaccuracy in early severity and complication prediction, resulting in heterogeneous treatment groups. A review of current predictors of AP outcome [5] (including IPN, OF, and the need for intervention) demonstrated that the accuracy of current systems ranges from 65% to 85%, implying a misclassification error of 15–35%. This degree of inaccuracy in the prediction has clinical and research practice consequences.
Improving the accuracy of early severity prediction is of paramount importance and a matter of significant international effort. Various individual serum biomarkers have been investigated. However, they have failed to improve the clinical utility of existing simple and inexpensive scoring systems [6,7,8,9,10]. Combinations of markers and/or scoring systems potentially add value but lack external and/or multicenter validation [11,12,13,14]. The development and increasing accessibility of omics platforms have provided opportunities for prognostication based on genetic [15], transcriptomic [16], proteomic [17,18,19,20], metabolic profiling [21,22], and multi-platform omics analyses [23] Nevertheless, the application of these platforms in AP remains in its infancy.
The premise of machine learning (ML) in disease prognostication is to incorporate the wisdom embedded within decisions made by multiple clinicians, and the outcomes of their patients, in order to inform the individualized patient treatment [24]. ML is a broad field involving computer science and statistics, and broadly speaking, it involves a machine-led selection of iterative computational models to progressively improve the model’s performance in a specific task. The ability to handle vast datasets in an inherently unbiased manner has led to the growing interest in, and use of, ML-based applications in multiple areas of medicine [25,26,27,28]. This includes the use of ML in the diagnosis, prognosis, and predicted treatment response in patients with gastrointestinal diseases, although the lack of high-quality datasets continues to present a problem [29].
In AP, ML has been used to aid in the prediction of OF [30,31,32] and severity [33,34,35]; however, thus far, no study has accurately and timeously predicted the need for therapeutic intervention [36]. The identification of high-risk patients who require specialist intervention is critical, as these patients are, not only, at considerable risk of adverse disease outcomes but timely management has considerable implications for the health-care system. This includes the possible need to provide services that may not be available throughout the day, or every day in the week, and the provision of services may mean a transfer to a different hospital in some care settings.
Although there have been attempts to standardize the language surrounding indications for intervention in AP [37], there are numerous instances (e.g., ongoing OF or other severe gastrointestinal symptoms, due to the mass effect of walled-off necrosis or disconnected pancreatic duct syndrome) [38] that warrant intervention under the care of an experienced pancreatologist. These can often be difficult to classify or use to provide general guidance on the use of traditional methods.
Therefore, this study aimed to apply an ML algorithm to preoperatively predict the need for intervention and mortality in patients admitted with AP.

2. Materials and Methods

2.1. Overview

Data on patients with AP were collected, retrospectively (single center, Chengdu) and prospectively (two centers, Liverpool and Chengdu), and analyzed following the STROBE guidelines for observational studies [39]. Confirmation that specific ethical approval was not required was provided by the Institutional Review Board of West China Hospital of Sichuan University (WCH/SCU), due to prior approval for the use of retrospective data. Informed consent was obtained from patients admitted to Royal Liverpool University Hospital (RLUH), and ethical approval was not required because anonymized data were used. Predictors and outcomes from both retrospective and prospective databases were used to develop and test predictive models for intervention and mortality.

2.2. Cohorts and Data Collection

Eligible patients were identified from the Hospital Information System by using the International Classification of Diseases, 10th edition, code K85. All patients were admitted to WCH/SCU or RLUH, within 48 h of abdominal pain onset, with a diagnosis of AP, as defined by the revised Atlanta classification [37]. Patients in the retrospective cohort were admitted between 1 October 2009 and 30 September 2013. Patients in the prospective cohorts were admitted between 1 September 2014 and 31 December 2015 (WCH/SCU) or between 1 June 2010 and 30 June 2017 (RLUH). Data collection in both centers was based on a predefined pro forma and coordinated by experienced researchers, with quality assurance and control measures in place at every step of the study process.

2.3. Potential Predictors

Demographic variables (age, sex, comorbidities, abdominal pain onset time, and etiology), available quantitative laboratory tests on admission common to all three cohorts (white blood cell [WBC], neutrophils, lymphocytes, hematocrit, urea, creatinine, albumin, and C-reactive protein [CRP]), and clinical severity scores on admission (sequential organ failure assessment [SOFA] [40], systemic inflammatory response syndrome [SIRS] [41], bedside index, for severity in acute pancreatitis [BISAP] [42], acute physiology, and chronic health examination [APACHE] II [43], as well as modified computerized tomographic severity index [MCTSI]) [44] were collected. Additional clinical variables, including pleural effusion, local complications, OF, pancreatic, and extrapancreatic infection (bacteremia and others) were also recorded (worst during hospitalization or before surgery), as were daily assessments of type, onset, and duration of OF.

2.4. Definition of Groups

The patients were divided into conservative-treatment (no intervention) and invasive-intervention (including pancreatic cyst percutaneous catheter drainage and necrosectomy) groups for further analysis.

2.5. Statistical Analysis and Model Development

The chi-squared test was used to analyze categorical data, and the Kruskal–Wallis test was used for ranked variables. The rank-sum test was used for skewed and continuous data. Random forest (RF) ML [45] multivariate analysis was used to construct the algorithms and resolve the impact of data imbalances on predictions (2714 cases in the non-intervention group, more than 20 times of the 132 cases in the intervention group). RF can process high-dimensional samples and does not require dimensionality reduction for datasets with numerous variables. It is worth noting that RF is an ensemble method that utilizes many classifiers to work together, and it has high accuracy and superiority on unbalanced datasets. The mean decrease in the Gini value of each variable, indicating the importance of the variable to the outcome, was obtained by the varImpPlot function using the R software. We comprehensively evaluated the model’s performance, using the area under receiver-operating-characteristic curve (AUC) analysis, and evaluated the post-test probabilities by calculating the positive and negative likelihood ratios.
All the analytic processes were performed using R software (version 3.6.3).

2.5.1. Data Sources

Since there were three datasets in this study: (1) a retrospective cohort from WCH/SCU, (2) a prospective cohort from WCH/SCU, (3) and a prospective cohort from RLUH, the differences between various data collection times and populations might have had varying effects on outcomes. Therefore, the differences affecting the research outcomes were analyzed. First, we used the three datasets, separately, to predict intervention needs and mortality. Thereafter, we aggregated the three datasets into a single dataset for the prediction. We found that the results of modelling the three datasets separately, and those of integrating them into one dataset, were similar. In addition, this study was a retrospective analysis of data collected in a previous period. Therefore, we consolidated the three different data sources into a single dataset before analysis and modeling.

2.5.2. Univariate Analysis

The impact of each individual variable on “need for intervention” and “mortality” was examined using univariate analysis. Where the resulting p-value was <0.10, the variable was included in multivariable analysis.

2.5.3. Performance of the ML Algorithm

For multivariate analysis, an RF ML approach was used. Patients were divided into three groups for modeling: (1) intervention and conservative management, (2) mortality and survival among intervention patients, and (3) mortality and survival among conservatively managed patients. The larger the mean decrease in the Gini value, the greater the impact of the variable. We extracted the characteristics of the intervention and deceased patients, compared with those of non-intervention and surviving patients, and evaluated the model’s performance using evaluation indicators (accuracy, AUC, sensitivity, specificity, and likelihood ratio). Accuracy was evaluated based on the percentage of correct predictions. To predict the performance of ML, accuracy was evaluated based on the proportion of correct predictions in the total sample. As a rule of thumb, a test with a high predictive value has a positive likelihood ratio >5, usually closer to 10, and occasionally higher [46]. In all three groups, the total dataset was divided into training, validation, and test datasets according to a specific ratio of 6:2:2. The training set was used to develop the model, the validation set was used to adjust the parameters, and the test set was used to obtain the final result, which was the average performance with 30 repetitions (Figure 1). The hyperparameters of random forest include the number of trees (ntree), the number of variables required to build a single tree (nvariable), and the minimum sample size of leaf nodes (nodesize). Through parameter sensitivity analysis (Supplementary Table S1), the final chosen hyperparameters were: ntree = 500, nvariable = 4, and nodesize = 1.

3. Results

3.1. Comparison of Characteristics between Intervention and Non-Intervention Patients with AP

A retrospective cohort of 2018 patients (WCH/SCU) and two prospective cohorts of 259 and 569 patients (WCH/SCU and RLUH, respectively) were included in the analysis. The proportions of intervention and mortality (chi-squared test; p = 0.432 and p = 0.411, respectively) were similar across all cohorts, indicating that any observed differences in the number of interventions and/or mortality were unlikely to be due to inherent differences in the source data.
The clinical characteristics of the 2846 patients are summarized in Table 1. The number of patients requiring therapeutic intervention was 132 (4.6%), while 2714 (95.4%) were managed conservatively. The most common etiologies (in order) were biliary, hypertriglyceridemia, and alcohol consumption. The median age of all participants was 46 years (interquartile range, 38–58 years), and 64.0% were men. There were no significant differences in age, sex, Charlson comorbidity index, or etiology between the two groups. The time from pain to admission was 6 h longer in the intervention group (p < 0.05).
WBC, neutrophil, hematocrit, urea, creatinine, and CRP in the intervention group were significantly higher than those in the non-intervention group, while albumin levels were lower (all p < 0.05). The admission clinical scoring systems, including SOFA, BISAP, SIRS, APACHE II, and worst MCTSI, were all higher among intervention patients, with the ratio of severe cases being three times higher than that in the non-intervention group.
Patients requiring intervention exhibited significantly worse clinical outcomes: 98/132 (74.2%) developed acute peripancreatic fluid collection, and 84/132 (63.6%) developed pancreatic and/or peripancreatic necrosis. Out of the 84 patients with necrosis, 81 were confirmed to have infectious necrosis; 99/132 (75%), 42/132 (31.8%), and 29/132 (22%) therapeutic-intervention patients developed persistent pulmonary, circulatory, and renal failure, respectively, with the duration of all three types’ OF lasting longer than those in the non-intervention group. Extrapancreatic infection was also more prevalent in the intervention group, regardless of bacteremia or lung infection.
The comparisons between death and survival among intervention patients, as well as among non-intervention patients, are shown in Supplementary Table S2 and Supplementary Table S3, respectively.

3.2. Important Features and Predictors for Intervention and Mortality

As shown in Table 2, important features (variables) associated with intervention and death differed. Compared with that in non-intervention patients, the duration of pulmonary failure was the most important factor in intervention patients. The remaining nine important variables for intervention patients, ranging from heavy to light, were neutrophils, albumin, lymphocytes, creatinine, age, hematocrit, onset of circulatory failure, APACHE II, and duration of circulatory failure. OF characteristics were all important variables for death among both intervention and non-intervention patients, especially for the occurrence of circulatory and renal failure. Circulatory failure, onset of circulatory failure, duration of circulatory failure, renal failure, duration of renal failure, duration of pulmonary failure, and APACHE II were all important variables for death in both intervention and non-intervention groups. The difference was that urea and CRP were important indicators of death in intervention patients, while creatine and WBC were important indicators in non-intervention patients.
Figure 2 shows the relationship between important variables (the top five) and the outcome. The first column (a) displays the top features for intervention, the second column (b) is for death in the intervention group, and the third column (c) is for death in the non-intervention group. A scatter plot was used to show the relationship between categorical variables and the outcome, and a box plot was used to show the relationship between quantitative data and the outcome. Pulmonary failure persisted significantly longer in the intervention groups than in the non-intervention groups, along with higher neutrophil and creatinine levels and a lower albumin level, while the lymphocyte level was similar between these two groups. The top five important features of death were all about circulatory and renal failure. The difference between the intervention and non-intervention groups, among deceased patients, was that the duration of renal and circulatory failure had an impact on death in the intervention group, while the most important variables for death in the non-intervention group were the rate of renal failure and circulatory failure.

3.3. Prediction and Diagnostic Performance for Intervention and Mortality

Regarding the prediction of intervention, the accuracy of ML-based intervention prediction was 96%, thus indicating that predicting both the positive and negative categories of the model was highly accurate. The model identified 74% (sensitivity) of patients requiring intervention. Overall, the AUC was approximately 90%, and the positive likelihood ratio was 22.3. The death in the intervention patients were 86% recognized (sensitivity), the AUC reached 89%, and the positive likelihood ratio was 6.14. In terms of death in non-intervention prediction, the ML-based model performed better, the AUC could reach 98%, and the positive likelihood ratio was 69.6 (Table 3). The performance of all three ML models on the test dataset was consistent with the above-mentioned.

3.4. Comparison of the Models with Prognostic Scores

Furthermore, the predictive performance for intervention and mortality, in patients with AP, from the test set was compared among ML models, SOFA, BISAP, SIRS, APACHE II, and worst MCTSI by calculating the positive likelihood ratios and post-test probabilities. In the test set, 4.64% of patients with AP required intervention. The existing prognostic scores on admission showed minimal to small changes, with an increase in the likelihood of intervention in patients with AP with extremely low sensitivities, while only the ML model moderately increased the rate, with a positive likelihood ratio of 25.5 and post-test probability of 55.4%. On predicting mortality in all intervention patients, the ML model performed better, or equally, with prognostic scores. Interestingly, the ML model significantly improved the likelihood ratio (71.9) in predicting mortality in non-intervention patients, increasing the 3.39% pre-test probability to 71.6% (post-test probability), while the worst MCTSI showed nearly no change. The details are presented in Table 4.

4. Discussion

To the best of our knowledge, this is the first study to use ML to quantify AP intervention indications and predictors of mortality on admission. Based on substantial international AP data from two centers, we found the duration of pulmonary failure to be an important indicator of intervention, followed by neutrophils and albumin, and OF characteristics were important predictors of death, in patients with AP, by ML. Using our models, we can predict whether patients with AP require intervention at an early stage of hospitalization, thus providing an important reference for timely consideration of whether to transfer to the intervention department or a higher-level hospital that can perform intervention. Furthermore, a pre-judgment can also be made regarding death, especially in those non-intervention patients with AP.
The use of big data to capture patient-level outcomes has increased exponentially over the past 10 years, providing a strong foundation for continuing investigations on questions more specific to surgery [47]. ML algorithms, based on big data from multiple sources, are being developed to help deliver care, inform health policy, and reduce waste, since various data sources can potentially yield a rich matched data set [48,49]. ML applications can improve the accuracy of treatment protocols and health outcomes through algorithmic processes [50]. While guidelines present evidence-based international consensus statements on AP management, mainly through the collaboration of a panel of experts, new and more instructive guidelines require more data to be implemented in this era of big data.
Clinicians worldwide seem to be following the same initial, guideline-based management protocol to the greatest extent possible; nonetheless, surgeons hold different opinions regarding multidisciplinary strategies for endoscopy, radiology, and interventions. Most guidelines and related randomized controlled trials compared intervention methods [51,52,53,54,55,56] or timing [57] of interventions but investigated indicators minimally. In addition, although IPN is the intervention recommended by most AP treatment guides for necrotizing pancreatitis [38,58,59,60], it is often determined when the intervention approaches in clinical practice. Clinical indicators for predicting interventions on admission, using real-world big data, can balance clinical efficacy with cost effectiveness. To identify intervention patients in the early stage of hospitalization, we intended to use the data obtained on admission, as well as the worst preoperative imaging manifestations and OF characteristics, to identify predictors of intervention.
A prediction model was ultimately established. The better the predictive performance, the higher the accuracy of predicting whether a new patient with AP will be operated on or die. There were no existing prognostic scores for intervention in patients with AP, as our results demonstrated that the existing available AP-related prognostic systems showed low predictive performance for intervention. Our results revealed that the AUC for the prediction of intervention was not low, the intervention patient-recognition rate (sensitivity) was 74%, and patients who did not require surgery had recognition rates (specificity) exceeding 90%, suggesting that the model is useful for the initial screening of interventions that do not require surgery. Patients with AP who do not require intervention are ruled out first (because of high accuracy and specificity), and the remaining patients can be further observed to determine whether intervention is warranted, thus saving medical resources. Moreover, a positive likelihood ratio >5 indicated our model’s good predictive effect, while other prognostic scores at the early stage of the disease almost lacked predictive value in predicting interventions in patients with AP.
The predictive performance for mortality was better with an AUC > 95% and a positive likelihood ratio > 10. This suggests that the model can be used to predict death in both interventions, more so in non-intervention patients, and attention can be focused on advancement. Regarding the top 10 variables important for death, whether the patient is operated on or not, the important variable was organ function, differing greatly from the variables important to intervention, and the other two studies predicted hospital mortality in patients with AP (Supplementary Table S4). The Dutch Pancreatitis Study Group concluded that infection, onset, and duration of OF were not associated with death in necrotizing pancreatitis [61], findings that are inconsistent with ours [62,63,64]. This may be because of the single center and multicenter analyses differed in their results. Therefore, we used a two-center study to further confirm that OF was more important than infection as a predictor of death in AP, based extensive AP data.
Our study also has some limitations. Firstly, most of the data were collected on admission; however, the condition of the patients with AP changed over time. To predict surgery and death more accurately, more time-consuming variables or more frequent data collection are required for predictive research. Secondly, if invasive intervention was required, we usually performed selective percutaneous catheter drainage (pancreatic necrosis less than 30%) or a retroperitoneal pancreatic necrosectomy approach (pancreatic necrosis greater than 30%), but we did not perform percutaneous or endoscopic transgastric drainage routinely [62]. Comparison between open and minimally invasive procedures would modify the current model and require further analysis. Thirdly, the retrospective collection of data may not contain all the features needed for current or future studies, which makes it impossible to guarantee homogeneity between the local data and study data in model reproduction. Therefore, more prospective data sources in multi-regional and multi-center studies may strengthen the interpretation of model validation methods and, consequently, establish general models that can be widely promoted.

5. Conclusions

ML models are potentially useful in predicting intervention and death, in patients with AP, using clinical indicators on admission.

Supplementary Materials

The following supporting information can be downloaded at: https://www.mdpi.com/article/10.3390/jpm12040616/s1, Table S1. Parameter sensitivity analysis. Table S2. Characteristics between died and survived intervention patients with AP. Table S3. Characteristics between died and survived non-intervention patients with AP. Table S4. Characteristics of studies predicted hospital mortality in patients with AP [65,66].

Author Contributions

N.S. and L.L. contributed equally to this study. Conceptualization, X.Z. and J.A.W.; Methodology, L.L., P.Z. and T.R.W.W.; Formal Analysis, L.L. and J.L.; Data Curation, N.S. and W.H.; Writing–Original Draft Preparation, N.S. and L.L.; Writing–Review & Editing, P.S., W.H., Q.X., J.A.W. and X.Z.; Supervision, Q.X. and X.Z.; Project Administration, Q.X. and R.S.; Funding Acquisition, N.S., X.Z. and Q.X. All authors have read and agreed to the published version of the manuscript.

Funding

This work was supported by the NZ-China Strategic Research Alliance 2016 Award (China: 2016YFE0101800, Q.X. and W.H.; New Zealand: J.A.W.); This study was supported by Sichuan Provincial Department of Science and Technology (Grant No. 19ZDYF1765, 2020YFS0235). 1.3.5 project for disciplines of excellence, West China Hospital, Sichuan University (Grant No. ZYJC18010). Center of Excellence-International Collaboration Initiative Grant (Grant No. 139170052).

Institutional Review Board Statement

Ethical approval was not required was provided by the Institutional Review Board of West China Hospital of Sichuan University (WCH/SCU) due to prior approval for the use of retrospective data. Informed consent was obtained from patients admitted to Royal Liverpool University Hospital (RLUH) and ethical approval was not required because anonymized data were used.

Informed Consent Statement

Patient consent was waived due to prior approval for the use of retrospective data or anonymized data were used.

Data Availability Statement

Restrictions apply to the availability of data generated or analysed during this study to preserve patient confidentiality or because they were used under license. The corresponding author will on request detail the restrictions and any conditions under which access to some data may be provided.

Acknowledgments

These authors thank all the staff from the pancreas multidisciplinary teams at West China Hospital of Sichuan University and Royal Liverpool University Hospital for their continuous support.

Conflicts of Interest

The authors declare no conflict of interest.

References

  1. Peery, A.F.; Crockett, S.D.; Murphy, C.C.; Lund, J.L.; Dellon, E.S.; Williams, J.L.; Jensen, E.T.; Shaheen, N.J.; Barritt, A.S.; Lieber, S.R.; et al. Burden and Cost of Gastrointestinal, Liver, and Pancreatic Diseases in the United States: Update 2018. Gastroenterology 2019, 156, 254–272.e11. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  2. Boxhoorn, L.; Voermans, R.P.; Bouwense, S.A.; Bruno, M.J.; Verdonk, R.C.; Boermeester, M.A.; van Santvoort, H.C.; Besselink, M.G. Acute pancreatitis. Lancet 2020, 396, 726–734. [Google Scholar] [CrossRef]
  3. Xiao, A.Y.; Tan, M.L.; Wu, L.M.; Asrani, V.M.; Windsor, J.A.; Yadav, D.; Petrov, M.S. Global incidence and mortality of pancreatic diseases: A systematic review, meta-analysis, and meta-regression of population-based cohort studies. Lancet Gastroenterol. Hepatol. 2016, 1, 45–55. [Google Scholar] [CrossRef]
  4. Moggia, E.; Koti, R.; Belgaumkar, A.P.; Fazio, F.; Pereira, S.P.; Davidson, B.R.; Gurusamy, K.S. Pharmacological interventions for acute pancreatitis. Cochrane Database Syst. Rev. 2017, 4, CD011384. [Google Scholar] [CrossRef]
  5. Gomatos, I.P.; Xiaodong, X.; Ghaneh, P.; Halloran, C.; Raraty, M.; Lane, B.; Sutton, R.; Neoptolemos, J.P. Prognostic markers in acute pancreatitis. Expert Rev. Mol. Diagn. 2014, 14, 333–346. [Google Scholar] [CrossRef]
  6. Staubli, S.M.; Oertli, D.; Nebiker, C.A. Laboratory markers predicting severity of acute pancreatitis. Crit. Rev. Clin. Lab. Sci. 2015, 52, 273–283. [Google Scholar] [CrossRef]
  7. Liu, T.; Huang, W.; Szatmary, P.; Abrams, S.T.; Alhamdi, Y.; Lin, Z.; Greenhalf, W.; Wang, G.; Sutton, R.; Toh, C.H. Accuracy of circulating histones in predicting persistent organ failure and mortality in patients with acute pancreatitis. Br. J. Surg. 2017, 104, 1215–1225. [Google Scholar] [CrossRef] [Green Version]
  8. Goswami, P.; Sonika, U.; Moka, P.; Sreenivas, V.; Saraya, A. Intestinal Fatty Acid Binding Protein and Citrulline as Markers of Gut Injury and Prognosis in Patients With Acute Pancreatitis. Pancreas 2017, 46, 1275–1280. [Google Scholar] [CrossRef]
  9. De-Madaria, E.; Molero, X.; Bonjoch, L.; Casas, J.; Cardenas-Jaen, K.; Montenegro, A.; Closa, D. Oleic acid chlorohydrin, a new early biomarker for the prediction of acute pancreatitis severity in humans. Ann. Intensive Care 2018, 8, 1. [Google Scholar] [CrossRef] [Green Version]
  10. Huang, Q.; Wu, Z.; Chi, C.; Wu, C.; Su, L.; Zhang, Y.; Zhu, J.; Liu, Y. Angiopoietin-2 Is an Early Predictor for Acute Gastrointestinal Injury and Intestinal Barrier Dysfunction in Patients with Acute Pancreatitis. Dig. Dis. Sci. 2021, 66, 114–120. [Google Scholar] [CrossRef]
  11. Hong, W.; Lillemoe, K.D.; Pan, S.; Zimmer, V.; Kontopantelis, E.; Stock, S.; Zippi, M.; Wang, C.; Zhou, M. Development and validation of a risk prediction score for severe acute pancreatitis. J. Transl. Med. 2019, 17, 146. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  12. Wu, H.; Li, J.; Zhao, J.; Li, S. A new scoring system can be applied to predict the organ failure related events in acute pancreatitis accurately and rapidly. Pancreatology 2020, 20, 622–628. [Google Scholar] [CrossRef] [PubMed]
  13. Tan, J.W.; Zhang, X.Q.; Geng, C.M.; Peng, L.L. Development of the National Early Warning Score-Calcium Model for Predicting Adverse Outcomes in Patients With Acute Pancreatitis. J. Emerg. Nurs. 2020, 46, 171–179. [Google Scholar] [CrossRef] [PubMed]
  14. Rasch, S.; Pichlmeier, E.M.; Phillip, V.; Mayr, U.; Schmid, R.M.; Huber, W.; Lahmer, T. Prediction of Outcome in Acute Pancreatitis by the qSOFA and the New ERAP Score. Dig. Dis. Sci. 2022, 67, 1371–1378. [Google Scholar] [CrossRef]
  15. Fan, L.; Hui, X.; Mao, Y.; Zhou, J. Identification of Acute Pancreatitis-Related Genes and Pathways by Integrated Bioinformatics Analysis. Dig. Dis. Sci. 2020, 65, 1720–1732. [Google Scholar] [CrossRef]
  16. Blenkiron, C.; Askelund, K.J.; Shanbhag, S.T.; Chakraborty, M.; Petrov, M.S.; Delahunt, B.; Windsor, J.A.; Phillips, A.R. MicroRNAs in mesenteric lymph and plasma during acute pancreatitis. Ann. Surg. 2014, 260, 341–347. [Google Scholar] [CrossRef]
  17. Waldron, R.T.; Lugea, A.; Gulla, A.; Pandol, S.J. Proteomic Identification of Novel Plasma Biomarkers and Pathobiologic Pathways in Alcoholic Acute Pancreatitis. Front. Physiol. 2018, 9, 1215. [Google Scholar] [CrossRef]
  18. Garcia-Hernandez, V.; Sanchez-Bernal, C.; Schvartz, D.; Calvo, J.J.; Sanchez, J.C.; Sanchez-Yague, J. A tandem mass tag (TMT) proteomic analysis during the early phase of experimental pancreatitis reveals new insights in the disease pathogenesis. J. Proteom. 2018, 181, 190–200. [Google Scholar] [CrossRef]
  19. Wang, C.; Zhang, Y.; Tan, J.; Chen, B.; Sun, L. Improved Integrated Whole Proteomic and Phosphoproteomic Profiles of Severe Acute Pancreatitis. J. Proteome Res. 2020, 19, 2471–2482. [Google Scholar] [CrossRef]
  20. Papachristou, G.I.; Malehorn, D.E.; Lamb, J.; Slivka, A.; Bigbee, W.L.; Whitcomb, D.C. Serum proteomic patterns as a predictor of severity in acute pancreatitis. Pancreatology 2007, 7, 317–324. [Google Scholar] [CrossRef]
  21. Peng, Y.; Hong, J.; Raftery, D.; Xia, Q.; Du, D. Metabolomic-based clinical studies and murine models for acute pancreatitis disease: A review. Biochim. Biophys. Acta Mol. Basis Dis. 2021, 1867, 166123. [Google Scholar] [CrossRef] [PubMed]
  22. Silva-Vaz, P.; Jarak, I.; Rato, L.; Oliveira, P.F.; Morgado-Nunes, S.; Paulino, A.; Castelo-Branco, M.; Botelho, M.F.; Tralhão, J.G.; Alves, M.G.; et al. Plasmatic Oxidative and Metabonomic Profile of Patients with Different Degrees of Biliary Acute Pancreatitis Severity. Antioxidants 2021, 10, 988. [Google Scholar] [CrossRef] [PubMed]
  23. Neyton, L.P.A.; Zheng, X.; Skouras, C.; Doeschl-Wilson, A.; Gutmann, M.U.; Uings, I.; Rao, F.V.; Nicolas, A.; Marshall, C.; Wilson, L.M.; et al. Molecular Patterns in Acute Pancreatitis Reflect Generalizable Endotypes of the Host Response to Systemic Injury in Humans. Ann. Surg. 2022, 275, e453–e462. [Google Scholar] [CrossRef] [PubMed]
  24. Rajkomar, A.; Dean, J.; Kohane, I. Machine Learning in Medicine. N. Engl. J. Med. 2019, 380, 1347–1358. [Google Scholar] [CrossRef]
  25. Deo, R.C. Machine Learning in Medicine. Circulation 2015, 132, 1920–1930. [Google Scholar] [CrossRef] [Green Version]
  26. DeGregory, K.W.; Kuiper, P.; DeSilvio, T.; Pleuss, J.D.; Miller, R.; Roginski, J.W.; Fisher, C.B.; Harness, D.; Viswanath, S.; Heymsfield, S.B.; et al. A review of machine learning in obesity. Obes. Rev. 2018, 19, 668–685. [Google Scholar] [CrossRef]
  27. Connor, C.W. Artificial Intelligence and Machine Learning in Anesthesiology. Anesthesiology 2019, 131, 1346–1359. [Google Scholar] [CrossRef] [Green Version]
  28. Bleidorn, W.; Hopwood, C.J. Using Machine Learning to Advance Personality Assessment and Theory. Personal. Soc. Psychol. Rev. 2019, 23, 190–203. [Google Scholar] [CrossRef]
  29. Le Berre, C.; Sandborn, W.J.; Aridhi, S.; Devignes, M.D.; Fournier, L.; Smail-Tabbone, M.; Danese, S.; Peyrin-Biroulet, L. Application of Artificial Intelligence to Gastroenterology and Hepatology. Gastroenterology 2020, 158, 76–94.e2. [Google Scholar] [CrossRef] [Green Version]
  30. Qiu, Q.; Nian, Y.J.; Guo, Y.; Tang, L.; Lu, N.; Wen, L.Z.; Wang, B.; Chen, D.F.; Liu, K.J. Development and validation of three machine-learning models for predicting multiple organ failure in moderately severe and severe acute pancreatitis. BMC Gastroenterol. 2019, 19, 118. [Google Scholar] [CrossRef] [Green Version]
  31. Qu, C.; Gao, L.; Yu, X.Q.; Wei, M.; Fang, G.Q.; He, J.; Cao, L.X.; Ke, L.; Tong, Z.H.; Li, W.Q. Machine Learning Models of Acute Kidney Injury Prediction in Acute Pancreatitis Patients. Gastroenterol. Res. Pract. 2020, 2020, 3431290. [Google Scholar] [CrossRef] [PubMed]
  32. Xu, F.; Chen, X.; Li, C.; Liu, J.; Qiu, Q.; He, M.; Xiao, J.; Liu, Z.; Ji, B.; Chen, D.; et al. Prediction of Multiple Organ Failure Complicated by Moderately Severe or Severe Acute Pancreatitis Based on Machine Learning: A Multicenter Cohort Study. Mediat. Inflamm. 2021, 2021, 5525118. [Google Scholar] [CrossRef] [PubMed]
  33. Pearce, C.B.; Gunn, S.R.; Ahmed, A.; Johnson, C.D. Machine learning can improve prediction of severity in acute pancreatitis using admission values of APACHE II score and C-reactive protein. Pancreatology 2006, 6, 123–131. [Google Scholar] [CrossRef] [PubMed]
  34. Sun, H.W.; Lu, J.Y.; Weng, Y.X.; Chen, H.; He, Q.Y.; Liu, R.; Li, H.P.; Pan, J.Y.; Shi, K.Q. Accurate prediction of acute pancreatitis severity with integrative blood molecular measurements. Aging 2021, 13, 8817–8834. [Google Scholar] [CrossRef]
  35. Jin, X.; Ding, Z.; Li, T.; Xiong, J.; Tian, G.; Liu, J. Comparison of MPL-ANN and PLS-DA models for predicting the severity of patients with acute pancreatitis: An exploratory study. Am. J. Emerg. Med. 2021, 44, 85–91. [Google Scholar] [CrossRef]
  36. Liu, N.; He, J.; Hu, X.; Xu, S.F.; Su, W.; Luo, J.F.; Wang, Q.F.; Guo, F. Acute necrotising pancreatitis: Measurements of necrosis volume and mean CT attenuation help early prediction of organ failure and need for intervention. Eur. Radiol. 2021, 31, 7705–7714. [Google Scholar] [CrossRef]
  37. Banks, P.A.; Bollen, T.L.; Dervenis, C.; Gooszen, H.G.; Johnson, C.D.; Sarr, M.G.; Tsiotos, G.G.; Vege, S.S. Classification of acute pancreatitis--2012: Revision of the Atlanta classification and definitions by international consensus. Gut 2013, 62, 102–111. [Google Scholar] [CrossRef]
  38. Working Group IAPAPAAPG. IAP/APA evidence-based guidelines for the management of acute pancreatitis. Pancreatology 2013, 13, e1–e15. [Google Scholar] [CrossRef]
  39. Von Elm, E.; Altman, D.G.; Egger, M.; Pocock, S.J.; Gotzsche, P.C.; Vandenbroucke, J.P. STROBE Initiative. Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) statement: Guidelines for reporting observational studies. BMJ 2007, 335, 806–808. [Google Scholar] [CrossRef] [Green Version]
  40. Halonen, K.I.; Pettilä, V.; Leppäniemi, A.K.; Kemppainen, E.A.; Puolakkainen, P.A.; Haapiainen, R.K. Multiple organ dysfunction associated with severe acute pancreatitis. Crit. Care Med. 2002, 30, 1274–1279. [Google Scholar] [CrossRef]
  41. Mofidi, R.; Duff, M.D.; Wigmore, S.J.; Madhavan, K.K.; Garden, O.J.; Parks, R.W. Association between early systemic inflammatory response, severity of multiorgan dysfunction and death in acute pancreatitis. Br. J. Surg. 2006, 93, 738–744. [Google Scholar] [CrossRef] [PubMed]
  42. Wu, B.U.; Johannes, R.S.; Sun, X.; Tabak, Y.; Conwell, D.L.; Banks, P.A. The early prediction of mortality in acute pancreatitis: A large population-based study. Gut 2008, 57, 1698–1703. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  43. Larvin, M.; McMahon, M.J. APACHE-II score for assessment and monitoring of acute pancreatitis. Lancet 1989, 2, 201–205. [Google Scholar] [CrossRef]
  44. Bollen, T.L.; Singh, V.K.; Maurer, R.; Repas, K.; van Es, H.W.; Banks, P.A.; Mortele, K.J. A comparative evaluation of radiologic and clinical scoring systems in the early prediction of severity in acute pancreatitis. Am. J. Gastroenterol. 2012, 107, 612–619. [Google Scholar] [CrossRef] [PubMed]
  45. Breiman, L. Random Forests. Mach. Learn. 2001, 45, 5–32. [Google Scholar] [CrossRef] [Green Version]
  46. Windsor, J.A. A better way to predict the outcome in acute pancreatitis? Am. J. Gastroenterol. 2010, 105, 1671–1673. [Google Scholar] [CrossRef]
  47. Knight, S.R.; Ots, R.; Maimbo, M.; Drake, T.M.; Fairfield, C.J.; Harrison, E.M. Systematic review of the use of big data to improve surgery in low- and middle-income countries. Br. J. Surg. 2019, 106, e62–e72. [Google Scholar] [CrossRef] [Green Version]
  48. Murdoch, T.B.; Detsky, A.S. The inevitable application of big data to health care. JAMA 2013, 309, 1351–1352. [Google Scholar] [CrossRef]
  49. Belle, A.; Thiagarajan, R.; Soroushmehr, S.M.; Navidi, F.; Beard, D.A.; Najarian, K. Big Data Analytics in Healthcare. Biomed. Res. Int. 2015, 2015, 370194. [Google Scholar] [CrossRef] [Green Version]
  50. Adkins, D.E. Machine Learning and Electronic Health Records: A Paradigm Shift. Am. J. Psychiatry 2017, 174, 93–94. [Google Scholar] [CrossRef]
  51. Van Santvoort, H.C.; Besselink, M.G.; Bakker, O.J.; Hofker, H.S.; Boermeester, M.A.; Dejong, C.H.; van Goor, H.; Schaapherder, A.F.; van Eijck, C.H.; Bollen, T.L.; et al. A step-up approach or open necrosectomy for necrotizing pancreatitis. N. Engl. J. Med. 2010, 362, 1491–1502. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  52. Raraty, M.G.; Halloran, C.M.; Dodd, S.; Ghaneh, P.; Connor, S.; Evans, J.; Sutton, R.; Neoptolemos, J.P. Minimal access retroperitoneal pancreatic necrosectomy: Improvement in morbidity and mortality with a less invasive approach. Ann. Surg. 2010, 251, 787–793. [Google Scholar] [CrossRef] [PubMed]
  53. Gomatos, I.P.; Halloran, C.M.; Ghaneh, P.; Raraty, M.G.; Polydoros, F.; Evans, J.C.; Smart, H.L.; Yagati-Satchidanand, R.; Garry, J.M.; Whelan, P.A.; et al. Outcomes From Minimal Access Retroperitoneal and Open Pancreatic Necrosectomy in 394 Patients With Necrotizing Pancreatitis. Ann. Surg. 2016, 263, 992–1001. [Google Scholar] [CrossRef] [PubMed]
  54. Bang, J.Y.; Arnoletti, J.P.; Holt, B.A.; Sutton, B.; Hasan, M.K.; Navaneethan, U.; Feranec, N.; Wilcox, C.M.; Tharian, B.; Hawes, R.H.; et al. An Endoscopic Transluminal Approach, Compared With Minimally Invasive Surgery, Reduces Complications and Costs for Patients With Necrotizing Pancreatitis. Gastroenterology 2019, 156, 1027–1040.e3. [Google Scholar] [CrossRef] [Green Version]
  55. Hollemans, R.A.; Bakker, O.J.; Boermeester, M.A.; Bollen, T.L.; Bosscha, K.; Bruno, M.J.; Buskens, E.; Dejong, C.H.; van Duijvendijk, P.; van Eijck, C.H.; et al. Superiority of Step-up Approach vs Open Necrosectomy in Long-term Follow-up of Patients With Necrotizing Pancreatitis. Gastroenterology 2019, 156, 1016–1026. [Google Scholar] [CrossRef] [Green Version]
  56. Van Brunschot, S.; Hollemans, R.A.; Bakker, O.J.; Besselink, M.G.; Baron, T.H.; Beger, H.G.; Boermeester, M.A.; Bollen, T.L.; Bruno, M.J.; Carter, R.; et al. Minimally invasive and endoscopic versus open necrosectomy for necrotising pancreatitis: A pooled analysis of individual data for 1980 patients. Gut 2018, 67, 697–706. [Google Scholar] [CrossRef]
  57. Van Grinsven, J.; van Dijk, S.M.; Dijkgraaf, M.G.; Boermeester, M.A.; Bollen, T.L.; Bruno, M.J.; van Brunschot, S.; Dejong, C.H.; van Eijck, C.H.; van Lienden, K.P.; et al. Postponed or immediate drainage of infected necrotizing pancreatitis (POINTER trial): Study protocol for a randomized controlled trial. Trials 2019, 20, 239. [Google Scholar] [CrossRef] [Green Version]
  58. Tenner, S.; Baillie, J.; DeWitt, J.; Vege, S.S. American College of Gastroenterology guideline: Management of acute pancreatitis. Am. J. Gastroenterol. 2013, 108, 1400–1416. [Google Scholar] [CrossRef]
  59. Yokoe, M.; Takada, T.; Mayumi, T.; Yoshida, M.; Isaji, S.; Wada, K.; Itoi, T.; Sata, N.; Gabata, T.; Igarashi, H.; et al. Japanese guidelines for the management of acute pancreatitis: Japanese Guidelines 2015. J. Hepatobiliary Pancreat. Sci. 2015, 22, 405–432. [Google Scholar] [CrossRef]
  60. Italian Association for the Study of the Pancreas (AISP); Pezzilli, R.; Zerbi, A.; Campra, D.; Capurso, G.; Golfieri, R.; Arcidiacono, P.G.; Billi, P.; Butturini, G.; Calculli, L.; et al. Consensus guidelines on severe acute pancreatitis. Dig. Liver Dis. 2015, 47, 532–543. [Google Scholar] [CrossRef]
  61. Schepers, N.J.; Bakker, O.J.; Besselink, M.G.; Ahmed Ali, U.; Bollen, T.L.; Gooszen, H.G.; Van Santvoort, H.C.; Bruno, M.J. Impact of characteristics of organ failure and infected necrosis on mortality in necrotising pancreatitis. Gut 2019, 68, 1044–1051. [Google Scholar] [CrossRef] [PubMed]
  62. Guo, Q.; Li, A.; Xia, Q.; Liu, X.; Tian, B.; Mai, G.; Huang, Z.; Chen, G.; Tang, W.; Jin, X.; et al. The role of organ failure and infection in necrotizing pancreatitis: A prospective study. Ann. Surg. 2014, 259, 1201–1207. [Google Scholar] [CrossRef] [PubMed]
  63. Shi, N.; Liu, T.; de la Iglesia-Garcia, D.; Deng, L.; Jin, T.; Lan, L.; Zhu, P.; Hu, W.; Zhou, Z.; Singh, V.; et al. Duration of organ failure impacts mortality in acute pancreatitis. Gut 2020, 69, 604–605. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  64. Lan, L.; Guo, Q.; Zhang, Z.; Zhao, W.; Yang, X.; Lu, H.; Zhou, Z.; Zhou, X. Classification of Infected Necrotizing Pancreatitis for Surgery Within or Beyond 4 Weeks Using Machine Learning. Front. Bioeng. Biotechnol. 2020, 8, 541. [Google Scholar] [CrossRef]
  65. Mofidi, R.; Duff, M.D.; Madhavan, K.K.; Garden, O.J.; Parks, R.W. Identification of Severe Acute Pancreatitis Using an Artificial Neural Network. Surgery 2007, 141, 59–66. [Google Scholar] [CrossRef]
  66. Ding, N.; Guo, C.; Li, C.; Zhou, Y.; Chai, X. An Artificial Neural Networks Model for Early Predicting in-Hospital Mortality in Acute Pancreatitis in Mimic-Iii. Biomed. Res. Int. 2021, 202, 6638919. [Google Scholar] [CrossRef]
Jpm 12 00616 g001 550
Figure 1. The flow chart of this study.
Figure 1. The flow chart of this study.
Jpm 12 00616 g001
Jpm 12 00616 g002 550
Figure 2. The relationship between important variable (the top five) and outcome. The first column (a1–a5) displays the top features for intervention, the second column (b1–b5) is for death in the intervention group, and the third column (c1–c5) is for death in the non-intervention group.
Figure 2. The relationship between important variable (the top five) and outcome. The first column (a1–a5) displays the top features for intervention, the second column (b1–b5) is for death in the intervention group, and the third column (c1–c5) is for death in the non-intervention group.
Jpm 12 00616 g002
Table
Table 1. Characteristics between intervention and non-intervention patients with AP.
Table 1. Characteristics between intervention and non-intervention patients with AP.
CharacteristicTotal
(n = 2846)		Intervention
(n = 132)		Non-Intervention
(n = 2714)		p
Demographics
Age, year (M[Q])46 (38–58)48 (39–62)46 (38–57)0.125
Male (%)1822 (64.0)88 (66.7)1734 (63.9)0.578
CCI (M[Q])0 (0–1)0 (0–1)0 (0–1)0.260
Modified CCI, (M[Q])0 (0–1)0 (0–2)0 (0–1)0.176
ASA (%) 0.005
I2120 (74.5)108 (81.8)2012 (74.1)
II573 (20.1)13 (9.8)560 (20.6)
III153 (5.4)11 (9.3)142 (5.2)
From onset to admission, h (M[Q])18 (10–27)24 (10–33)18 (10–27)0.001
Aetiology (%) 0.063
Biliary1069 (37.6)65 (49.2)1004 (37.0)
Hypertriglyceridemia805 (28.3)33 (25.0)772 (28.4)
Alcoholics216 (7.6)8 (6.1)208 (7.7)
ERCP20 (0.7)0 (0.0)20 (0.7)
Drug-induced8 (0.3)1 (0.8)7 (0.3)
Others728 (25.6)25 (18.9)703 (25.9)
Laboratory tests
WBC, 109/L (M[Q])12.9 (10.01–16.30)14.3 (10.43–17.35)12.87 (10–16.26)0.011
Neutrophils, 109/L (M[Q])11.00 (8.10–14.34)12.66 (9.17–15.61)10.95 (8.05–14.28)0.001
Lymphocyte, 109/L (M[Q])1.01 (0.70–1.49)0.96 (0.62–1.53)1.02 (0.70–1.49)0.352
Hematocrit, % (M[Q])43 (39–46)45 (40–49)43 (39.3–46)0.003
Urea, mmol/L (M[Q])5.00 (3.72–6.60)6.36 (4.79–8.61)4.92 (3.70–6.47)<0.001 *
Creatinine, μmmol/L (M[Q])74 (62–89)87 (68–134)73 (62–88)<0.001 *
Albumin, g/L (M[Q])42.0 (38.2–45.3)37.3 (32.3–43.2)42.1 (38.6–45.4)<0.001 *
CRP, mg/L (M[Q])28.7 (3.31–142)158 (20–22)26 (2.7–136)<0.001 *
Clinical scoring systems
SOFA (M[Q])0 (0–2)2 (0–3)0 (0–1)<0.001 *
BISAP (M[Q])1 (0–2)2 (1–2)1 (0–2)<0.001 *
SIRS (M[Q])1 (1–2)2 (1–3)1 (1–2)<0.001 *
APACHE II (M[Q])4 (2–7)7 (4–11)4 (2–7)<0.001 *
RAC (%) <0.001 *
Mild1373 (48.2)4 (3.0)1369 (50.4)
Moderately severe888 (31.2)29 (22.0)859 (31.7)
Severe585 (20.6)99 (75.0)486 (17.9)
Worst MCTSI (M[Q])2 (0–6)8 (6–10)2 (0–6)<0.001 *
From admission to worst MCTSI, day (M[Q])0 (0–2)2 (1–9)0 (0–1)<0.001 *
Clinical outcomes
Local complication
APFC (%)1121 (39.4)98 (74.2)1023 (37.7)<0.001 *
Necrosis (%)416 (14.6)84 (63.6)332 (12.2)<0.001 *
Single organ failure
Pulmonary failure (%) <0.001 *
TOF417 (14.7)8 (6.1)409 (15.1)
POF578 (20.3)99 (75.0)479 (17.6)
Onset of pulmonary failure, day (M[Q])0 (0–1)1 (1–2)0 (0–1)<0.001 *
Duration of pulmonary failure, day (M[Q])0 (0–1)12.5 (1–24)0 (0–1)<0.001 *
Circulatory failure (%) <0.001 *
TOF42 (1.5)9 (6.8)33 (1.2)
POF111 (3.9)42 (31.8)69 (2.5)
Onset of circulatory failure, day (M[Q])0 (0–0)0 (0–3)0 (0–0)<0.001 *
Duration of circulatory failure, day (M[Q])0 (0–0)0 (0–3)0 (0–0)<0.001 *
Renal failure (%) <0.001 *
TOF57 (2.0)15 (11.4)42 (1.5)
POF104 (3.7)29 (22.0)75 (2.8)
Onset of renal failure, day (M[Q])0 (0–0)0 (0–1)0 (0–0)<0.001 *
Duration of renal failure, day (M[Q])0 (0–0)0 (0–1)0 (0–0)<0.001 *
Pleural effusion (%)268 (9.4)15 (11.4)253 (9.3)0.528
IPN (%)85 (3.0)81 (61.4)4 (0.1)<0.001 *
Extrapancreatic infection (%) <0.001 *
Bacteremia75 (2.6)24 (18.2)51 (1.9)
Lung and others147 (5.2)31 (23.5)116 (4.3)
AP, acute pancreatitis; CCI, Charlson comorbidity index; ASA, American society of anesthesiologists; ERCP, endoscopic retrograde cholangiopancreatography; WBC, white blood cell count; CRP, C-reactive protein; SOFA, sequential organ failure assessment; BISAP, bedside index of severity in acute pancreatitis; SIRS, systemic inflammatory response syndrome; APACHE II, acute physiology and chronic health evaluation II; RAC, revised Atlanta classification; MCTSI, modified computerized tomographic severity index; APFC, acute peripancreatic fluid collection; IPN, infected pancreatic necrosis; TOF, transient organ failure; POF, persistent organ failure; M[Q], median and inter-quartile range for quantitative data; (%), number and percentage for categorical variables; * p < 0.05, indicates statistical significance.
Table
Table 2. Top 10 important features for intervention or mortality among the three groups.
Table 2. Top 10 important features for intervention or mortality among the three groups.
InterventionDeath in InterventionDeath in Non-Intervention
VariableMean Decrease GiniVariableMean Decrease GiniVariableMean Decrease Gini
Duration of pulmonary failure23.78Duration of renal failure2.54Renal failure10.99
Neutrophils10.18Duration of circulatory failure2.52Circulatory failure10.00
Albumin9.91Onset of circulatory failure2.35Duration of circulatory failure8.62
Lymphocytes9.06Circulatory failure2.21Onset of circulatory failure7.70
Creatine8.36Renal failure1.60Duration of renal failure6.37
Age8.27Creatinine1.59Onset of renal failure5.46
Hematocrit8.09Duration of pulmonary failure1.38APACHE II4.72
Onset of circulatory failure7.95Urea1.19Duration of pulmonary failure4.45
APACHE II6.70APACHE II1.19Creatinine4.09
Duration of circulatory failure5.48CRP0.92WBC3.80
APACHE II, acute physiology and chronic health evaluation II; CRP, C-reactive protein; WBC, white blood cell count.
Table
Table 3. Performance of prediction for the three groups.
Table 3. Performance of prediction for the three groups.
AccuracyAUCSensitivitySpecificityLikelihood Ratio (+)Likelihood Ratio (−)
Predicting Intervention in AP (n = 2846)
Validation (n = 569)0.960.900.740.9722.30.27
Test (n = 569)0.970.910.760.9725.50.35
Predicting Death in Intervention (n = 132)
Validation (n = 26)0.840.890.740.866.140.30
Test (n = 26)0.820.890.820.824.800.28
Predicting Death in Non-Intervention (n = 2714)
Validation (n = 543)0.980.980.760.9969.60.25
Test (n = 543)0.980.990.770.9971.90.31
Table
Table 4. Performance of prediction with ML models and clinical scoring systems in the test set.
Table 4. Performance of prediction with ML models and clinical scoring systems in the test set.
SensitivitySpecificityLikelihood Ratio (+)Post-Test Probability (%)
Intervention (4.64% pre-test probability)
ML model0.760.9725.555.4
SOFA0.080.985.019.6
BISAP0.080.984.317.3
SIRS0.060.983.213.5
APACHE II0.080.985.420.8
Worst MCTSI0.130.9912.738.2
Death in intervention (21.97% pre-test probability)
ML model0.820.824.857.5
SOFA0.690.783.751.0
BISAP0.520.964.455.3
SIRS0.440.842.339.3
APACHE II0.690.926.464.3
Worst MCTSI0.480.692.036.0
Death in non-intervention (3.39% pre-test probability)
ML model0.770.9971.971.6
SOFA0.110.9921.543.0
BISAP0.140.9932.553.3
SIRS0.070.9912.730.8
APACHE II0.150.9930.251.4
Worst MCTSI0.030.961.03.4
ML, machine learning; SOFA, sequential organ failure assessment; BISAP, bedside index of severity in acute pancreatitis; SIRS, systemic inflammatory response syndrome; APACHE II, acute physiology and chronic health evaluation II; MCTSI, modified computerized tomographic severity index.
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Share and Cite

MDPI and ACS Style

Shi, N.; Lan, L.; Luo, J.; Zhu, P.; Ward, T.R.W.; Szatmary, P.; Sutton, R.; Huang, W.; Windsor, J.A.; Zhou, X.; et al. Predicting the Need for Therapeutic Intervention and Mortality in Acute Pancreatitis: A Two-Center International Study Using Machine Learning. J. Pers. Med. 2022, 12, 616. https://doi.org/10.3390/jpm12040616

AMA Style

Shi N, Lan L, Luo J, Zhu P, Ward TRW, Szatmary P, Sutton R, Huang W, Windsor JA, Zhou X, et al. Predicting the Need for Therapeutic Intervention and Mortality in Acute Pancreatitis: A Two-Center International Study Using Machine Learning. Journal of Personalized Medicine. 2022; 12(4):616. https://doi.org/10.3390/jpm12040616

Chicago/Turabian Style

Shi, Na, Lan Lan, Jiawei Luo, Ping Zhu, Thomas R. W. Ward, Peter Szatmary, Robert Sutton, Wei Huang, John A. Windsor, Xiaobo Zhou, and et al. 2022. "Predicting the Need for Therapeutic Intervention and Mortality in Acute Pancreatitis: A Two-Center International Study Using Machine Learning" Journal of Personalized Medicine 12, no. 4: 616. https://doi.org/10.3390/jpm12040616

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop