Abstract
Pre-operative prediction of post-surgical recovery for patients is vital for clinical decision-making and personalized treatments, especially with lumbar spine surgery, where patients exhibit highly heterogeneous outcomes. Existing predictive tools mainly rely on traditional Patient-Reported Outcome Measures (PROMs), which fail to capture the long-term dynamics of patient conditions before the surgery. Moreover, existing studies focus on predicting a single surgical outcome. However, recovery from spine surgery is multi-dimensional, including multiple distinctive but interrelated outcomes, such as pain interference, physical function, and quality of recovery. In recent years, the emergence of smartphones and wearable devices has presented new opportunities to capture longitudinal and dynamic information regarding patients' conditions outside the hospital. This paper proposes a novel machine learning approach, Multi-Modal Multi-Task Learning (M3TL), using smartphones and wristbands to predict multiple surgical outcomes after lumbar spine surgeries. We formulate the prediction of pain interference, physical function, and quality of recovery as a multi-task learning (MTL) problem. We leverage multi-modal data to capture the static and dynamic characteristics of patients, including (1) traditional features from PROMs and Electronic Health Records (EHR), (2) Ecological Momentary Assessment (EMA) collected from smartphones, and (3) sensing data from wristbands. Moreover, we introduce new features derived from the correlation of EMA and wearable features measured within the same time frame, effectively enhancing predictive performance by capturing the interdependencies between the two data modalities. Our model interpretation uncovers the complementary nature of the different data modalities and their distinctive contributions toward multiple surgical outcomes. Furthermore, through individualized decision analysis, our model identifies personal high risk factors to aid clinical decision making and approach personalized treatments. In a clinical study involving 122 patients undergoing lumbar spine surgery, our M3TL model outperforms a diverse set of baseline methods in predictive performance, demonstrating the value of integrating multi-modal data and learning from multiple surgical outcomes. This work contributes to advancing personalized peri-operative care with accurate pre-operative predictions of multi-dimensional outcomes.
- Martín Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Greg S Corrado, Andy Davis, Jeffrey Dean, Matthieu Devin, et al. 2016. Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467 (2016).Google Scholar
- Michelle Accardi-Ravid, Linda Eaton, Alexa Meins, Daniel Godfrey, Debra Gordon, Ivan Lesnik, and Ardith Doorenbos. 2020. A qualitative descriptive Study of patient experiences of pain before and after spine surgery. Pain Medicine 21, 3 (2020), 604--612.Google ScholarCross Ref
- Hasan S Ahmad, Andrew I Yang, Gregory W Basil, Disha Joshi, Michael Y Wang, William C Welch, and Jang W Yoon. 2022. Developing a prediction model for identification of distinct perioperative clinical stages in spine surgery with smartphone-based mobility data. Neurosurgery 90, 5 (2022), 588--596.Google ScholarCross Ref
- Sajid Ali, Shaker El-Sappagh, Farman Ali, Muhammad Imran, and Tamer Abuhmed. 2022. Multitask deep learning for cost-effective prediction of patient's length of stay and readmission state using multimodal physical activity sensory data. IEEE Journal of Biomedical and Health Informatics 26, 12 (2022), 5793--5804.Google ScholarCross Ref
- Renée Allvin, Katarina Berg, Ewa Idvall, and Ulrica Nilsson. 2007. Postoperative recovery: a concept analysis. Journal of Advanced Nursing 57, 5 (Mar 2007), 552--558. https://doi.org/10.1111/j.1365-2648.2006.04156.xGoogle ScholarCross Ref
- Saad M Alsaadi, James H McAuley, Julia M Hush, Serigne Lo, Delwyn J Bartlett, Roland R Grunstein, and Chris G Maher. 2014. The bidirectional relationship between pain intensity and sleep disturbance/quality in patients with low back pain. The Clinical journal of pain 30, 9 (2014), 755--765.Google Scholar
- Tihomir Asparouhov, Ellen L Hamaker, and Bengt Muthén. 2018. Dynamic structural equation models. Structural equation modeling: a multidisciplinary journal 25, 3 (2018), 359--388.Google Scholar
- Sangwon Bae, Anind K Dey, and Carissa A Low. 2016. Using passively collected sedentary behavior to predict hospital readmission. In Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing. 616--621.Google ScholarDigital Library
- A Barzouhi, C Vleggeert-Lankamp, G Lycklama a Nijeholt, S Boden, D Davis, T Dina, N Boos, R Rieder, V Schade, E Carragee, et al. 2017. Systematic Literature Review of Imaging Features of Spinal Degeneration in Asymptomatic Populations. manuelletherapie 21, 02 (2017), 54--55.Google Scholar
- Jeremiah W Bertz, David H Epstein, and Kenzie L Preston. 2018. Combining ecological momentary assessment with objective, ambulatory measures of behavior and physiology in substance-use research. Addictive behaviors 83 (2018), 5--17.Google Scholar
- Marius Breitmayer, Michael Stach, Robin Kraft, Johannes Allgaier, Manfred Reichert, Winfried Schlee, Thomas Probst, Berthold Langguth, and Rüdiger Pryss. 2023. Predicting the presence of tinnitus using ecological momentary assessments. Scientific Reports 13, 1 (2023), 8989.Google ScholarCross Ref
- Jason P Burnham, Chenyang Lu, Lauren H Yaeger, Thomas C Bailey, and Marin H Kollef. 2018. Using wearable technology to predict health outcomes: a literature review. Journal of the American Medical Informatics Association 25, 9 (2018), 1221--1227.Google ScholarCross Ref
- David Cella, Susan Yount, Nan Rothrock, Richard Gershon, Karon Cook, Bryce Reeve, Deborah Ader, James F. Fries, Bonnie Bruce, and Mattias Rose. 2007. The Patient-Reported Outcomes Measurement Information System (PROMIS). Medical Care 45, Suppl 1 (May 2007), S3-S11. https://doi.org/10.1097/01.mlr.0000258615.42478.55Google ScholarCross Ref
- Tongjia Chu, Chen Zhao, Jian Zhang, Kehang Duan, Mingyang Li, Tianqi Zhang, Shengnan Lv, Huan Liu, and Feng Wei. 2022. Application of a convolutional neural network for multitask learning to simultaneously predict microvascular invasion and vessels that encapsulate tumor clusters in hepatocellular carcinoma. Annals of Surgical Oncology 29, 11 (2022), 6774--6783.Google ScholarCross Ref
- Heidy Cos, Dingwen Li, Gregory Williams, Jeffrey Chininis, Ruixuan Dai, Jingwen Zhang, Rohit Srivastava, Lacey Raper, Dominic Sanford, William Hawkins, et al. 2021. Predicting outcomes in patients undergoing pancreatectomy using wearable technology and machine learning: prospective cohort study. Journal of medical Internet research 23, 3 (2021), e23595.Google ScholarCross Ref
- Tom J Crijns, David N Bernstein, David Ring, Ronald M Gonzalez, Danielle M Wilbur, and Warren C Hammert. 2019. Depression and pain interference correlate with physical function in patients recovering from hand surgery. Hand 14, 6 (2019), 830--835.Google ScholarCross Ref
- Rebecca J Crochiere, Fengqing Zhang, Adrienne S Juarascio, Stephanie P Goldstein, J Graham Thomas, and Evan M Forman. 2021. Comparing ecological momentary assessment to sensor-based approaches in predicting dietary lapse. Translational behavioral medicine 11, 12 (2021), 2099--2109.Google Scholar
- Ruixuan Dai, Thomas Kannampallil, Jingwen Zhang, Nan Lv, Jun Ma, and Chenyang Lu. 2022. Multi-task learning for randomized controlled trials: a case study on predicting depression with wearable data. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 6, 2 (2022), 1--23.Google ScholarDigital Library
- Bradley Efron and Robert Tibshirani. 1997. Improvements on cross-validation: the 632+ bootstrap method. J. Amer. Statist. Assoc. 92, 438 (1997), 548--560.Google Scholar
- James B Elsner and Anastasios A Tsonis. 1996. Singular spectrum analysis: a new tool in time series analysis. Springer Science & Business Media.Google Scholar
- Jeremy CT Fairbank and Paul B Pynsent. 2000. The Oswestry disability index. Spine 25, 22 (2000), 2940--2953.Google ScholarCross Ref
- Lynne M Feehan, Jasmina Geldman, Eric C Sayre, Chance Park, Allison M Ezzat, Ju Young Yoo, Clayon B Hamilton, and Linda C Li. 2018. Accuracy of Fitbit devices: systematic review and narrative syntheses of quantitative data. JMIR mHealth and uHealth 6, 8 (2018), e10527.Google Scholar
- Chris Fifty, Ehsan Amid, Zhe Zhao, Tianhe Yu, Rohan Anil, and Chelsea Finn. 2021. Efficiently identifying task groupings for multi-task learning. Advances in Neural Information Processing Systems 34 (2021), 27503--27516.Google Scholar
- M Frumkin, J Greenberg, J Zhang, S Javeed, Z Xu, B Benedict, K Botterbush, W Ray, C Lu, and T Rodebaugh. 2024. In-Vivo Assessment of Movement-Evoked Pain using Digital Technology in Patients with Chronic Back Pain: Implications for treatment personalization. (2024).Google Scholar
- Madelyn R Frumkin, Jacob K Greenberg, Preston Boyd, Saad Javeed, Bulenda Shayo, Jin Shin, Elizabeth A Wilson, Justin K Zhang, Michael JL Sullivan, Simon Haroutounian, et al. 2023. Establishing the reliability, validity, and prognostic utility of the momentary pain catastrophizing scale for use in ecological momentary assessment research. The Journal of Pain 24, 8 (2023), 1423--1433.Google ScholarCross Ref
- Hans J Gerbershagen, Sanjay Aduckathil, Albert JM van Wijck, Linda M Peelen, Cor J Kalkman, and Winfried Meissner. 2013. Pain intensity on the first day after surgery: a prospective cohort study comparing 179 surgical procedures. Anesthesiology 118, 4 (2013), 934--944.Google ScholarCross Ref
- Hans J. Gerbershagen, Sanjay Aduckathil, Albert J. M. van Wijck, Linda M. Peelen, Cor J. Kalkman, and Winfried Meissner. 2013. Pain Intensity on the First Day after Surgery. Anesthesiology 118, 4 (Apr 2013), 934--944. https://doi.org/10.1097/aln.0b013e31828866b3Google ScholarCross Ref
- Hamid Reza Ghafarian Malamiri, Iman Rousta, Haraldur Olafsson, Hadi Zare, and Hao Zhang. 2018. Gap-filling of MODIS time series land surface temperature (LST) products using singular spectrum analysis (SSA). Atmosphere 9, 9 (2018), 334.Google ScholarCross Ref
- Debra B Gordon, June L Dahl, Christine Miaskowski, Bill McCarberg, Knox H Todd, Judith A Paice, Arthur G Lipman, Marilyn Bookbinder, Steve H Sanders, Dennis C Turk, et al. 2005. American pain society recommendations for improving the quality of acute and cancer pain management: American Pain Society Quality of Care Task Force. Archives of internal medicine 165, 14 (2005), 1574--1580.Google Scholar
- JK Greenberg, M Frumkin, Z Xu, J Zhang, S Javeed, JK Zhang, B Benedict, K Botterbush, S Yakdan, CA Molina, et al. 2024. Preoperative Mobile Health Data Improve Predictions of Recovery From Lumbar Spine Surgery. Neurosurgery (2024).Google Scholar
- Jacob K Greenberg, Madelyn R Frumkin, Saad Javeed, Justin K Zhang, Ruixuan Dai, Camilo A Molina, Brenton H Pennicooke, Nitin Agarwal, Paul Santiago, Matthew L Goodwin, et al. 2023. Feasibility and acceptability of a preoperative multimodal mobile health assessment in spine surgery candidates. Neurosurgery 92, 3 (2023), 538--546.Google ScholarCross Ref
- Jacob K Greenberg, Michael P Kelly, Joshua M Landman, Justin K Zhang, Shay Bess, Justin S Smith, Lawrence G Lenke, Christopher I Shaffrey, and Keith H Bridwell. 2022. Individual differences in postoperative recovery trajectories for adult symptomatic lumbar scoliosis. Journal of Neurosurgery: Spine 37, 3 (2022), 429--438.Google ScholarCross Ref
- Ellen L Hamaker, Tihomir Asparouhov, Annette Brose, Florian Schmiedek, and Bengt Muthén. 2018. At the frontiers of modeling intensive longitudinal data: Dynamic structural equation models for the affective measurements from the COGITO study. Multivariate behavioral research 53, 6 (2018), 820--841.Google Scholar
- Richard Hardstone, Simon-Shlomo Poil, Giuseppina Schiavone, Rick Jansen, Vadim V Nikulin, Huibert D Mansvelder, and Klaus Linkenkaer-Hansen. 2012. Detrended fluctuation analysis: a scale-free view on neuronal oscillations. Frontiers in physiology 3 (2012), 450.Google Scholar
- Lu He, Sreenath Chalil Madathil, Greg Servis, and Mohammad T Khasawneh. 2021. Neural network-based multi-task learning for inpatient flow classification and length of stay prediction. Applied Soft Computing 108 (2021), 107483.Google ScholarCross Ref
- Jeffrey J Hébert, Edward Abraham, Niels Wedderkopp, Erin Bigney, Eden Richardson, Mariah Darling, Hamilton Hall, Charles G Fisher, Y Raja Rampersaud, Kenneth C Thomas, et al. 2020. Preoperative factors predict postoperative trajectories of pain and disability following surgery for degenerative lumbar spinal stenosis. Spine 45, 21 (2020), E1421.Google ScholarCross Ref
- Natasha Jaques, Sara Taylor, Akane Sano, and Rosalind Picard. 2015. Multi-task, multi-kernel learning for estimating individual wellbeing. In Proc. NIPS Workshop on Multimodal Machine Learning, Montreal, Quebec, Vol. 898. 3.Google Scholar
- Mark P Jensen and Dennis C Turk. 2014. Contributions of psychology to the understanding and treatment of people with chronic pain: why it matters to ALL psychologists. American Psychologist 69, 2 (2014), 105.Google ScholarCross Ref
- Wenyu Jiang and Richard Simon. 2007. A comparison of bootstrap methods and an adjusted bootstrap approach for estimating the prediction error in microarray classification. Statistics in medicine 26, 29 (2007), 5320--5334.Google Scholar
- Ara Jo, Bryan D Coronel, Courtney E Coakes, and Arch G Mainous III. 2019. Is there a benefit to patients using wearable devices such as Fitbit or health apps on mobiles? A systematic review. The American journal of medicine 132, 12 (2019), 1394--1400.Google Scholar
- Rudolph Emil Kalman. 1960. A New Approach to Linear Filtering and Prediction Problems. Transactions of the ASME-Journal of Basic Engineering 82, Series D (1960), 35--45.Google Scholar
- Saddam F Kanaan, Paul M Arnold, Douglas C Burton, Hung-Wen Yeh, Lindsay Loyd, and Neena K Sharma. 2015. Investigating and predicting early lumbar spine surgery outcomes. Journal of allied health 44, 2 (2015), 83--90.Google Scholar
- Saddam F Kanaan, Lemuel R Waitman, Hung-Wen Yeh, Paul M Arnold, Douglas C Burton, and Neena K Sharma. 2015. Structural equation model analysis of the length-of-hospital stay after lumbar spine surgery. The Spine Journal 15, 4 (2015), 612--621.Google ScholarCross Ref
- M Karas, N Marinsek, J Goldhahn, L Foschini, E Ramirez, and I Clay. [n. d.]. Predicting Subjective Recovery from Lower Limb Surgery Using Consumer Wearables. Digit Biomark. 2020; 4 (Suppl 1): 73--86. doi: 10.1159/000511531.Google ScholarCross Ref
- Alex Kendall, Yarin Gal, and Roberto Cipolla. 2018. Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In Proceedings of the IEEE conference on computer vision and pattern recognition. 7482--7491.Google Scholar
- Richard Kendall, Bill Wagner, Darrel Brodke, Jerry Bounsanga, Maren Voss, Yushan Gu, Ryan Spiker, Brandon Lawrence, and Man Hung. 2018. The relationship of PROMIS pain interference and physical function scales. Pain Medicine 19, 9 (2018), 1720--1724.Google ScholarCross Ref
- Sara Khor, Danielle Lavallee, Amy M Cizik, Carlo Bellabarba, Jens R Chapman, Christopher R Howe, Dawei Lu, A Alex Mohit, Rod J Oskouian, Jeffrey R Roh, et al. 2018. Development and validation of a prediction model for pain and functional outcomes after lumbar spine surgery. JAMA surgery 153, 7 (2018), 634--642.Google Scholar
- Ho-Joong Kim, Joon-Hee Park, Jang-Woo Kim, Kyoung-Tak Kang, Bong-Soon Chang, Choon-Ki Lee, and Jin S Yeom. 2014. Prediction of postoperative pain intensity after lumbar spinal surgery using pain sensitivity and preoperative back pain severity. Pain medicine 15, 12 (2014), 2037--2045.Google Scholar
- Zachary D King, Judith Moskowitz, Begum Egilmez, Shibo Zhang, Lida Zhang, Michael Bass, John Rogers, Roozbeh Ghaffari, Laurie Wakschlag, and Nabil Alshurafa. 2019. Micro-stress EMA: A passive sensing framework for detecting in-the-wild stress in pregnant mothers. Proceedings of the ACM on interactive, mobile, wearable and ubiquitous technologies 3, 3 (2019), 1--22.Google ScholarDigital Library
- Atesh Koul, Cristina Becchio, and Andrea Cavallo. 2018. Cross-validation approaches for replicability in psychology. Frontiers in psychology 9 (2018), 1117.Google Scholar
- Kurt Kroenke, Robert L. Spitzer, and Janet B. W. Williams. 2001. The PHQ-9: Validity of a brief depression severity measure. Journal of General Internal Medicine 16, 9 (Sep 2001), 606--613. https://doi.org/10.1046/j.1525-1497.2001.016009606.xGoogle ScholarCross Ref
- CASEY K LEE, HAROLD T HANSEN, and ANDREW B WEISS. 1978. Developmental lumbar spinal stenosis: Pathology and surgical treatment. Spine 3, 3 (1978), 246--255.Google ScholarCross Ref
- Lukas Liebel and Marco Körner. 2018. Auxiliary tasks in multi-task learning. arXiv preprint arXiv:1805.06334 (2018).Google Scholar
- Breton Line, Shay Bess, Jeffrey L Gum, Richard Hostin, Khaled Kebaish, Christopher Ames, Douglas Burton, Gregory Mundis, Robert Eastlack, Munish Gupta, et al. 2022. Opioid use prior to surgery is associated with worse preoperative and postoperative patient reported quality of life and decreased surgical cost effectiveness for symptomatic adult spine deformity; a matched cohort analysis. North American Spine Society Journal (NASSJ) 9 (2022), 100096.Google ScholarCross Ref
- Carissa A Low, Dana H Bovbjerg, Steven Ahrendt, M Haroon Choudry, Matthew Holtzman, Heather L Jones, James F Pingpank Jr, Lekshmi Ramalingam, Herbert J Zeh III, Amer H Zureikat, et al. 2018. Fitbit step counts during inpatient recovery from cancer surgery as a predictor of readmission. Annals of Behavioral Medicine 52, 1 (2018), 88--92.Google ScholarCross Ref
- Scott M Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. Advances in neural information processing systems 30 (2017).Google Scholar
- Nicolai Maldaner, Marketa Sosnova, Anna M Zeitlberger, Michal Ziga, Oliver P Gautschi, Luca Regli, Astrid Weyerbrock, and Martin N Stienen. 2020. Evaluation of the 6-minute walking test as a smartphone app-based self-measurement of objective functional impairment in patients with lumbar degenerative disc disease. Journal of Neurosurgery: Spine 33, 6 (2020), 779--788.Google ScholarCross Ref
- Anne F Mannion, A Elfering, Ralph Staerkle, Astrid Junge, Dieter Grob, Jiri Dvorak, Nicola Jacobshagen, Norbert Karl Semmer, and Norbert Boos. 2007. Predictors of multidimensional outcome after spinal surgery. European Spine Journal 16 (2007), 777--786.Google ScholarCross Ref
- Matthew J McGirt, Scott L Parker, Silky Chotai, Deborah Pfortmiller, Jeffrey M Sorenson, Kevin Foley, and Anthony L Asher. 2017. Predictors of extended length of stay, discharge to inpatient rehab, and hospital readmission following elective lumbar spine surgery: introduction of the Carolina-Semmes Grading Scale. Journal of Neurosurgery: Spine 27, 4 (2017), 382--390.Google ScholarCross Ref
- Angus GK McNair, F MacKichan, JL Donovan, ST Brookes, KNL Avery, SM Griffin, T Crosby, and JM Blazeby. 2016. What surgeons tell patients and what patients want to know before major cancer surgery: a qualitative study. BMC cancer 16 (2016), 1--8.Google ScholarCross Ref
- Ralph J Mobbs, Kevin Phan, Monish Maharaj, and Prashanth J Rao. 2016. Physical activity measured with accelerometer and self-rated disability in lumbar spine surgery: a prospective study. Global Spine Journal 6, 5 (2016), 459--464.Google ScholarCross Ref
- Makoto Mori, Sanket S Dhruva, Arnar Geirsson, and Harlan M Krumholz. 2022. Characterization of multi-domain postoperative recovery trajectories after cardiac surgery using a digital platform. npj Digital Medicine 5, 1 (2022), 192.Google Scholar
- William Mualem, Sulaman Durrani, Nikita Lakomkin, Jamie Van Gompel, Alfredo Quiñones-Hinojosa, and Mohamad Bydon. 2022. Utilizing data from wearable technologies in the era of telemedicine to assess patient function and outcomes in neurosurgery: systematic review and time-trend analysis of the literature. World neurosurgery (2022).Google Scholar
- Manpreet S. Mundi, Paul A. Lorentz, Karen Grothe, Todd A. Kellogg, and Maria L. Collazo-Clavell. 2015. Feasibility of Smartphone-Based Education Modules and Ecological Momentary Assessment/Intervention in Pre-bariatric Surgery Patients. Obesity Surgery 25, 10 (Feb 2015), 1875--1881. https://doi.org/10.1007/s11695-015-1617-7Google ScholarCross Ref
- Lindsay D. Nelson, Jana Ranson, Adam R. Ferguson, Joseph Giacino, David O. Okonkwo, Alex B. Valadka, Geoffrey T. Manley, Michael A. McCrea, and the TRACK-TBI Investigators. 2017. Validating Multi-Dimensional Outcome Assessment Using the Traumatic Brain Injury Common Data Elements: An Analysis of the TRACK-TBI Pilot Study Sample. Journal of Neurotrauma 34, 22 (Nov 2017), 3158--3172. https://doi.org/10.1089/neu.2017.5139Google ScholarCross Ref
- Che Ngufor, Sudhindra Upadhyaya, Dennis Murphree, Daryl Kor, and Jyotishman Pathak. 2015. Multi-task learning with selective cross-task transfer for predicting bleeding and other important patient outcomes. In 2015 IEEE International conference on data science and advanced analytics (DSAA). IEEE, 1--8.Google ScholarCross Ref
- Che Ngufor, Sudhindra Upadhyaya, Dennis Murphree, Nageswar Madde, Daryl Kor, and Jyotishman Pathak. 2015. A heterogeneous multi-task learning for predicting RBC transfusion and perioperative outcomes. In Artificial Intelligence in Medicine: 15th Conference on Artificial Intelligence in Medicine, AIME 2015, Pavia, Italy, June 17-20, 2015. Proceedings 15. Springer, 287--297.Google ScholarCross Ref
- Jared Ou-Young, Stuart Boggett, Doa El-Ansary, Sandy Clarke-Errey, Colin Royse, and Andrea Bowyer. 2023. Identifying risk factors for poor multidimensional recovery after major surgery: A systematic review. Acta Anaesthesiologica Scandinavica 67, 10 (Jul 2023), 1294--1305. https://doi.org/10.1111/aas.14302Google ScholarCross Ref
- Diane Oyen and Terran Lane. 2012. Leveraging domain knowledge in multitask Bayesian network structure learning. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 26, 1091--1097.Google Scholar
- Fabian Pedregosa, Gaël Varoquaux, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, Peter Prettenhofer, Ron Weiss, Vincent Dubourg, et al. 2011. Scikit-learn: Machine learning in Python. the Journal of machine Learning research 12 (2011), 2825--2830.Google Scholar
- F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay. 2011. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research 12 (2011), 2825--2830.Google ScholarDigital Library
- Julie A Penley, Joe Tomaka, and John S Wiebe. 2002. The association of coping to physical and psychological health outcomes: A meta-analytic review. Journal of behavioral medicine 25 (2002), 551--603.Google ScholarCross Ref
- Prashanth J Rao, Kevin Phan, Monish M Maharaj, Matthew H Pelletier, William R Walsh, and Ralph J Mobbs. 2016. Accelerometers for objective evaluation of physical activity following spine surgery. Journal of Clinical Neuroscience 26 (2016), 14--18.Google ScholarCross Ref
- Rosalba Rosato, Valentina Palazzo, Felice Borghi, Marco Camanni, Andrea Puppo, Elena Maria Delpiano, Luca Pellegrino, Elisa Piovano, Alessio Rizzo, Monica Rolfo, et al. 2023. Factor structure of post-operative quality of recovery questionnaire (QoR-15): An Italian adaptation and validation. Frontiers in Psychology 13 (2023), 1096579.Google ScholarCross Ref
- Stefan Schneider, Doerte U Junghaenel, Joan E Broderick, Masakatsu Ono, Marcella May, and Arthur A Stone. 2021. II. Indices of pain intensity derived from ecological momentary assessments and their relationships with patient functioning: an individual patient data meta-analysis. The journal of pain 22, 4 (2021), 371--385.Google Scholar
- Saul Shiffman, Arthur A Stone, and Michael R Hufford. 2008. Ecological momentary assessment. Annu. Rev. Clin. Psychol. 4 (2008), 1--32.Google ScholarCross Ref
- Richard L Skolasky, Stephen T Wegener, Anica M Maggard, and Lee W Riley. 2014. The Impact of Reduction of Pain After Lumbar Spine Surgery. Spine 39, 17 (Aug 2014), 1426--1432. https://doi.org/10.1097/brs.0000000000000428Google ScholarCross Ref
- Matthew Smuck, Amir Muaremi, Patricia Zheng, Justin Norden, Aman Sinha, Richard Hu, and Christy Tomkins-Lane. 2018. Objective measurement of function following lumbar spinal stenosis decompression reveals improved functional capacity with stagnant real-life physical activity. The Spine Journal 18, 1 (2018), 15--21.Google ScholarCross Ref
- Joseph E Snavely, Joseph A Weiner, Daniel J Johnson, Wellington K Hsu, and Alpesh A Patel. 2021. Preoperative PROMIS scores predict postoperative outcomes in lumbar spine surgery patients. Spine 46, 17 (2021), 1139--1146.Google ScholarCross Ref
- Trevor Standley, Amir Zamir, Dawn Chen, Leonidas Guibas, Jitendra Malik, and Silvio Savarese. 2020. Which tasks should be learned together in multi-task learning?. In International Conference on Machine Learning. PMLR, 9120--9132.Google Scholar
- Martin N Stienen, Paymon G Rezaii, Allen L Ho, Anand Veeravagu, Corinna C Zygourakis, Christy Tomkins-Lane, Jon Park, John K Ratliff, and Atman M Desai. 2020. Objective activity tracking in spine surgery: a prospective feasibility study with a low-cost consumer grade wearable accelerometer. Scientific Reports 10, 1 (2020), 4939.Google ScholarCross Ref
- AA Stone, JE Broderick, RE Goldman, DU Junghaenel, A Bolton, M May, and S Schneider. 2020. Indices of pain intensity derived from ecological momentary assessments: rationale and stakeholder interviews. Journal of Pain,(under review)[Europe PMC free article][Abstract][Google Scholar] (2020).Google Scholar
- Sneha Subramaniam, Jeffrey J Aalberg, Rainier P Soriano, and Celia M Divino. 2018. New 5-factor modified frailty index using American College of Surgeons NSQIP data. Journal of the American College of Surgeons 226, 2 (2018), 173--181.Google ScholarCross Ref
- Michael JL Sullivan, Scott R Bishop, and Jayne Pivik. 1995. The pain catastrophizing scale: development and validation. Psychological assessment 7, 4 (1995), 524.Google Scholar
- Olga Troyanskaya, Michael Cantor, Gavin Sherlock, Pat Brown, Trevor Hastie, Robert Tibshirani, David Botstein, and Russ B Altman. 2001. Missing value estimation methods for DNA microarrays. Bioinformatics 17, 6 (2001), 520--525.Google ScholarCross Ref
- Carl Van Walraven, Peter C Austin, Alison Jennings, Hude Quan, and Alan J Forster. 2009. A modification of the Elixhauser comorbidity measures into a point system for hospital death using administrative data. Medical care (2009), 626--633.Google Scholar
- Giorgia Varallo, Emanuele Maria Giusti, Federica Scarpina, Roberto Cattivelli, Paolo Capodaglio, and Gianluca Castelnuovo. 2020. The association of kinesiophobia and pain catastrophizing with pain-related disability and pain intensity in obesity and chronic lower-back pain. Brain Sciences 11, 1 (2020), 11.Google ScholarCross Ref
- Johan WS Vlaeyen and Steven J Linton. 2000. Fear-avoidance and its consequences in chronic musculoskeletal pain: a state of the art. Pain 85, 3 (2000), 317--332.Google ScholarCross Ref
- Stefanos Voglis, Michal Ziga, Anna M Zeitlberger, Marketa Sosnova, Oliver Bozinov, Luca Regli, David Bellut, Astrid Weyerbrock, Martin N Stienen, and Nicolai Maldaner. 2022. Smartphone-based real-life activity data for physical performance outcome in comparison to conventional subjective and objective outcome measures after degenerative lumbar spine surgery. Brain and Spine 2 (2022), 100881.Google ScholarCross Ref
- Zirui Wang, Zihang Dai, Barnabás Póczos, and Jaime Carbonell. 2019. Characterizing and avoiding negative transfer. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 11293--11302.Google ScholarCross Ref
- James N Weinstein, Tor D Tosteson, Jon D Lurie, Anna NA Tosteson, Emily Blood, Brett Hanscom, Harry Herkowitz, Frank Cammisa, Todd Albert, Scott D Boden, et al. 2008. Surgical versus nonsurgical therapy for lumbar spinal stenosis. New England Journal of Medicine 358, 8 (2008), 794--810.Google ScholarCross Ref
- Cheng K Fred Wen, Stefan Schneider, Arthur A Stone, and Donna Spruijt-Metz. 2017. Compliance with mobile ecological momentary assessment protocols in children and adolescents: a systematic review and meta-analysis. Journal of medical Internet research 19, 4 (2017), e132.Google ScholarCross Ref
- Sen Wu, Hongyang R Zhang, and Christopher Ré. 2020. Understanding and improving information transfer in multi-task learning. arXiv preprint arXiv:2005.00944 (2020).Google Scholar
- Hiroyuki Yoshihara and Daisuke Yoneoka. 2014. Trends in the incidence and in-hospital outcomes of elective major orthopaedic surgery in patients eighty years of age and older in the United States from 2000 to 2009. JBJS 96, 14 (2014), 1185--1191.Google ScholarCross Ref
- Ruoxi Yu, Yali Zheng, Ruikai Zhang, Yuqi Jiang, and Carmen CY Poon. 2019. Using a multi-task recurrent neural network with attention mechanisms to predict hospital mortality of patients. IEEE journal of biomedical and health informatics 24, 2 (2019), 486--492.Google Scholar
- Ming Yuan and Yi Lin. 2006. Model selection and estimation in regression with grouped variables. Journal of the Royal Statistical Society Series B: Statistical Methodology 68, 1 (2006), 49--67.Google ScholarCross Ref
- Jingwen Zhang, Ruixuan Dai, Ashraf Rjob, Ruiqi Wang, Reshad Hamauon, Jeffrey Candell, Thomas Bailey, Victoria J Fraser, Maria Cristina Vazquez Guillamet, and Chenyang Lu. 2023. Contact Tracing for Healthcare Workers in an Intensive Care Unit. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 7, 3 (2023), 1--23.Google ScholarDigital Library
- Jingwen Zhang, Dingwen Li, Ruixuan Dai, Heidy Cos, Gregory A Williams, Lacey Raper, Chet W Hammill, and Chenyang Lu. 2022. Predicting post-operative complications with wearables: a case study with patients undergoing pancreatic surgery. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 6, 2 (2022), 1--27.Google ScholarDigital Library
Index Terms
- Predicting Multi-dimensional Surgical Outcomes with Multi-modal Mobile Sensing: A Case Study with Patients Undergoing Lumbar Spine Surgery
Recommendations
Predicting Post-Operative Complications with Wearables: A Case Study with Patients Undergoing Pancreatic Surgery
Post-operative complications and hospital readmission are of great concern to surgical patients and health care providers. Wearable devices such as Fitbit wristbands enable long-term and non-intrusive monitoring of patients outside clinical environments. ...
Predicting Outcomes for Cancer Patients with Transformer-Based Multi-task Learning
AI 2021: Advances in Artificial IntelligenceAbstractCancer patients often experience numerous hospital admissions as a result of their cancer and treatment, which can negatively impact treatment progress and quality of life. Accurately predicting outcomes for cancer patients is therefore crucial in ...
Forces in laparoscopic surgical tools
Minimally invasive surgery MIS, even with its shortcomings, has had a far reaching impact in the field of surgery. During MIS procedures, as the surgeon's hands are remote from the site of the surgery, they do not have a feel of the tissue being ...
Comments