PREDICT<\/h1><\/div>Machine Learning Predictions Improving Patient Care<\/p>\n<\/div><\/div><\/div><\/div><\/div>
![\"PREDICT](\"https:\/\/lab.research.sickkids.ca\/sung\/wp-content\/uploads\/sites\/153\/2024\/11\/PREDICT-Logo-Updated-PNG.png\" "\\"PREDICT")
<\/span><\/div><\/div><\/div>Pediatric Real-world Evaluative Data sciences for Clinical Transformation (PREDICT)<\/b> provides end-to-end service for clinicians looking to implement machine learning models into their routine clinical care. From idea conception, to development, silent trial, deployment and clinical implementation, the PREDICT team works with clinicians to implement clinically important models safely and effectively.<\/p>\n<\/div><\/div><\/div><\/div><\/div><\/i><\/span><\/div><\/div><\/div>\nOver 200 models across 4 centres<\/p>\n<\/div><\/div><\/div>
<\/i><\/span><\/div><\/div><\/div>\nOver 95 peer reviewed publications in last 2 years (including 8 technical contributions)<\/p>\n<\/div><\/div><\/div>
<\/i><\/span><\/div><\/div><\/div>\nFirst to demonstrate the transformative portability of large-scale foundation models, representing the next-generation paradigm<\/p>\n<\/div><\/div><\/div>
<\/div><\/div><\/div><\/div><\/div><\/div>Key publications<\/h2><\/div>Yan AP, Guo LL, Patel P, Schecter T, Arciniegas SE, Inoue J, Vettese E, Jessa K, Cardiff B, Tomlinson G, Dupuis LL, Sung L. Development and prospective evaluation of a machine learning model to predict vomiting among pediatric cancer and hematopoietic cell transplant patients.<\/a> BMC Canc. 2025 Oct 31;25(1):1679. doi: https:\/\/doi.org\/10.1186\/s12885-025-15137-1. PMID: 41174551; PMCID: PMC12577177\u00a0<\/span><\/p>\nYan AP, Arciniegas SE, Cohn I, Verstegen RHJ, Seto W, Silver S, Guo LL, Inoue J, Wolochacz AW, Jessa K, Tomlinson G, Sung L. Retrospective evaluation of a machine learning model to facilitate pharmacogenetic testing.<\/a> BMJ Digi Health and AI. 2025 Oct 14;12025;1:e000134. doi: 10.1136\/bmjdhai-2025-000134.<\/p>\nYan AP, Guo LL, Inoue J, Arciniegas SE, Vettese E, Wolochacz A, Crellin-Parsons N, Purves B, Wallace S, Patel A, Roshdi M, Jessa K, Cardiff B, Sung L. A roadmap to implementing machine learning in healthcare: from concept to practice.<\/a> Front. 2025 Jan 19;7. doi: 10.3389\/fdgth.2025.1462751.<\/p>\nArciniegas SE, Yan AP, Rapoport A, Jeewa A, Muhame RM, Guo LL, Wolochacz A, Jessa K, Cardiff B, Tomlinson G, Witt J, Ferracci C, Sung L, Dipchand A, Nelson K. Development and prospective evaluation of a machine learning model to predict serious cardiac outcomes among paediatric cardiac inpatients.<\/a> BMJ Digi Health and AI. 2025;1:e000114. https:\/\/doi.org\/10.1136\/bmjdhai-2025-000114.<\/p>\nGuo LL, Fries J, Steinberg E, Fleming SL, Morse K, Aftandilian C, Posada J, Shah N, Sung L. A multi-center study on the adaptability of a shared foundation model for electronic health records.<\/a> NPJ Digit Med. 2024 Jun 27;7(1):171. doi: 10.1038\/s41746-024-01166-w. PMID: 38937550; PMCID: PMC11211479.<\/p>\nLemmon J, Guo LL, Steinberg E, Morse KE, Fleming SL, Aftandilian C, Pfohl SR, Posada JD, Shah N, Fries J, Sung L. Self-supervised machine learning using adult inpatient data produces effective models for pediatric clinical prediction tasks.<\/a> J Am Med Inform Assoc. 2023 Nov 17;30(12):2004-2011. doi: 10.1093\/jamia\/ocad175. PMID: 37639620; PMCID: PMC10654865.<\/p>\nGuo LL, Steinberg E, Fleming SL, Posada J, Lemmon J, Pfohl SR, Shah N, Fries J, Sung L. EHR foundation models improve robustness in the presence of temporal distribution shift.<\/a> Sci Rep. 2023 Mar 7;13(1):3767. doi: 10.1038\/s41598-023-30820-8. PMID: 36882576; PMCID: PMC9992466.<\/p>\n<\/div><\/div><\/div><\/div><\/div>
Machine Learning Predictions Improving Patient Care<\/p>\n<\/div><\/div><\/div><\/div><\/div>
<\/span><\/div><\/div><\/div>Pediatric Real-world Evaluative Data sciences for Clinical Transformation (PREDICT)<\/b> provides end-to-end service for clinicians looking to implement machine learning models into their routine clinical care. From idea conception, to development, silent trial, deployment and clinical implementation, the PREDICT team works with clinicians to implement clinically important models safely and effectively.<\/p>\n<\/div><\/div><\/div><\/div><\/div> Over 200 models across 4 centres<\/p>\n<\/div><\/div><\/div> Over 95 peer reviewed publications in last 2 years (including 8 technical contributions)<\/p>\n<\/div><\/div><\/div> First to demonstrate the transformative portability of large-scale foundation models, representing the next-generation paradigm<\/p>\n<\/div><\/div><\/div> Yan AP, Guo LL, Patel P, Schecter T, Arciniegas SE, Inoue J, Vettese E, Jessa K, Cardiff B, Tomlinson G, Dupuis LL, Sung L. Development and prospective evaluation of a machine learning model to predict vomiting among pediatric cancer and hematopoietic cell transplant patients.<\/a> BMC Canc. 2025 Oct 31;25(1):1679. doi: https:\/\/doi.org\/10.1186\/s12885-025-15137-1. PMID: 41174551; PMCID: PMC12577177\u00a0<\/span><\/p>\n Yan AP, Arciniegas SE, Cohn I, Verstegen RHJ, Seto W, Silver S, Guo LL, Inoue J, Wolochacz AW, Jessa K, Tomlinson G, Sung L. Retrospective evaluation of a machine learning model to facilitate pharmacogenetic testing.<\/a> BMJ Digi Health and AI. 2025 Oct 14;12025;1:e000134. doi: 10.1136\/bmjdhai-2025-000134.<\/p>\n Yan AP, Guo LL, Inoue J, Arciniegas SE, Vettese E, Wolochacz A, Crellin-Parsons N, Purves B, Wallace S, Patel A, Roshdi M, Jessa K, Cardiff B, Sung L. A roadmap to implementing machine learning in healthcare: from concept to practice.<\/a> Front. 2025 Jan 19;7. doi: 10.3389\/fdgth.2025.1462751.<\/p>\n Arciniegas SE, Yan AP, Rapoport A, Jeewa A, Muhame RM, Guo LL, Wolochacz A, Jessa K, Cardiff B, Tomlinson G, Witt J, Ferracci C, Sung L, Dipchand A, Nelson K. Development and prospective evaluation of a machine learning model to predict serious cardiac outcomes among paediatric cardiac inpatients.<\/a> BMJ Digi Health and AI. 2025;1:e000114. https:\/\/doi.org\/10.1136\/bmjdhai-2025-000114.<\/p>\n Guo LL, Fries J, Steinberg E, Fleming SL, Morse K, Aftandilian C, Posada J, Shah N, Sung L. A multi-center study on the adaptability of a shared foundation model for electronic health records.<\/a> NPJ Digit Med. 2024 Jun 27;7(1):171. doi: 10.1038\/s41746-024-01166-w. PMID: 38937550; PMCID: PMC11211479.<\/p>\n Lemmon J, Guo LL, Steinberg E, Morse KE, Fleming SL, Aftandilian C, Pfohl SR, Posada JD, Shah N, Fries J, Sung L. Self-supervised machine learning using adult inpatient data produces effective models for pediatric clinical prediction tasks.<\/a> J Am Med Inform Assoc. 2023 Nov 17;30(12):2004-2011. doi: 10.1093\/jamia\/ocad175. PMID: 37639620; PMCID: PMC10654865.<\/p>\n Guo LL, Steinberg E, Fleming SL, Posada J, Lemmon J, Pfohl SR, Shah N, Fries J, Sung L. EHR foundation models improve robustness in the presence of temporal distribution shift.<\/a> Sci Rep. 2023 Mar 7;13(1):3767. doi: 10.1038\/s41598-023-30820-8. PMID: 36882576; PMCID: PMC9992466.<\/p>\n<\/div><\/div><\/div><\/div><\/div>Key publications<\/h2><\/div>