Adam Paul Yan ^1,2 Lin Lawrence Guo ² Jiro Inoue ² Santiago Eduardo Arciniegas ² Emily Vettese ² Agata Wolochacz ² Nicole Crellin-Parsons ² Brandon Purves ³ Steven Wallace ³ Azaz Patel ³ Medhat Roshdi ³ Karim Jessa ^3,4 Bren Cardiff ³ Lillian Sung ^1,2,3*

• ¹ Division of Haematology/Oncology, The Hospital for Sick Children, Toronto, Canada
• ² Program in Child Health Evaluative Sciences, The Hospital for Sick Children, Toronto, Canada
• ³ Information Management Technology, The Hospital for Sick Children, Toronto, Canada
• ⁴ Department of Emergency Medicine, The Hospital for Sick Children, Toronto, Canada

The adoption of machine learning (ML) has been slow within the healthcare setting. We launched Pediatric Real-world Evaluative Data sciences for Clinical Transformation (PREDICT) at a pediatric hospital. Its goal was to develop, deploy, evaluate and maintain clinical ML models to improve pediatric patient outcomes using electronic health records data.To provide examples from the PREDICT experience illustrating how common challenges with clinical ML deployment were addressed.We present common challenges in developing and deploying models in healthcare related to the following: identify clinical scenarios, establish data infrastructure and utilization, create machine learning operations and integrate into clinical workflows.We show examples of how these challenges were overcome and provide suggestions for pragmatic solutions while maintaining best practices.Discussion: These approaches will require refinement over time as the number of deployments and experience increase.