Hacking the hackathon: insights from hosting a novel trainee-oriented multidisciplinary event

• Published in: BMJ innovations Vol. 7; no. 3; pp. 586 - 589
• Main Authors: Amat, Maelys, Duralde, Erin R, Lam, Barbara D, Lipcsey, Megan, Persaud, Brian K, Celi, Leo Anthony
• Format: Journal Article
• Language: English
• Published: London All India Institute of Medical Sciences 01.07.2021; BMJ Publishing Group LTD
• Subjects: Case reports; Collaboration; Data analysis; delivery of health care; Design thinking; Early-stage innovation report; Feedback; health; information science; Innovations; Intensive care; Interdisciplinary aspects; Internal medicine; Machine learning; Medical education; Medical students; Medicine; Pharmacists; Physicians; Problem solving; Teams; United States > US; Massachusetts
• ISSN: 2055-8074; 2055-642X
• DOI: 10.1136/bmjinnov-2020-000583

[...]a healthcare datathon brings data scientists, statisticians, engineers and clinicians together to analyse a dataset and investigate data-driven solutions to common clinical problems.5 These types of events have been celebrated for their ability to create diverse teams and involve learners in the earlier stages of problem solving and innovation.6 Studies have shown that hackathons also enhance the knowledge and skills associated with being an effective team player and leader.7 Despite the tremendous potential these events hold in medical education, they typically span multiple days, making it nearly impossible for clinician trainees with demanding schedules to participate. Table 1 Event details for the BIG microhack and the BIG microdatathon BIG microhack (2019) BIG microdatathon (2020) Collaborators BIDMC Department of Internal Medicine, MIT Sloan School of Management BIDMC Department of Internal Medicine, Department of Graduate Medical Education, MIT Critical Data, Google Cloud Targeted participants Resident physicians and other trainees, clinicians of all types (physicians, pharmacists, nurses, etc), business school students Resident physicians and other trainees, clinicians of all types (physicians, pharmacists, nurses, etc), data scientists Event length 3 hours 6 hours Goal Clinicians partnered with business school students in teams and practised rapid ideation to create solutions to the questions: ‘How can we improve medication list accuracy for our patients,’ ‘How can we improve care of the elderly in their own homes,’ and ‘How can we improve our process for obtaining images from outside hospitals?’ Clinicians and data scientists worked in teams to tackle one of two questions using the MIMIC database15: ‘Do non-English speaking patients receive more advanced care at the end of their lives?’ and ‘Can we create a machine learning model to predict mortality in patients who are started on continuous renal replacement therapy?’ Agenda Preparation 17:30–18:00 hours: room setup 18:00–18:30 hours: train team facilitators The event 18:30–19:00 hours: welcome and introduction 19:00–19:45 hours: facilitate ideation with teams 19:45–20:00 hours: team presentations Preparation 8:00–9:00 hours: room setup The event 9:00–9:30 hours: welcome and introduction 9:30–11:00 hours: introduction to machine learning 11:00–12:00 hours: data extraction 12:00–14:00 hours: working lunch and data analysis 14:00–15:00 hours: team presentations BIDMC, Beth Israel Deaconess Medical Center; BIG, Beth Israel Deaconess Innovation Group; MIMIC, Medical Information Mart for Intensive Care; MIT, Massachusetts Institute of Technology. Organisers invited participants via email and created two questions for teams to investigate, focusing on questions that would impact clinical practice and could be answered using MIMIC data without requiring advanced machine learning techniques. Data analysis On registration, participants provided demographic information including organisational affiliation and role via a Google Form (Alphabet, Mountain View, California, USA).