David Ben-Israel1, W Bradley Jacobs2, Steve Casha3, Stefan Lang1, Won Hyung A Ryu4, Madeleine de Lotbiniere-Bassett1, David W Cadotte5. 1. Department of Clinical Neurosciences, Division of Neurosurgery, 1403 29 St. NW, Calgary, Alberta, T2N 2T9, Canada. 2. Department of Clinical Neurosciences, Division of Neurosurgery, 1403 29 St. NW, Calgary, Alberta, T2N 2T9, Canada; University of Calgary Combine Spine Program, 1403 29 St. NW, Calgary, Alberta, T2N 2T9, Canada. 3. Department of Clinical Neurosciences, Division of Neurosurgery, 1403 29 St. NW, Calgary, Alberta, T2N 2T9, Canada; University of Calgary Combine Spine Program, 1403 29 St. NW, Calgary, Alberta, T2N 2T9, Canada; Hotchkiss Brain Institute, University of Calgary, 1403 29 St. NW, Calgary, Alberta, T2N 2T9, Canada. 4. Department of Clinical Neurosciences, Division of Neurosurgery, 1403 29 St. NW, Calgary, Alberta, T2N 2T9, Canada; Hotchkiss Brain Institute, University of Calgary, 1403 29 St. NW, Calgary, Alberta, T2N 2T9, Canada. 5. Department of Clinical Neurosciences, Division of Neurosurgery, 1403 29 St. NW, Calgary, Alberta, T2N 2T9, Canada; University of Calgary Combine Spine Program, 1403 29 St. NW, Calgary, Alberta, T2N 2T9, Canada; Hotchkiss Brain Institute, University of Calgary, 1403 29 St. NW, Calgary, Alberta, T2N 2T9, Canada; Department of Radiology, University of Calgary, 1403 29 St. NW, Calgary, Alberta, T2N 2T9, Canada. Electronic address: david.cadotte@ucalgary.ca.
Abstract
BACKGROUND: Despite the expanding use of machine learning (ML) in fields such as finance and marketing, its application in the daily practice of clinical medicine is almost non-existent. In this systematic review, we describe the various areas within clinical medicine that have applied the use of ML to improve patient care. METHODS: A systematic review was performed in accordance with the PRISMA guidelines using Medline(R), EBM Reviews, Embase, Psych Info, and Cochrane Databases, focusing on human studies that used ML to directly address a clinical problem. Included studies were published from January 1, 2000 to May 1, 2018 and provided metrics on the performance of the utilized ML tool. RESULTS: A total of 1909 unique publications were reviewed, with 378 retrospective articles and 8 prospective articles meeting inclusion criteria. Retrospective publications were found to be increasing in frequency, with 61 % of articles published within the last 4 years. Prospective articles comprised only 2 % of the articles meeting our inclusion criteria. These studies utilized a prospective cohort design with an average sample size of 531. CONCLUSION: The majority of literature describing the use of ML in clinical medicine is retrospective in nature and often outlines proof-of-concept approaches to impact patient care. We postulate that identifying and overcoming key translational barriers, including real-time access to clinical data, data security, physician approval of "black box" generated results, and performance evaluation will allow for a fundamental shift in medical practice, where specialized tools will aid the healthcare team in providing better patient care.
BACKGROUND: Despite the expanding use of machine learning (ML) in fields such as finance and marketing, its application in the daily practice of clinical medicine is almost non-existent. In this systematic review, we describe the various areas within clinical medicine that have applied the use of ML to improve patient care. METHODS: A systematic review was performed in accordance with the PRISMA guidelines using Medline(R), EBM Reviews, Embase, Psych Info, and Cochrane Databases, focusing on human studies that used ML to directly address a clinical problem. Included studies were published from January 1, 2000 to May 1, 2018 and provided metrics on the performance of the utilized ML tool. RESULTS: A total of 1909 unique publications were reviewed, with 378 retrospective articles and 8 prospective articles meeting inclusion criteria. Retrospective publications were found to be increasing in frequency, with 61 % of articles published within the last 4 years. Prospective articles comprised only 2 % of the articles meeting our inclusion criteria. These studies utilized a prospective cohort design with an average sample size of 531. CONCLUSION: The majority of literature describing the use of ML in clinical medicine is retrospective in nature and often outlines proof-of-concept approaches to impact patient care. We postulate that identifying and overcoming key translational barriers, including real-time access to clinical data, data security, physician approval of "black box" generated results, and performance evaluation will allow for a fundamental shift in medical practice, where specialized tools will aid the healthcare team in providing better patient care.
Authors: Benjamin Kompa; Joe B Hakim; Anil Palepu; Kathryn Grace Kompa; Michael Smith; Paul A Bain; Stephen Woloszynek; Jeffery L Painter; Andrew Bate; Andrew L Beam Journal: Drug Saf Date: 2022-05-17 Impact factor: 5.606
Authors: Francesco Blasi; Enrico Gianluca Caiani; Matteo Giuseppe Cereda; Daniela Donetti; Marco Montorsi; Vincenzo Panella; Gaia Panina; Felicia Pelagalli; Elisabetta Speroni Journal: Front Public Health Date: 2022-06-29
Authors: Amol A Verma; Joshua Murray; Russell Greiner; Joseph Paul Cohen; Kaveh G Shojania; Marzyeh Ghassemi; Sharon E Straus; Chloe Pou-Prom; Muhammad Mamdani Journal: CMAJ Date: 2021-08-29 Impact factor: 8.262
Authors: Roberto Aringhieri; Patrick Hirsch; Marion S Rauner; Melanie Reuter-Oppermanns; Margit Sommersguter-Reichmann Journal: Cent Eur J Oper Res Date: 2021-12-10 Impact factor: 2.345
Authors: Amol A Verma; Joshua Murray; Russell Greiner; Joseph Paul Cohen; Kaveh G Shojania; Marzyeh Ghassemi; Sharon E Straus; Chloé Pou-Prom; Muhammad Mamdani Journal: CMAJ Date: 2021-11-08 Impact factor: 8.262
Authors: George E Fowler; Rhiannon C Macefield; Conor Hardacre; Mark P Callaway; Neil J Smart; Natalie S Blencowe Journal: BMJ Open Date: 2021-10-20 Impact factor: 2.692