Pragmatic considerations for fostering reproducible research in artificial intelligence

Artificial intelligence and deep learning methods hold great promise in the medical sciences in areas such as enhanced tumor identification from radiographic images, and natural language processing to extract complex information from electronic health records. Scientific review of AI algorithms has involved reproducibility, in which investigators share protocols, raw data, and programming codes. Within the realm of medicine, reproducibility introduces important challenges, including risk to patient privacy, challenges in reproducing results, and questions regarding ownership and financial value of large medical datasets. Scientific review, however, mandates some form of resolution of these inherent conflicts. We propose several approaches to permit scientific review while maintaining patient privacy and data confidentiality.

[1]  J. Kwon,et al.  An Algorithm Based on Deep Learning for Predicting In‐Hospital Cardiac Arrest , 2018, Journal of the American Heart Association.

[2]  L. D. Jones,et al.  Artificial intelligence, machine learning and the evolution of healthcare , 2018, Bone & joint research.

[3]  R. Peng.  Reproducible Research in Computational Science , 2011, Science.

[4]  C. Cornu,et al.  How the new European data protection regulation affects clinical research and recommendations? , 2019, Therapie.

[5]  Michael J Ackerman,et al.  Noninvasive assessment of dofetilide plasma concentration using a deep learning (neural network) analysis of the surface electrocardiogram: A proof of concept study , 2018, PloS one.

[6]  Matthew Hutson,et al.  Missing data hinder replication of artificial intelligence studies , 2018 .

[7]  C. Krittanawong,et al.  Artificial Intelligence in Precision Cardiovascular Medicine. , 2017, Journal of the American College of Cardiology.

[8]  A. Thorogood.  Canada: will privacy rules continue to favour open science? , 2018, Human Genetics.

[9]  D. Trafimow,et al.  Replication, falsification, and the crisis of confidence in social psychology , 2015, Front. Psychol..

[10]  Kipp W. Johnson,et al.  Artificial Intelligence in Cardiology. , 2018, Journal of the American College of Cardiology.

[11]  Xiangyi Kong,et al.  Automatic Detection of Acromegaly From Facial Photographs Using Machine Learning Methods , 2017, EBioMedicine.

[12]  Rickey E. Carter,et al.  Screening for cardiac contractile dysfunction using an artificial intelligence–enabled electrocardiogram , 2019, Nature Medicine.

[13]  Subhashini Venugopalan,et al.  Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. , 2016, JAMA.

[14]  Oleg S. Pianykh,et al.  Current Applications and Future Impact of Machine Learning in Radiology. , 2018, Radiology.

[15]  Hongfang Liu,et al.  Ascertainment of asthma prognosis using natural language processing from electronic medical records. , 2018, The Journal of allergy and clinical immunology.

[16]  Leo Anthony Celi,et al.  The reproducibility crisis in the age of digital medicine , 2019, npj Digital Medicine.

[17]  F. Dominici,et al.  Reproducible epidemiologic research. , 2006, American journal of epidemiology.

[18]  Philip B. Stark,et al.  Before reproducibility must come preproducibility , 2018, Nature.

[19]  S. Kalkman,et al.  Responsible data sharing in international health research: a systematic review of principles and norms , 2019, BMC Medical Ethics.