Digital Health Frontier
By John Halamka and Paul Cerrato - In the second installment in the series, we explain how gradient boosting can help make patient care more precise and cost effective.
By John Halamka and Paul Cerrato - Many physicians ignore the recommendations provided by machine learning algorithms because they don’t trust them. A few imaginative software enhancements may give them more confidence in an algorithm’s diagnostic and therapeutic suggestions.
By John Halamka and Paul Cerrato - The potential benefits of AI-enabled algorithms have to be weighed against the risk of dataset shift, which can compromise their accuracy in ways that developers never anticipated.
By John Halamka and Paul Cerrato - Our vision for health care technology includes a steadfast determination to use AI to augment human intelligence — not contribute to a dystopian future some fear is already upon us.
By John Halamka and Paul Cerrato - One of the privileges we enjoy working in digital health is the opportunity to use state-of-the-art AI tools to unearth actionable insights from millions of patient records, without compromising their privacy.
By John Halamka and Paul Cerrato - Machine learning-enhanced algorithms may help clinicians select the best medications for each patient, speeding up the long journey to find effective relief for a crippling disorder.
By John Halamka and Paul Cerrato - Some clinicians reject any AI-infused recommendations, while others are so confident in these tools that they forfeit their independent diagnostic skills. A closer look at the research can turn these mistakes into insights.
By John Halamka and Paul Cerrato - Randomized controlled trials (RCTs), the gold standard in clinical medicine, only tell us how the average patient responds to a treatment or an AI-based algorithm. N of 1 trials provide a unique opportunity to individualize patient care.
By John Halamka and Paul Cerrato - Predicting cardiovascular disease and death is an imperfect science; the right AI algorithms can make these estimates more accurate.
By John Halamka and Paul Cerrato - Affective computing and sentiment analysis can help clinicians read between the lines, allowing them to detect patients’ unexpressed feelings and subtle emotional cues that may signal subclinical disease—and much more.
By John Halamka and Paul Cerrato - A better understanding of proteomics, genomics, and a variety of other biomarkers can help personalize patient care and shed new light on human physiology and pathology.
By John Halamka and Paul Cerrato - Most AI-driven algorithms take the clinician from A—the ailing patient—to D—the final diagnosis—ignoring intermediate steps B and C in the diagnostic journey. There is a better way.