Rethinking PICO in the Machine Learning Era: ML-PICO

Background  Machine learning (ML) has captured the attention of many clinicians who may not have formal training in this area but are otherwise increasingly exposed to ML literature that may be relevant to their clinical specialties. ML papers that follow an outcomes-based research format can be assessed using clinical research appraisal frameworks such as PICO (Population, Intervention, Comparison, Outcome). However, the PICO frameworks strain when applied to ML papers that create new ML models, which are akin to diagnostic tests. There is a need for a new framework to help assess such papers. Objective  We propose a new framework to help clinicians systematically read and evaluate medical ML papers whose aim is to create a new ML model: ML-PICO (Machine Learning, Population, Identification, Crosscheck, Outcomes). We describe how the ML-PICO framework can be applied toward appraising literature describing ML models for health care. Conclusion  The relevance of ML to practitioners of clinical medicine is steadily increasing with a growing body of literature. Therefore, it is increasingly important for clinicians to be familiar with how to assess and best utilize these tools. In this paper we have described a practical framework on how to read ML papers that create a new ML model (or diagnostic test): ML-PICO. We hope that this can be used by clinicians to better evaluate the quality and utility of ML papers.     

C.B‐17 SCID mice develop epicardial calcinosis with unaltered cardiac function

Inbred mouse strains are the most widely used mammalian model organism in biomedical research owing to ease of genetic manipulation and short lifespan; however, each inbred strain possesses a unique repertoire of deleterious homozygous alleles that can make a specific strain more susceptible to a particular disease. In the current study, we report dystrophic cardiac calcinosis (DCC) in C.B‐17 SCID male mice at 10 weeks of age with no significant change in cardiac function. Acquisition of DCC was characterized by myocardial injury, fibrosis, calcification, and necrosis of the tissue. At 10 weeks of age, 38% of the C.B‐17 SCID mice from two different commercial colonies exhibited significant calcinosis on the ventricular epicardium, predominantly on the right ventricle. The frequency of calcinosis was more than 50% for mice obtained from Taconic's Cambridge City colony and 25% for mice obtained from Taconic's German Town colony. Interestingly, the DCC phenotype did not affect cardiac function at 10 weeks of age. No differences in echocardiography or electrocardiography were observed between the calcinotic and non‐calcinotic mice from either colony. Our findings suggest that C.B‐17 SCID mice exhibit DCC as early as 10 weeks of age with no significant impact on cardiac function. This strain of mice should be cautiously considered for the study of cardiac physiology.