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.     

The relationship between childhood maltreatment and psychopathology in adults undergoing bariatric surgery

Background

A history of childhood maltreatment and psychopathology are common in adults with obesity.

Giant right atrium and subvalvular pulmonary stenosis: A case report of an interesting combination

A 20‐year‐old Congolese woman presented with presyncope, dyspnea, and anasarca. Past medical history was unremarkable. Echocardiography revealed a rare combination of giant right atrium (RA), a dilated and hypertrophied right ventricle, subvalvular pulmonary stenosis (subPS), severe tricuspid regurgitation (TR), pericardial effusion and what appeared to be a spontaneously closed ventricular septal defect (VSD). Cardiac Magnetic Resonance and Cardiac Computed Tomography confirmed the findings excluding the presence of intra‐cardiac and extra‐cardiac shunt and other associated congenital anomalies. The patient underwent subPS resection, right atrioplasty, and tricuspid annuloplasty. Multimodality approach facilitated the detection of the abnormalities and provided clarity when determining the optimal surgical strategy.     

Experience of detection of rubella markers during local outbreaks in West Siberia

This paper presents an analysis of samples from 75 patients for the presence of rubella virus, viral RNA, and specific antibodies. For all samples, RNA detection was higher than virus isolation. It was found that it was not possible to isolate rubella virus in every sixth clinical sample containing the viral RNA. Primary structures of the site (from the 8072nd to 8291st nucleotide) of the rubella virus genome from 14 samples were determined. This paper shows that all the samples of rubella virus belong to the first genotype, subgroups 1h, and very likely to subgroups 1a and 1F. For the first time, the circulation of rubella virus of the genotype has been shown both prior to the start of mass vaccination in Western Siberia and after.     

Absence of FGFR3–TACC3 rearrangement in hematological malignancies with numerical chromosomal alteration

FGFR–TACC, found in different tumor types, is characterized by the fusion of a member of fibroblast grown factor receptor (FGFR) tyrosine kinase (TK) family to a member of the transforming acidic coiled-coil (TACC) proteins. Because chromosome numerical alterations, hallmarks of FGFR–TACC fusions are present in many hematological disorders and there are no data on the prevalence, we studied a series of patients with acute myeloid leukemia and myelodysplastic syndrome who presented numerical alterations using cytogenetic traditional analysis. None of the analyzed samples showed FGFR3–TACC3 gene fusion, so screening for this mutation at diagnosis is not recommended.