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.     

A comparison of double single suture-button fixation,suture-button fixation,and screw fixation for ankle syndesmosis injury: A retrospective cohort study

Different methods have been used throughout the years for syndesmotic injury but there is no consensus on the ideal treatment. Some methods are expensive and some have more complications. The aim of this study is to compare single suture endobutton with double suture endobutton and screw fixation for syndesmotic injury.Sixty nine patients with syndesmotic injury with fibular fractures whom were treated with a single interosseous suture endobutton system (ZipTight^TM, Zimmer Biomet), a double interosseous suture endobutton system (ZipTight^TM, Zimmer Biomet) and 1 syndesmotic screw (TST, Istanbul, Turkey) were included in this study. Functional and radiological results from patient records between 2015 and 2018 were retrospectively evaluated.Twenty patients were treated with the double interosseous suture endobutton, 23 were treated with the single interosseous suture endobutton, and 26 were treated with traditional AO screw fixation. Three patients from the screw fixation group (11.5%) required revision surgery (P < .05). All the radiologic and clinical outcomes were statistical similar in all 3 groups.Our findings showed that the interosseous suture endobutton system is at least as safe as the screw fixation technique for treatment of syndesmosis joint injuries and can be used as an alternative to the screw method. The interosseous suture endobutton system eliminates the need for a second surgery to remove the hardware, which minimizes the probability of re-diastasis. Since our results showed no statistical difference between single and double interosseous suture endobutton systems, the less costly single endobutton system may be the better alternative.