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.     

Premature Ticagrelor Discontinuation in Secondary Prevention of Atherosclerotic CVD: JACC Review Topic of the Week

Ticagrelor is a cornerstone of modern antithrombotic therapy alongside aspirin in patients with acute coronary syndrome and after percutaneous coronary intervention. Adverse effects such as bleeding and dyspnea have been associated with premature ticagrelor discontinuation, which may limit any potential advantage of ticagrelor over clopidogrel. The randomized trials of ticagrelor captured adverse events, offering the opportunity to more precisely quantify these effects across studies. Therefore, a meta-analysis of 4 randomized clinical trials of ticagrelor conducted between January 2007 and June 2017 was performed to quantify the incidence and causes of premature ticagrelor discontinuation. Among 66,870 patients followed for a median 18 months, premature ticagrelor discontinuation was seen in 25%; bleeding was the most common cause of discontinuation followed by dyspnea. Versus the comparators, the relative risk of dyspnea-related discontinuation during follow-up was 6.4-fold higher, the relative risk of bleeding was 3.2-fold higher, and the relative risk of discontinuation due to any adverse event was 59% higher for patients receiving ticagrelor. Understanding these potential barriers to adherence to ticagrelor is crucial for informed patient-physician decision making and can inform future efforts to improve ticagrelor adherence. This review discusses the incidence, causes, and biological mechanisms of ticagrelor-related adverse effects and offers strategies to improve adherence to ticagrelor.     

Acute disseminated encephalomyelitis: the importance of early magnetic resonance imaging

The diagnosis of acute disseminated encephalomyelitis (ADEM) is frequently missed or delayed with consequent delay in instituting therapy in the crucial phase of the illness. The role of MRI in the diagnosis of ADEM is well established, however, the value of its early utilization of treatment on the outcome of patients has not been adequately stressed. Three patients with ADEM are described. Delay in the diagnosis of the first was associated with severe sequelae, while in the other two early diagnosis and institution of corticosteroid therapy which was facilitated by MRI, was associated with a better outcome. MRI should be carried out early once the diagosis of ADEM is entertained.     

Pharmacological Studies on Leaves of Withania somnifera.

Anti-inflammatory activity and protective effect against CCl (4)-induced hepatotoxicity of alcoholic extract of leaves of WITHANIA SOMNIFERA have been assessed. The leaves were found to possess marked effects in subacute inflammation and hepatotoxicity. A comparison of the anti-inflammatory properties revealed the extract at 1 g/kg dose to be as active as 50 mg/kg of phenylbutazone and 10 mg/kg of hydrocortisone. The protective effect of the extract at 1 g/kg dose against CCl (4)-induced hepatotoxicity was comparable to 10 mg/kg of hydrocortisone.