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.     

Deferoxamine promotes recovery of traumatic spinal cord injury by inhibiting ferroptosis

Ferroptosis is an iron-dependent novel cell death pathway. Deferoxamine, a ferroptosis inhibitor, has been reported to promote spinal cord injury repair. It has yet to be clarified whether ferroptosis inhibition represents the mechanism of action of Deferoxamine on spinal cord injury recovery. A rat model of Deferoxamine at thoracic 10 segment was established using a modified Allen's method. Ninety 8-week-old female Wistar rats were used. Rats in the Deferoxamine group were intraperitoneally injected with 100 mg/kg Deferoxamine 30 minutes before injury. Simultaneously, the Sham and Deferoxamine groups served as controls. Drug administration was conducted for 7 consecutive days. The results were as follows:(1) Electron microscopy revealed shrunken mitochondria in the spinal cord injury group.(2) The Basso, Beattie and Bresnahan locomotor rating score showed that recovery of the hindlimb was remarkably better in the Deferoxamine group than in the spinal cord injury group.(3) The iron concentration was lower in the Deferoxamine group than in the spinal cord injury group after injury.(4) Western blot assay revealed that, compared with the spinal cord injury group, GPX4, xCT, and glutathione expression was markedly increased in the Deferoxamine group.(5) Real-time polymerase chain reaction revealed that, compared with the Deferoxamine group, mRNA levels of ferroptosis-related genes Acyl-CoA synthetase family member 2(ACSF2) and iron-responsive element-binding protein 2(IREB2) were up-regulated in the Deferoxamine group.(6) Deferoxamine increased survival of neurons and inhibited gliosis. These findings confirm that Deferoxamine can repair spinal cord injury by inhibiting ferroptosis. Targeting ferroptosis is therefore a promising therapeutic approach for spinal cord injury.     

2018-2020年焦作市儿童青少年视力现状分析

目的 了解2018—2020年河南省焦作市儿童青少年视力状况，为相关部门制定儿童青少年近视预防控制措施提供依据。方法 2018—2020年分别在焦作市选择1～2个城区和1个郊县，采用分层整群抽样方法抽取幼儿园、小学和中学共25所学校，对幼儿园5.5～6.5岁儿童和不同学段学生开展远视力检查和屈光检测，以SPSS 17.0软件统计分析数据，采用单因素χ2检验分析不同特征人群的近视率。结果 共调查22 257人，总体近视率62.13%,2018—2020年近视率先降后升；女生近视率（65.71%）高于男生（58.63%），差异有统计学意义（χ2=118.555,P<0.05），城区近视率（64.37%）高于郊县（57.73%），差异有统计学意义（χ2=93.226,P<0.05）；近视率和中、高度近视率均随学段升高而升高，幼儿园、小学、初中和高中近视率分别达21.45%,46.71%,80.43%和88.21%，高中阶段中高度近视率分别达41.40%和20.16%。结论焦作市儿童青少年的近视患病形势不容乐观，近视发展呈低龄化，中高度近视率较高。学校、家庭和社会应共同干预，采取减...