Incorporating artificial intelligence (AI) into clinics brings the risk of automation bias, which potentially misleads the clinician’s decision-making. The purpose of this study was to propose a potential strategy to mitigate automation bias. This was a laboratory study with a randomized cross-over design. The diagnosis of anterior cruciate ligament (ACL) rupture, a common injury, on magnetic resonance imaging (MRI) was used as an example. Forty clinicians were invited to diagnose 200 ACLs with and without AI assistance. The AI’s correcting and misleading (automation bias) effects on the clinicians’ decision-making processes were analyzed. An ordinal logistic regression model was employed to predict the correcting and misleading probabilities of the AI. We further proposed an AI suppression strategy that retracted AI diagnoses with a higher misleading probability and provided AI diagnoses with a higher correcting probability. The AI significantly increased clinicians’ accuracy from 87.2%±13.1% to 96.4%±1.9% (P < .001). However, the clinicians’ errors in the AI-assisted round were associated with automation bias, accounting for 45.5% of the total mistakes. The automation bias was found to affect clinicians of all levels of expertise. Using a logistic regression model, we identified an AI output zone with higher probability to generate misleading diagnoses. The proposed AI suppression strategy was estimated to decrease clinicians’ automation bias by 41.7%. Although AI improved clinicians’ diagnostic performance, automation bias was a serious problem that should be addressed in clinical practice. The proposed AI suppression strategy is a practical method for decreasing automation bias.

BACKGROUND: Cardiac ischemia/reperfusion (I/R) injury has emerged as an important therapeutic target for ischemic heart disease. Currently, there is no effective therapy for reducing cardiac I/R injury. Damage-associated molecular patterns are endogenous molecules released after cellular damage to exaggerate tissue inflammation and injury. RIPK3 (receptor-interacting protein kinase 3), a well-established intracellular mediator of cell necroptosis and inflammation, serves as a circulating biomarker of multiple diseases. However, whether extracellular RIPK3 also exerts biological functions in cardiac I/R injury remains totally unknown. METHODS: Patients with acute myocardial infarction receiving percutaneous coronary intervention (PCI) were recruited independently in the discovery cohort (103 patients) and validation cohort (334 patients), and major adverse cardiovascular events were recorded. Plasma samples were collected before and after PCI (6 and 24 h) for RIPK3 concentration measurement. Cultured neonatal rat ventricular myocytes, macrophages and endothelial cells, and in vivo mouse models with myocardial injury induced by I/R (or hypoxia/reoxygenation) were used to investigate the role and mechanisms of extracellular RIPK3. Another cohort including patients with acute myocardial infarction receiving PCI and healthy volunteers was recruited to further explore the mechanisms of extracellular RIPK3. RESULTS: In the discovery cohort, elevated plasma RIPK3 levels after PCI are associated with poorer short- and long-term outcomes in patients with acute myocardial infarction, as confirmed in the validation cohort. In both cultured cells and in vivo mouse models, recombinant RIPK3 protein exaggerated myocardial I/R (or hypoxia/reoxygenation) injury, which was alleviated by the RIPK3 antibody. Mechanistically, RIPK3 acted as a damage-associated molecular pattern and bound with RAGE (receptor of advanced glycation end-products), subsequently activating CaMKII (Ca ²⁺ /calmodulin-dependent kinase II) to elicit the detrimental effects. The positive correlation between plasma RIPK3 concentrations and CaMKII phosphorylation in human peripheral blood mononuclear cells was confirmed. CONCLUSIONS: We identified the positive relationship between plasma RIPK3 concentrations and the risk of major adverse cardiovascular events in patients with acute myocardial infarction receiving PCI. As a damage-associated molecular pattern, extracellular RIPK3 plays a causal role in multiple pathological conditions during cardiac I/R injury through RAGE/CaMKII signaling. These findings expand our understanding of the physiological and pathological roles of RIPK3, and also provide a promising therapeutic target for myocardial I/R injury and the associated complications.

Background: Clinical decision support systems (CDSS) are an integral component of health information technologies and can assist disease interpretation, diagnosis, treatment, and prognosis. However, the utility of CDSS in the clinic remains controversial. Objective: The aim is to assess the effects of CDSS integrated with British Medical Journal (BMJ) Best Practice–aided diagnosis in real-world research. Methods: This was a retrospective, longitudinal observational study using routinely collected clinical diagnosis data from electronic medical records. A total of 34,113 hospitalized patient records were successively selected from December 2016 to February 2019 in six clinical departments. The diagnostic accuracy of the CDSS was verified before its implementation. A self-controlled comparison was then applied to detect the effects of CDSS implementation. Multivariable logistic regression and single-group interrupted time series analysis were used to explore the effects of CDSS. The sensitivity analysis was conducted using the subgroup data from January 2018 to February 2019. Results: The total accuracy rates of the recommended diagnosis from CDSS were 75.46% in the first-rank diagnosis, 83.94% in the top-2 diagnosis, and 87.53% in the top-3 diagnosis in the data before CDSS implementation. Higher consistency was observed between admission and discharge diagnoses, shorter confirmed diagnosis times, and shorter hospitalization days after the CDSS implementation (all P<.001). Multivariable logistic regression analysis showed that the consistency rates after CDSS implementation (OR 1.078, 95% CI 1.015-1.144) and the proportion of hospitalization time 7 days or less (OR 1.688, 95% CI 1.592-1.789) both increased. The interrupted time series analysis showed that the consistency rates significantly increased by 6.722% (95% CI 2.433%-11.012%, P=.002) after CDSS implementation. The proportion of hospitalization time 7 days or less significantly increased by 7.837% (95% CI 1.798%-13.876%, P=.01). Similar results were obtained in the subgroup analysis. Conclusions: The CDSS integrated with BMJ Best Practice improved the accuracy of clinicians’ diagnoses. Shorter confirmed diagnosis times and hospitalization days were also found to be associated with CDSS implementation in retrospective real-world studies. These findings highlight the utility of artificial intelligence-based CDSS to improve diagnosis efficiency, but these results require confirmation in future randomized controlled trials.

Background: Both knee osteoarthritis (KOA) and depressive symptoms (DS) are major public health issues affecting the quality of life. This study aimed to examine the association between KOA and DS.Methods: Data were gathered from the China Health and Retirement Longitudinal Study in 2011–2015 which surveyed middle-aged to elderly individuals and their spouses in 28 provinces in China. An adjusted Cox proportional hazards regression model was used to estimate hazard ratios (HRs).Results: The analysis for baseline KOA and the subsequent risk of DS was based on 2582 participants without baseline DS. During the follow-up, KOA patients were more likely to have DS than non-KOA participants (adjusted HR = 1.38: 95% CI = 1.23 to 1.83). The analysis for baseline DS and the subsequent risk of KOA was based on 4293 participants without baseline KOA, those with DS were more likely to develop KOA than non-DS participants (adjusted HR = 1.51: 95% CI = 1.26 to 1.81). Subgroup analysis showed sex and age had no significant moderating effect on the KOA-DS association.Conclusions: Our results provide evidence that the association between KOA and DS is bidirectional. Therefore, primary prevention and management of KOA and DS should consider this relationship.

The aim of this study was to develop a brief version of cognitive assessment test for evaluating the efficacy of treatments targeting cognitive impairments in Chinese schizophrenia patients, to examine its reliability, and establish normative data. Stratified according to age, gender, and educational level, healthy adult subjects were recruited from fifteen institutions in seven administrative regions of China and 723 valid samples were obtained, of which 50 were retested. Generalized Linear Models were conducted to analyze the effects of age, sex, and education. There was no significant difference between genders, while significant effects were demonstrated respectively among age and education on the normative data of C-BCT. The Cronbach α of C-BCT is 0.75, and the test-retest reliability (ICC) ranged from 0.62 to 0.76. Normative data of C-BCT were generated by gender, age and education, and the effects of these demographic factors were analyzed. It revealed good internal consistency and test-retest reliability of C-BCT.