No abstract

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 <italic>P</italic>&lt;.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%, <italic>P</italic>=.002) after CDSS implementation. The proportion of hospitalization time 7 days or less significantly increased by 7.837% (95% CI 1.798%-13.876%, <italic>P</italic>=.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.

Purpose Acute aortic syndrome is a constellation of life-threatening medical conditions for which rapid assessment and targeted intervention are important for the prognosis of patients who are at high risk of in-hospital death. The current study aims to develop and externally validate an early prediction mortality model that can be used to identify high-risk patients with acute aortic syndrome in the emergency department. Patients and Methods This retrospective multi-center observational study enrolled 1088 patients with acute aortic syndrome admitted to the emergency departments of two hospitals in China between January 2017 and March 2021 for model development. A total of 210 patients with acute aortic syndrome admitted to the emergency departments of Peking University Third Hospital between January 2007 and December 2021 was enrolled for model validation. Demographics and clinical factors were collected at the time of emergency department admission. The predictive variables were determined by referring to the results of previous studies and the baseline analysis of this study. The study’s endpoint was in-hospital death. To assess internal validity, we used a fivefold cross-validation method. Model performance was validated internally and externally by evaluating model discrimination using the area under the receiver-operating characteristic curve (AUC). A nomogram was developed based on the binary regression results. Results In the development cohort, 1088 patients with acute aortic syndromes were included, and 88 (8.1%) patients died during hospitalization. In the validation cohort, 210 patients were included, and 20 (9.5%) patients died during hospitalization. The final model included the following variables: digestive system symptoms (OR=2.25; P=0.024), any pulse deficit (OR=7.78; P<0.001), creatinine (µmol/L)(OR=1.00; P=0.018), lesion extension to iliac vessels (OR=4.49; P<0.001), pericardial effusion (OR=2.67; P=0.008), and Stanford type A (OR=10.46; P<0.001). The model’s AUC was 0.838 (95% CI 0.784–0.892) in the development cohort and 0.821 (95% CI 0.750–0.891) in the validation cohort, and the Hosmer–Lemeshow test showed p=0.597. The fivefold cross-validation demonstrated a mean accuracy of 0.94, a mean precision of 0.67, and a mean recall of 0.13. Conclusion This risk prediction tool uses simple variables to provide robust prediction of the risk of in-hospital death from acute aortic syndrome and validated well in an independent cohort. The tool can help emergency clinicians quickly identify high-risk acute aortic syndrome patients, although further studies are needed for verifying the prospective data and the results of our study.