Biosignals such as electrocardiogram or photoplethysmogram are widely used for determining and monitoring the medical condition of patients. It was recently discovered that more information could be gathered from biosignals by applying artificial intelligence (AI). At present, one of the most impactful advancements in AI is deep learning. Deep learning-based models can extract important features from raw data without feature engineering by humans, provided the amount of data is sufficient. This AI-enabled feature presents opportunities to obtain latent information that may be used as a digital biomarker for detecting or predicting a clinical outcome or event without further invasive evaluation. However, the black box model of deep learning is difficult to understand for clinicians familiar with a conventional method of analysis of biosignals. A basic knowledge of AI and machine learning is required for the clinicians to properly interpret the extracted information and to adopt it in clinical practice. This review covers the basics of AI and machine learning, and the feasibility of their application to real-life situations by clinicians in the near future.

Park TJ, et al. Yonsei Med J. 2022 Jul;63(7):692-700. https://doi.org/10.3349/ymj.2022.63.7.692

Korean Circulation Journal 대한심장학회지 순환기 You SC, et al. Korean Circ J. 2022 Dec;52:e112. https://doi.org/10.4070/kcj.2022.0294

This study aimed to investigate the association between glucose dysregulation and delirium after non-cardiac surgery. Among a total of 203,787 patients who underwent non-cardiac surgery between January 2011 and June 2019 at our institution, we selected 61,805 with available preoperative blood glucose levels within 24 h before surgery. Patients experiencing glucose dysregulation were divided into three groups: hyperglycemia, hypoglycemia, and both. We compared the incidence of postoperative delirium within 30 days after surgery between exposed and unexposed patients according to the type of glucose dysregulation. The overall incidence of hyperglycemia, hypoglycemia, and both was 5851 (9.5%), 1452 (2.3%), and 145 (0.2%), respectively. The rate of delirium per 100 person-months of the exposed group was higher than that of the unexposed group in all types of glucose dysregulation. After adjustment, the hazard ratios of glucose dysregulation in the development of delirium were 1.35 (95% CI, 1.18–1.56) in hyperglycemia, 1.36 (95% CI, 1.06–1.75) in hypoglycemia, and 3.14 (95% CI, 1.27–7.77) in both. The subgroup analysis showed that exposure to hypoglycemia or both to hypo- and hyperglycemia was not associated with delirium in diabetic patients, but hyperglycemia was consistently associated with postoperative delirium regardless of the presence of diabetes. Preoperative glucose dysregulation was associated with increased risk of delirium after non-cardiac surgery. Our findings may be helpful for preventing postoperative delirium, and further investigations are required to verify the association and mechanisms for the effect we observed.

Background: Mood disorder has emerged as a serious concern for public health; in particular, bipolar disorder has a less favorable prognosis than depression. Although prompt recognition of depression conversion to bipolar disorder is needed, early prediction is challenging due to overlapping symptoms. Recently, there have been attempts to develop a prediction model by using federated learning. Federated learning in medical fields is a method for training multi-institutional machine learning models without patient-level data sharing. Objective: This study aims to develop and validate a federated, differentially private multi-institutional bipolar transition prediction model. Methods: This retrospective study enrolled patients diagnosed with the first depressive episode at 5 tertiary hospitals in South Korea. We developed models for predicting bipolar transition by using data from 17,631 patients in 4 institutions. Further, we used data from 4541 patients for external validation from 1 institution. We created standardized pipelines to extract large-scale clinical features from the 4 institutions without any code modification. Moreover, we performed feature selection in a federated environment for computational efficiency and applied differential privacy to gradient updates. Finally, we compared the federated and the 4 local models developed with each hospital's data on internal and external validation data sets. Results: In the internal data set, 279 out of 17,631 patients showed bipolar disorder transition. In the external data set, 39 out of 4541 patients showed bipolar disorder transition. The average performance of the federated model in the internal test (area under the curve [AUC] 0.726) and external validation (AUC 0.719) data sets was higher than that of the other locally developed models (AUC 0.642-0.707 and AUC 0.642-0.699, respectively). In the federated model, classifications were driven by several predictors such as the Charlson index (low scores were associated with bipolar transition, which may be due to younger age), severe depression, anxiolytics, young age, and visiting months (the bipolar transition was associated with seasonality, especially during the spring and summer months). Conclusions: We developed and validated a differentially private federated model by using distributed multi-institutional psychiatric data with standardized pipelines in a real-world environment. The federated model performed better than models using local data only.

Background: Machine-learning techniques are useful for creating prediction models in clinical practice. This study aimed to construct a prediction model of postoperative 30-day mortality based on an automatically extracted electronic preoperative evaluation sheet. Methods: We used data from 276,341 consecutive adult patients who underwent non-cardiac surgery between January 2011 and December 2020 at a tertiary center for model development and internal validation, and another dataset from 63,384 patients between January 2011 and October 2021 at another center for external validation. Postoperative 30-day mortality was 0.16%. We developed an extreme gradient boosting (XGB) prediction model using only variables from preoperative evaluation sheets. Results: The model yielded an area under the curve of 0.960 and an area under the precision and recall curve of 0.216, which were 0.932 and 0.122, respectively, in the external validation set. The optimal threshold calculated by Youden’s J statistic had a sensitivity of 0.885 and specificity of 0.914. In an additional analysis with balanced distribution, the model showed a similar predictive value. Conclusion: We presented a machine-learning prediction model for 30-day mortality after non-cardiac surgery using preoperative variables automatically extracted from electronic medical records and validated the model in a multi-center setting. Our model may help clinicians predict postoperative outcomes.