Background: Ventilator weaning is one of the most significant challenges in the intensive care unit (ICU). Approximately 30% of patients fail to wean, resulting in prolonged use of ventilators and increased mortality. There are numerous high-performance prediction models available today, but they require a large number of parameters to predict and are thus impractical in clinical practice. Objectives: This study aims to create an artificial intelligence (AI) model for predicting weaning time and to identify the most simplified key predictors that will allow the model to achieve adequate accuracy with as few parameters as possible. Methods: This is a retrospective study of to-be-weaned patients (n = 1439) hospitalized in the cardiac ICU of Cheng Hsin General Hospital’s Department of Cardiac Surgery from November 2018 to August 2020. The patients were divided into two groups based on whether they could be weaned within 24 h (i.e., “patients weaned within 24 h” (n = 1042) and “patients not weaned within 24 h” (n = 397)). Twenty-eight variables were collected including demographic characteristics, arterial blood gas readings, and ventilation set parameters. We created a prediction model using logistic regression and compared it to other machine learning techniques such as decision tree, random forest, support vector machine (SVM), extreme gradient boosting, and artificial neural network. Forward, backward, and stepwise selection methods were used to identify significant variables, and the receiver operating characteristic curve was used to assess the accuracy of each AI model. Results: The SVM [receiver operating characteristic curve (ROC-AUC) = 88%], logistic regression (ROC-AUC = 86%), and XGBoost (ROC-AUC = 85%) models outperformed the other five machine learning models in predicting weaning time. The accuracies in predicting patient weaning within 24 h using seven variables (i.e., expiratory minute ventilation, expiratory tidal volume, ventilation rate set, heart rate, peak pressure, pH, and age) were close to those using 28 variables. Conclusions: The model developed in this research successfully predicted the weaning success of ICU patients using a few and easily accessible parameters such as age. Therefore, it can be used in clinical practice to identify difficult-to-wean patients to improve their treatment.

(1) Background: Posterior circulation ischemic stroke has high mortality and disability rates and requires an early prediction prognosis to provide the basis for an interventional approach. Current quantitative measures are only able to accurately assess the prognosis of patients using magnetic resonance imaging (MRI). However, it is difficult to obtain MRI images in critically urgent cases. Therefore, the development of a noncontrast CT-based rapid-assist tool is needed to enhance the value of the clinical application. (2) Objective: This study aimed to develop an auxiliary-annotating noncontrast CT-efficient tool, which is based on a deep learning model, to provide a quantitative scale and the prognosis of posterior circulation ischemic stroke patients. (3) Methods: A total of 31 patients with posterior circulation ischemic stroke, diagnosed in the stroke registry at the Tri-Service General Hospital from November 2019 to July 2020, were included in the study, with a total of 578 CT images collected from noncontrast CT and MRI that were ≤ 3 days apart. A 5-fold cross validation was used to develop an image segmentation model to identify nine posterior circulation structures, and intersection over union (IoU) was used to assess the ability of the model to identify each structure. A quantitative score was integrated to assess the importance of the proportion of ischemic lesions in each posterior circulation structure, and the ROC curve was compared with the semiquantitative score for prognostic power. The prognoses of the patients were defined into two groups of 18 patients. An mRS score of 0–2 at discharge was defined as a good prognosis, while an mRS score of 3–6 was deemed to be a poor prognosis. (4) Results: The performance of the image segmentation model for identifying the nine posterior circulation structures in noncontrast CT images was evaluated. The IoU of the left cerebellum was 0.78, the IoU of the right cerebellum was 0.79, the IoU of the left occipital lobe was 0.74, the IoU of the right occipital lobe was 0.68, the IoU of the left thalamus was 0.73, the IoU of the right thalamus was 0.75, the IoU of the medulla oblongata was 0.82, and the IoU of the midbrain was 0.83. The prognostic AUC of posterior circulation patients predicted using a quantitative integrated score was 0.74, which was significantly higher than that of the pc-ASPECTS (AUC = 0.63, p = 0.035), with a sensitivity of 0.67 and a specificity of 0.72. (5) Conclusions: In this study, a deep learning model was used to develop a noncontrast CT-based quantitative integrated score tool, which is an effective tool for clinicians to assess the prognosis of posterior circulation ischemic stroke.

For patients with acute myocardial infarction scheduled to undergo percutaneous coronary stent implantation, in most cases a drug-eluting stent is recommended as the first choice for treatment. However, there is a lack of research on the effectiveness of bare-metal stents and drug-eluting stents on patients with different types of myocardial infarction. Our objective was to explore the effects of bare-metal stents and drug-eluting stents on patients with different types of myocardial infarction in terms of major cardiovascular incidents. This retrospective cohort study included 934 patients with myocardial infarction undergoing coronary artery stent implantation for the first time at the cardiac catheter room of the Tri-Service General Hospital in the Neihu District between 2014 and 2018. Patients’ information, including demographic data, laboratory data, cardiac echocardiography results, and angiocardiography results, was collected by reviewing medical records. Cox proportional hazards regression was used to adjust the potential confounding factors, and the adjusted data were then used to compare the correlation between different types of stents and major cardiovascular incidents in patients with ST-elevation myocardial infarction and non-ST-elevation myocardial infarction. After the confounding factors were adjusted, in patients with ST-elevation myocardial infarction receiving a drug-eluting stent compared with those receiving a bare-metal stent, it was found that the mortality risk was lower in terms of all causes of death (Adj-HR = 0.26, 95% CI = 0.14–0.48, p < 0.001) and cardiogenic death (Adj-HR = 0.20, 95% CI = 0.08–0.55, p = 0.002), the risk of non-fatal myocardial infarction was lower (Adj-HR = 0.17, 95% CI = 0.04–0.73, p = 0.017), and there was no difference in the risk of revascularization at the lesion site (Adj-HR = 0.59, 95% CI = 0.24–1.43, p = 0.243). It terms of the findings in patients with non-ST-elevation myocardial infarction, those receiving a drug-eluting stent had a lower risk of revascularization at the lesion site (Adj-HR = 0.48, 95% CI = 0.24–0.97, p = 0.04); however, there was no difference in the mortality risk in terms of all causes of death (Adj-HR = 0.71, 95% CI = 0.37–1.35, p = 0.296) or cardiogenic death (Adj-HR = 0.59, 95% CI = 0.18–1.90, p = 0.379),or in the risk of non-fatal myocardial infarction (Adj-HR = 0.27, 95% CI = 0.06–1.25, p = 0.093). Compared with bare-metal stents, drug-eluting stents provide better protection against death to receivers with ST-elevation myocardial infarction; however, this protection is decreased in receivers with non-ST-elevation myocardial infarction. It is recommended that for patients with non-ST-elevation myocardial infarction who are indicated to receive a drug-eluting stent, the clinical effectiveness of the treatment must be considered.

Knee osteoarthritis (KOA) inducing physiological pain and psychological health which is a public health issue in the older adults. However, research about the gender-specific effects on young–old and old–old is still scarce. The aim was to explore the vulnerability of physiology and psychology to KOA among the young–old and the old–old by gender. This case-control study recruited participants from health examinations at the Tri-Service General Hospital between March 2015 and October 2019. The Western Ontario and McMaster Universities Arthritis Index (WOMAC) and the 12-item short-form survey (SF-12) were used to evaluate the health status and quality of life (QoL) of subjects. Kellgren-Lawrence grading system (KL) was adopted to assess knee radiographs of subjects, KL grade ≥ 2 as KOA patients (KL grade ≥ 3 as severe KOA patients) and KL grade < 2 as controls. Student t-test and χ2 test were used to compare the distribution differences between KOA patients and controls, including demographic data, health statuses and QoL. The association of KOA and QoL was determined using multiple regression analysis. There were 772 subjects (young–old, n = 543; old–old, n = 229) in this study, 406 KOA patients (including 85 severe KOA patients) and 366 healthy individuals. In the young–old, KOA may play a least role in health status and QoL. However, in the old–old, males with severe KOA would cause a decrease in SF-12 mental component summary score (MCS) (β= −13.75, 95% CI: −23.90 to −3.61); however, females with severe KOA would cause a decrease in SF-12 physical functioning domain (β = −19.44; 95% CI: −35.32 to −3.56). The spectrum of anguish from KOA leads to differential reduction of QoL determined by age and gender. This study provides a glimpse on physiological and psychological need among the young–old and the old–old with KOA by gender.

The 2019 coronavirus disease pandemic disrupts synchronized lifestyles and influences an individual’s health status. However, Taiwan has limited studies on the impact of the epidemic on the health and lifestyle of its citizens. This study aims to investigate the impact on lifestyle and health status during the first wave of 2019 coronavirus disease in Taiwan. The 2008 to 2021 Taiwan Biobank database was adopted in this study, covering 29,572 participants and was designed into 3 time periods, Episodes 1, 2, and 3. The definition of metabolic syndrome (MetS) is based on the strict ministry of health and welfare. Logistic regression model was used to explore related risk factors. Prevalence rates of MetS were 16.5%, 17.0%, and 18.7% during Episodes 1, 2, and 3, respectively. When compared to the pre-pandemic prevalence of MetS, the odds ratios increased by 1.19 [95% confidence intervals (CIs): 1.02–1.38] during the nationwide Level 3 epidemic alert, particularly, in male aged 45 to 64 years old and females aged under 45 years old by 1.56 (95% CI: 1.14–2.13) and 1.89 (95% CI: 1.22–2.92), respectively. During pandemic, sweeping influences on Taiwanese health status, especially in the labor force, may provide a lesson in health promotion policy at a specific age.