A Deep-Learning Algorithm-Enhanced Electrocardiogram Interpretation for Detecting Pulmonary Embolism.

Background: The early diagnosis of pulmonary embolism (PE) remains a challenge. Electrocardiograms (ECGs) and D-dimer levels are used to screen potential cases. Objective: To develop a deep learning model (DLM) to detect PE using ECGs and investigate the clinical value of false detections in patients without PE. Methods: Among patients who visited the emergency department between 2011 and 2019, PE cases were identified through a review of medical records. Non-PE ECGs were collected from patients without a diagnostic code for PE. There were 113 PE and 51,456 non-PE ECGs in the training and validation sets for developing the DLM, respectively, and 27 PE and 13,105 non-PE cases in an independent testing set for performance validation. A human-machine competition was conducted from the testing set to compare the performance of the DLM with that of physicians. Receiver operating characteristic (ROC) curves, sensitivity, and specificity were used to determine the diagnostic value. Survival analysis was used to assess the prognosis of the patients without PE, stratified by DLM prediction. Results: The DLM was as effective as physicians in diagnosing PE, with 70.8% sensitivity and 69.7% specificity. The area under the ROC curve of DLM was 0.778 in the testing set and up to 0.9 with D-dimer and demographic data. The non-PE patients whose ECG was misclassified as PE by DLM had higher all-cause mortality [hazard ratio (HR) 2.13 (1.51-3.02)] and risk of non-cardiovascular hospitalization [HR 1.55 (1.42-1.68)] than those correctly classified. Conclusions: A DLM-enhanced ECG system may prompt PE recognition and provide prognostic outcomes in patients with false-positive predictions.

Erythrocyte indices and localized stage II/III periodontitis in military young men and women: CHIEF oral health study.

BACKGROUND: Prior studies have shown an association between generalized periodontitis and anemia in older or undernourished adults. The aim of the study was to examine the associations of erythrocyte indices with localized periodontitis in robust young adults, which has never been reported before. METHODS: The study included 1286 military participants, aged 19-40 years, with regular exercise training in Hualien, Taiwan. Localized periodontitis was grouped to healthy/stage I and stage II/III (n = 803 and 325) in men and (n = 130 and 28) in women according to the 2017 criteria of the world workshop. Systemic inflammation was evaluated by leukocyte counts. Multiple logistic regression analysis with adjustment for age, tobacco smoking status, betel nut chewing status, body mass index and leucocyte counts were used to determine the associations. RESULTS: Greater mean corpuscular volume in young men [odds ratio (OR) and 95% confidence intervals 1.03 (1.01-1.06)], and greater hematocrit and hemoglobin levels in young women were associated with a higher risk of localized stage II/III periodontitis [OR: 1.17 (1.02-1.34) and 1.60 (1.06-2.41), respectively]. However, there were no associations for erythrocyte counts. CONCLUSIONS: The localized stage II/III periodontitis risk increased with greater erythrocyte indices in robust young adults. This finding could be explained in part by that localized periodontitis may promote physical stress, possibly resulting in an increase of erythrocyte indices. On the other side, greater physical fitness associated with a lower risk of periodontitis may consume iron storage in the body, leading to exercise-induced anemia or smaller erythrocyte volume.

Associations of decayed teeth and localized periodontitis with mental stress in young adults: CHIEF oral health study.

The associations of mental stress with decayed teeth in children and periodontitis in old-aged adults have been described. However, the associations for young adults were not clear. This study aimed to examine the associations of decayed teeth and localized periodontitis with mental stress in young adults. This study included 334 military recruiters, aged 19-45 years in Taiwan. Mental stress was assessed by the brief symptom rating scale-5 (BSRS-5), including five domains: anxiety, depression, hostility, interpersonal sensitivity and insomnia (maximum score of 20). Those with symptomatic mental stress were defined as having BSRS-5 > 5 (n = 34). Multiple linear and logistic regression models were used to determine the associations of decayed tooth numbers and periodontitis with BSRS-5, with adjustments for age, sex, education level, physical activity, body weight category and smoking status. The BSRS-5 was positively correlated with decayed tooth numbers [ß: 0.26 (95% confidence interval: 0.01-0.52)]. Those who had more than two decayed teeth [odds ratio: 3.59 (1.52-8.46)] had a higher risk of symptomatic mental stress. In contrast, the correlation between BSRS-5 and localized severer periodontitis was null. Our study recommended that decayed teeth instead of localized periodontitis, was a risk factor for mental stress in young adults.

Association between mild anemia and physical fitness in a military male cohort: The CHIEF study.

Anemia defined as reduced hemoglobin levels of red blood cells may carry less oxygen to skeletal muscle and impair physical performance. Previous studies have shown that exercise intolerance was related to moderate or severe anemia, however, the relationship to mild anemia was unknown. We investigated the cross-sectional association of mild anemia defined as a hemoglobin level of 10.0-13.9 g/dL with physical fitness in 3,666 military young males in Taiwan in 2014. Aerobic fitness was evaluated by 3000-meter run test, and anaerobic fitness was evaluated by 2-minute sit-ups and 2-minute push-ups, respectively. Multiple logistic regressions for the best 10% and the worst 10% performers were used to determine the relationship. There were 343 mild anemic males in whom 47.8% were microcytic anemia and 3,323 non-anemic males for the analysis. The multiple logistic regression shows that as compared with non-anemic males, mild anemic males were more likely to be the worst 10% performers in the 3000-meter run test (odds ratios (OR) and 95% confidence intervals: 1.47, 1.01-2.14) after adjusting for age, service specialty, body mass index, waist size, mean blood pressure, unhealthy behaviors, lipid profiles, and exercise frequency. On the contrary, mild anemic males had higher possibility to be the best 10% performers in the 2-minute push-ups test (OR: 1.48, 1.08-2.04). However, there was no association between mild anemia and 2-minute sit-ups. Our findings suggest that unspecified mild anemia might be associated with lower cardiorespiratory fitness but not with anaerobic fitness in physically active military males.