Establish and validate the reliability of predictive models in bone mineral density by deep learning as examination tool for women.

While FRAX with BMD could be more precise in estimating the fracture risk, DL-based models were validated to slightly reduce the number of under- and over-treated patients when no BMD measurements were available. The validated models could be used to screen for patients at a high risk of fracture and osteoporosis. PURPOSE: Fracture risk assessment tool (FRAX) is useful in classifying the fracture risk level, and precise prediction can be achieved by estimating both clinical risk factors and bone mineral density (BMD) using dual X-ray absorptiometry (DXA). However, DXA is not frequently feasible because of its cost and accessibility. This study aimed to establish the reliability of deep learning (DL)-based alternative tools for screening patients at a high risk of fracture and osteoporosis. METHODS: Participants were enrolled from the National Bone Health Screening Project of Taiwan in this cross-sectional study. First, DL-based models were built to predict the lowest T-score value in either the lumbar spine, total hip, or femoral neck and their respective BMD values. The Bland-Altman analysis was used to compare the agreement between the models and DXA. Second, the predictive model to classify patients with a high fracture risk was built according to the estimated BMD from the first step and the FRAX score without BMD. The performance of the model was compared with the classification based on FRAX with BMD. RESULTS: Approximately 10,827 women (mean age, 65.4 ± 9.4 years) were enrolled. In the prediction of the lumbar spine BMD, total hip BMD, femoral neck BMD, and lowest T-score, the root-mean-square error (RMSE) was 0.099, 0.089, 0.076, and 0.68, respectively. The Bland-Altman analysis revealed a nonsignificant difference between the predictive models and DXA. The FRAX score with femoral neck BMD for major osteoporotic fracture risk was 9.7% ± 6.7%, whereas the risk for hip fracture was 3.3% ± 4.6%. Comparison between the classification of FRAX with and without BMD revealed the accuracy rate, positive predictive value (PPV), and negative predictive value (NPV) of 78.8%, 64.6%, and 89.9%, respectively. The area under the receiver operating characteristic curve (AUROC), accuracy rate, PPV, and NPV of the classification model were 0.913 (95% confidence interval: 0.904-0.922), 83.5%, 71.2%, and 92.2%, respectively. CONCLUSION: While FRAX with BMD could be more precise in estimating the fracture risk, DL-based models were validated to slightly reduce the number of under- and over-treated patients when no BMD measurements were available. The validated models could be used to screen for patients at a high risk of fracture and osteoporosis.

The long-term risk of cardiovascular events in patients following bariatric surgery compared to a non-surgical population with obesity and the general population: a comprehensive national cohort study.

PURPOSE: This study evaluated the differences in long-term cardiovascular events between obese patients who received bariatric surgery (BS), those who did not, and the general population (GP). METHODS: Between 2003 and 2008, patients with severe obesity, aged 18-55 years, were divided into the non-surgical (NS) and BS groups and were included in this retrospective study. We also extracted data of healthy civilians defined as the GP. The incidence of cardiovascular events, including myocardial infarction, intracranial hemorrhage, epidural hemorrhage, ischemic stroke, and transient ischemic attack, was defined as the primary end point. Patients were followed up either until the end of 2013, upon reaching the primary end point, or death. RESULTS: After propensity score matching, 1436 patients were included in both the BS and NS groups, and 4829 subjects were enrolled as the GP. Of these, 57 (3.9%), 10 (0.6%), and 30 (0.62%) subjects in the NS, BS, and GP, respectively, experienced cardiovascular events. Multivariate analysis revealed that patients with BS had a significantly lower risk of cardiovascular events (HR = 0.168; 95% CI 0.085-0.328; p < 0.001) than those in the NS group, but it was not significantly different in the BS group compared with the GP (HR = 1.202; 95% CI 0.585-2.471; p = 0.617). CONCLUSION: Long-term risk of cardiovascular events was significantly lower among patients who had BS, compared to the NS obese patients. Thus, the long-term cardiovascular risk between those who received BS and the GP had no significant difference, in a retrospective view.

Advanced Sampling Technique in Radiology Free-Text Data for Efficiently Building Text Mining Models by Deep Learning in Vertebral Fracture.

This study aims to establish advanced sampling methods in free-text data for efficiently building semantic text mining models using deep learning, such as identifying vertebral compression fracture (VCF) in radiology reports. We enrolled a total of 27,401 radiology free-text reports of X-ray examinations of the spine. The predictive effects were compared between text mining models built using supervised long short-term memory networks, independently derived by four sampling methods: vector sum minimization, vector sum maximization, stratified, and simple random sampling, using four fixed percentages. The drawn samples were applied to the training set, and the remaining samples were used to validate each group using different sampling methods and ratios. The predictive accuracy was measured using the area under the receiver operating characteristics (AUROC) to identify VCF. At the sampling ratios of 1/10, 1/20, 1/30, and 1/40, the highest AUROC was revealed in the sampling methods of vector sum minimization as confidence intervals of 0.981 (95%CIs: 0.980-0.983)/0.963 (95%CIs: 0.961-0.965)/0.907 (95%CIs: 0.904-0.911)/0.895 (95%CIs: 0.891-0.899), respectively. The lowest AUROC was demonstrated in the vector sum maximization. This study proposes an advanced sampling method, vector sum minimization, in free-text data that can be efficiently applied to build the text mining models by smartly drawing a small amount of critical representative samples.

Impact of Recurrent Weight Gain Thresholds on Comorbid Conditions Progression Following Laparoscopic Sleeve Gastrectomy.

INTRODUCTION: Defining recurrent weight gain after metabolic bariatric surgery poses a significant challenge. Our study aimed to standardize recurrent weight gain measurements in patients undergoing laparoscopic sleeve gastrectomy (LSG) and ascertain its association with comorbidity progression. METHODS: We conducted a retrospective data analysis on 122 patients who underwent LSG, tracking their progress over 2-7 years. Data on weight, blood pressure measurements, and laboratory tests were collected, focusing on the postoperative period to identify nadir weight, total weight loss, and recurrent weight gain. RESULTS: Significant weight loss and comorbidity remission were noted, with diabetes, hypertension, and dyslipidemia showing substantial remission rates of 85.71%, 68.24%, and 85.37%, respectively. The median recurrent weight gain was 6.30 kg within 12 months of the nadir. Progression proportion of diabetes, hypertension, and dyslipidemia were 8.20%, 44.26%, and 40.98%, respectively. Hypertension progression was strongly associated with a recurrent weight gain ≥ 10 kg and ≥ 20% of maximum weight loss. Dyslipidemia progression was significantly correlated with recurrent weight gain ≥ 10 kg and ≥ 20% of maximum weight loss. Diabetes progression was significantly correlated with recurrent weight gain ≥ 10% of pre-surgery body weight and ≥ 25% of maximum weight loss. A ≥ 10% weight gain of maximum weight loss did not significantly impact the progression of these conditions. CONCLUSION: Recurrent weight gain ≥ 20% of maximum weight loss can be treated as a specific threshold indicating comorbidity progression post-LSG. Standardizing the measurement of recurrent weight gain can help healthcare providers to implement targeted management strategies to optimize long-term health outcomes.

Bariatric Surgery Decreases the Risk of Non-traffic Accident-Related Fractures in Patients with Obesity: Real-world Data from Taiwan.

OBJECTIVES: The aim of this study is to investigate the impact of bariatric surgery on non-traffic accident-related fractures in patients with obesity. METHODS: This retrospective cohort study was conducted using the Taiwan National Health Insurance Research Database. Patients aged 18 to 55 years with obesity diagnosis between 2003 and 2008 were enrolled and divided into two groups: non-surgical and bariatric surgery groups. Patients with endocrine bone disease and malignancy history were excluded. Healthy patients were also randomly selected from the database and assigned to the general population group. The development of fracture was the primary end point. All patients were followed until the end of 2013 or death, whichever came first. RESULTS: After propensity score matching, 1322, 1322, and 4359 subjects were included in the bariatric surgery (BS), non-surgical (NS), and general population (GP) groups, respectively. Based on multivariate analysis, the risk of overall fractures is similar between the BS group (hazard ratio [HR] = 0.774, p = 0.164) and the NS group; nevertheless, the risk of overall fractures was higher in the BS group (HR = 2.210, p<0.001) than in the GP group. The BS group had a significantly lower risk of non-traffic accident-related fractures (HR = 0.542, p = 0.010) than the NS group but a higher risk of non-traffic accident-related fractures (HR = 1.693, p = 0.023) than the GP group. CONCLUSIONS: Bariatric surgery may decrease the risk of non-traffic accident-related fractures; however, the risk remains higher in patients with obesity than in the general population.

Decreased Long-Term Respiratory Infection Risk After Bariatric Surgery: a Comprehensive National Cohort Study.

PURPOSE: This study aims to determine whether bariatric surgery (BS) decreases the risk of respiratory tract infections (RTIs) in obese patients. MATERIALS AND METHODS: This retrospective, population-based, matched cohort study utilized data from the Taiwan National Health Insurance Research Database. All patients 18 to 55 years of age with obesity diagnosed between 2005 and 2010 were enrolled. Patients were separated into two groups based on whether they underwent BS. Two groups were selected using 1:1 propensity score matching according to age, sex, and comorbidities. The general population was also enrolled for comparison. The primary endpoint was the incidence of RTIs, including pneumonia, influenza, and bronchitis. All patients were followed up until the end of 2013, the primary endpoint, or death. RESULTS: Compared to the non-surgery group, the BS group was at significantly lower risk for RTIs (aHR 0.432, 95% CI 0.340-0.549, p < 0.001) with shorter length of hospital stay (LOH) and lower cost. Regardless of the RTI-related mortality, pneumonia, influenza, and bronchitis rates, BS did have significant protective effects on the non-surgery group. Compared to the general population, the BS group was at higher risk for RTIs (aHR 3.601, 95% CI 2.742-4.728, p < 0.001) with similar LOH and lower cost. CONCLUSION: Patients with obesity who underwent BS were at significantly lower risk for RTIs than obese patients who did not undergo BS but were at higher risk for RTIs than the general population. BS may result in a long-term reduction of the RTI risk.

Evaluation of the 10 Years' Association Between DXA Screening and Mortality in Patients Who Received Vertebroplasty in the Taiwan Population.

BACKGROUND: Osteoporotic fractures are a significant cause of morbidity and mortality affecting population worldwide. All guidelines recommended vertebral fracture assessment by dual-energy X-ray absorptiometry (DXA). This study aimed at evaluation of any associated benefits of screening with DXA in patients who had received vertebroplasty in Taiwan. METHODS: Data were obtained from the National Health Insurance Research Database (NHIRD) in Taiwan. We retrospectively compared the data of patients, who were admitted for vertebroplasty, whether they received DXA screening or not. The outcomes of interest were recurrence of spinal fracture and mortality during a follow-up period of 10 years. RESULTS: From this Taiwan national database, the screening rate of osteoporosis in patient who received vertebroplasty was 11.7%. The mean age in the non-DXA screened cohort (n=32,986) was 74.03±12.21 years (71.98% female). In the DXA screened cohort (n=4361), the mean age was 76.43±9.19 years (79.91% female). During the 10-year follow-up period, after matching, non-DXA patients had significantly higher mortality rates than their DXA counterparts, which were 42.37% and 37.73% (p-value < 0.0001), respectively. The re-fracture rates between non-DXA and DXA patients were not significantly different at 17.26% and 16.89% (p-value = 0.1766), respectively. CONCLUSION: The rate of DXA screening before patients receiving vertebroplasty was extremely low, at 11.7%. Our results showed that DXA screening before vertebroplasty in spinal fractures patients had lower mortality. From this national retrospective cohort study, routine screening of osteoporosis in spinal fracture patients can lead to reduction in mortality.

Check point to get adequate weight loss within 6-months after laparoscopic sleeve gastrectomy for morbid obesity in Asian population.

Purpose of this study is to develope a scoring system to predict the likelihood of excess body weight loss (EBWL) ≥ 50% 6-months after laparoscopic sleeve gastrectomy (LSG). From April 2016 to September 2018, data was collected from 160 patients (BMI ≥ 32) who underwent primary LSG with at least 6-months follow-up. They were separated into score generation (operated by one surgeon, n = 122) and validation groups (operated by 3 different surgeons, n = 38). EBWL at 6-months ≥ 50% was considered adequate weight loss. Independent variables including age, gender, initial body mass index (BMI), comorbidities, life-style habits, percentage of EBWL and percentage of total body weight loss at 1-week, 1-month, and 3-months were analyzed with mutivariate logistic regression to generate the scoring system. The system was applied to internal and external validation groups to determine efficacy. As results, between the score generation and internal validation groups, the only significant difference in patient characteristics was in exercise participation. EBWL at 1-month > 19.5% (1 point) and EBWL at 3-months > 37.7% (2 points) were identified as independent factors to predict EBWL at 6-months ≥ 50%. When scores were > 1, the system had 94.03% positive predictive value (PPV) and 81.82% negative predictive value (NPV) (AUC: 0.923). Internal validation scores > 1 had a 95.83% PPV and 85.71% NPV (AUC: 0.975). External validation results showed 88.59% PPV and 72.00% NPV (AUC: 0.802). We concluded that this scoring system provides a reliable, objective prediction of EBWL at 6-months ≥ 50%. Patients requiring more aggressive clinical follow-up and intervention can be detected as early as 1- to 3-months after LSG.