Machine learning models for screening clinically significant nephrolithiasis in overweight and obese populations.

PURPOSES: Our aim is to build and evaluate models to screen for clinically significant nephrolithiasis in overweight and obesity populations using machine learning (ML) methodologies and simple health checkup clinical and urine parameters easily obtained in clinics. METHODS: We developed ML models to screen for clinically significant nephrolithiasis (kidney stone > 2 mm) in overweight and obese populations (body mass index, BMI ≥ 25 kg/m2) using gender, age, BMI, gout, diabetes mellitus, estimated glomerular filtration rate, bacteriuria, urine pH, urine red blood cell counts, and urine specific gravity. The data were collected from hospitals in Kaohsiung, Taiwan between 2012 and 2021. RESULTS: Of the 2928 subjects we enrolled, 1148 (39.21%) had clinically significant nephrolithiasis and 1780 (60.79%) did not. The testing dataset consisted of data collected from 574 subjects, 235 (40.94%) with clinically significant nephrolithiasis and 339 (59.06%) without. One model had a testing area under curve of 0.965 (95% CI, 0.9506-0.9794), a sensitivity of 0.860 (95% CI, 0.8152-0.9040), a specificity of 0.947 (95% CI, 0.9230-0.9708), a positive predictive value of 0.918 (95% CI, 0.8820-0.9544), and negative predictive value of 0.907 (95% CI, 0.8756-0.9371). CONCLUSION: This ML-based model was found able to effectively distinguish the overweight and obese subjects with clinically significant nephrolithiasis from those without. We believe that such a model can serve as an easily accessible and reliable screening tool for nephrolithiasis in overweight and obesity populations and make possible early intervention such as lifestyle modifications and medication for prevention stone complications.

Optimal deployment of automated external defibrillators in a long and narrow environment.

AIM OF THE STUDY: Public access to automated external defibrillators (AEDs) plays a key role in increasing survival outcomes for patients with out-of-hospital cardiac arrest. Based on the concept of maximizing "rescue benefit" of AEDs, we aimed to propose a systematic methodology for optimizing the deployment of AEDs, and develop such strategies for long and narrow spaces. METHODS: We classified the effective coverage of an AED in hot, warm, and cold zones. The AEDs were categorized, according to their accessibility, as fixed, summonable, or patrolling types. The overall rescue benefit of the AEDs were evaluated by the weighted size of their collective hot zones. The optimal strategies for the deployment of AEDs were derived mathematically and numerically verified by computer programs. RESULTS: To maximize the overall rescue benefit of the AEDs, the AEDs should avoid overlapping with each other's coverage as much as possible. Specific rules for optimally deploying one, two, or multiple AEDs, and various types of AEDs are summarized and presented. CONCLUSION: A methodology for assessing the rescue benefit of deployed AEDs was proposed, and deployment strategies for maximizing the rescue benefit of AEDs along a long, narrow, corridor-like, finite space were derived. The strategies are simple and readily implementable. Our methodology can be easily generalized to search for optimal deployment of AEDs in planar areas or three-dimensional spaces.

Does COVID-19 Vaccination Cause Storage Lower Urinary Tract Symptoms?

We investigated the storage lower urinary tract symptoms (LUTS) before and after the first dose of coronavirus disease 2019 (COVID-19) vaccine and the association between pre-vaccinated overactive bladder (OAB) and the worsening of storage LUTS following COVID-19 vaccination. This cross-sectional study in a third-level hospital in Taiwan used the validated pre- and post-vaccinated Overactive Bladder Symptom Score (OABSS). Diagnosis of OAB was made using pre-vaccinated OABSS. The deterioration of storage LUTS was assessed as the increased score of OABSS following vaccination. Of 889 subjects, up to 13.4% experienced worsened storage LUTS after vaccination. OAB was significantly associated with an increased risk of worsening urinary urgency (p = 0.030), frequency (p = 0.027), and seeking medical assistance due to urinary adverse events (p < 0.001) after vaccination. The OAB group faced significantly greater changes in OABSS-urgency (p = 0.003), OABSS-frequency (p = 0.025), and total OABSS (p = 0.014) after vaccination compared to those observed in the non-OAB group. Multivariate regression revealed that pre-vaccinated OAB (p = 0.003) was a risk for the deterioration of storage LUTS. In conclusion, storage LUTS may deteriorate after vaccination. OAB was significantly associated with higher risk and greater changes in worsening storage LUTS. Storage LUTS should be closely monitored after COVID-19 vaccination, especially in those OAB patients.

Prediction of the Uric Acid Component in Nephrolithiasis Using Simple Clinical Information about Metabolic Disorder and Obesity: A Machine Learning-Based Model.

There is a great need for a diagnostic tool using simple clinical information collected from patients to diagnose uric acid (UA) stones in nephrolithiasis. We built a predictive model making use of machine learning (ML) methodologies entering simple parameters easily obtained at the initial clinical visit. Socio-demographic, health, and clinical data from two cohorts (A and B), both diagnosed with nephrolithiasis, one between 2012 and 2016 and the other between June and December 2020, were collected before nephrolithiasis treatment. A ML-based model for predicting UA stones in nephrolithiasis was developed using eight simple parameters-sex, age, gout, diabetes mellitus, body mass index, estimated glomerular filtration rate, bacteriuria, and urine pH. Data from Cohort A were used for model training and validation (ratio 3:2), while data from Cohort B were used only for validation. One hundred and forty-six (13.3%) out of 1098 patients in Cohort A and 3 (4.23%) out of 71 patients in Cohort B had pure UA stones. For Cohort A, our model achieved a validation AUC (area under ROC curve) of 0.842, with 0.8475 sensitivity and 0.748 specificity. For Cohort B, our model achieved 0.936 AUC, with 1.0 sensitivity, and 0.912 specificity. This ML-based model provides a convenient and reliable method for diagnosing urolithiasis. Using only eight readily available clinical parameters, including information about metabolic disorder and obesity, it distinguished pure uric acid stones from other stones before treatment.

Prediction of hospitalization using artificial intelligence for urgent patients in the emergency department.

Timely assessment to accurately prioritize patients is crucial for emergency department (ED) management. Urgent (i.e., level-3, on a 5-level emergency severity index system) patients have become a challenge since under-triage and over-triage often occur. This study was aimed to develop a computational model by artificial intelligence (AI) methodologies to accurately predict urgent patient outcomes using data that are readily available in most ED triage systems. We retrospectively collected data from the ED of a tertiary teaching hospital between January 1, 2015 and December 31, 2019. Eleven variables were used for data analysis and prediction model building, including 1 response, 2 demographic, and 8 clinical variables. A model to predict hospital admission was developed using neural networks and machine learning methodologies. A total of 282,971 samples of urgent (level-3) visits were included in the analysis. Our model achieved a validation area under the curve (AUC) of 0.8004 (95% CI 0.7963-0.8045). The optimal cutoff value identified by Youden's index for determining hospital admission was 0.5517. Using this cutoff value, the sensitivity was 0.6721 (95% CI 0.6624-0.6818), and the specificity was 0.7814 (95% CI 0.7777-0.7851), with a positive predictive value of 0.3660 (95% CI 0.3586-0.3733) and a negative predictive value of 0.9270 (95% CI 0.9244-0.9295). Subgroup analysis revealed that this model performed better in the nontraumatic adult subgroup and achieved a validation AUC of 0.8166 (95% CI 0.8199-0.8212). Our AI model accurately assessed the need for hospitalization for urgent patients, which constituted nearly 70% of ED visits. This model demonstrates the potential for streamlining ED operations using a very limited number of variables that are readily available in most ED triage systems. Subgroup analysis is an important topic for future investigation.

Macrophage metalloelastase (MMP12) regulates adipose tissue expansion, insulin sensitivity, and expression of inducible nitric oxide synthase.

Macrophage metalloelastase, a matrix metallopeptidase (MMP12) predominantly expressed by mature tissue macrophages, is implicated in pathological processes. However, physiological functions for MMP12 have not been described. Because mRNA levels for the enzyme increase markedly in adipose tissue of obese mice, we investigated the role of MMP12 in adipose tissue expansion and insulin resistance. In humans, MMP12 expression correlated positively and significantly with insulin resistance, TNF-α expression, and the number of CD14(+)CD206(+) macrophages in adipose tissue. MMP12 was the most abundant matrix metallopeptidase detected by proteomic analysis of conditioned medium of M2 macrophages and dendritic cells. In contrast, it was detected only at low levels in bone marrow derived macrophages and M1 macrophages. When mice received a high-fat diet, adipose tissue mass increased and CD11b(+)F4/80(+)CD11c(-) macrophages accumulated to a greater extent in MMP12-deficient (Mmp12(-/-)) mice than in wild-type mice (Mmp12(+/+)). Despite being markedly more obese, fat-fed Mmp12(-/-) mice were more insulin sensitive than fat-fed Mmp12(+/+) mice. Expression of inducible nitric oxide synthase (Nos2) by Mmp12(-/-) macrophages was significantly impaired both in vivo and in vitro, suggesting that MMP12 might mediate nitric oxide production during inflammation. We propose that MMP12 acts as a double-edged sword by promoting insulin resistance while combatting adipose tissue expansion.