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.

Patient stratification based on the risk of severe illness in emergency departments through collaborative machine learning models.

OBJECTIVES: Emergency department (ED) overcrowding presents a global challenge that inhibits prompt care for critically ill patients. Traditional 5-level triage system that heavily rely on the judgment of the triage staff could fail to detect subtle symptoms in critical patients, thus leading to delayed treatment. Unlike previous rivalry-focused approaches, our study aimed to establish a collaborative machine learning (ML) model that renders risk scores for severe illness, which may assist the triage staff to provide a better patient stratification for timely critical cares. METHODS: This retrospective study was conducted at a tertiary teaching hospital. Data were collected from January 2015 to October 2022. Demographic and clinical information were collected at triage. The study focused on severe illness as the outcome. We developed artificial neural network (ANN) models, with or without utilizing the Taiwan Triage and Acuity Scale (TTAS) score as one of the predictors. The model using the TTAS score is termed a machine-human collaborative model (ANN-MH), while the model without it is referred to as a machine-only model (ANN-MO). The predictive power of these models was assessed using the area under the receiver-operating-characteristic (AUROC) and the precision-recall curves (AUPRC); their sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1 score were compared. RESULTS: The study analyzed 668,602 ED visits from 2015 to 2022. Among them, 278,724 visits from 2015 to 2018 were used for model training and validation, while 320,201 visits from 2019 to 2022 were for testing model performance. Approximately 2.6% of visits were by severely ill patients, whose TTAS scores ranged from 1 to 5. The ANN-MH model achieved a testing AUROC of 0.918 and AUPRC of 0.369, while for the ANN-MO model the AUROC and AUPRC were 0.909 and 0.339, respectively. Based on these metrics, the ANN-MH model outperformed the ANN-MO model, and both surpassed human triage classification. Subgroup analyses further highlighted the models' capability to identify higher-risk patients within the same triage level. CONCLUSIONS: The traditional 5-level triage system often falls short, leading to under-triage of critical patients. Our models include a score-based differentiation within a triage level to offer advanced risk stratification, thereby promoting patient safety.

Managing emergency department overcrowding via ambulance diversion: a discrete event simulation model.

BACKGROUND/PURPOSE: Ambulance diversion (AD) is considered one of the possible solutions to relieve emergency department (ED) overcrowding. Study of the effectiveness of various AD strategies is prerequisite for policy-making. Our aim is to develop a tool that quantitatively evaluates the effectiveness of various AD strategies. METHODS: A simulation model and a computer simulation program were developed. Three sets of simulations were executed to evaluate AD initiating criteria, patient-blocking rules, and AD intervals, respectively. The crowdedness index, the patient waiting time for service, and the percentage of adverse patients were assessed to determine the effect of various AD policies. RESULTS: Simulation results suggest that, in a certain setting, the best timing for implementing AD is when the crowdedness index reaches the critical value, 1.0 - an indicator that ED is operating at its maximal capacity. The strategy to divert all patients transported by ambulance is more effective than to divert either high-acuity patients only or low-acuity patients only. Given a total allowable AD duration, implementing AD multiple times with short intervals generally has better effect than having a single AD with maximal allowable duration. CONCLUSION: An input-throughput-output simulation model is proposed for simulating ED operation. Effectiveness of several AD strategies on relieving ED overcrowding was assessed via computer simulations based on this model. By appropriate parameter settings, the model can represent medical resource providers of different scales. It is also feasible to expand the simulations to evaluate the effect of AD strategies on a community basis. The results may offer insights for making effective AD policies.

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.

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.

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 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.

The Impact of Ambulance and Patient Diversion on Crowdedness of Multiple Emergency Departments in a Region.

Emergency department (ED) overcrowding threatens healthcare quality. Ambulance diversion (AD) may relieve ED overcrowding; however, diverting patients from an overcrowded ED will load neighboring EDs with more patients and may result in regional overcrowding. The purpose of this study was to evaluate the impact of different diversion strategies on the crowdedness of multiple EDs in a region. The importance of regional coordination was also explored. A queuing model for patient flow was utilized to develop a computer program for simulating AD among EDs in a region. Key parameters, including patient arrival rates, percentages of patients of different acuity levels, percentage of patients transported by ambulance, and total resources of EDs, were assigned based on real data. The crowdedness indices of each ED and the regional crowdedness index were assessed to evaluate the effectiveness of various AD strategies. Diverting patients equally to all other EDs in a region is better than diverting patients only to EDs with more resources. The effect of diverting all ambulance-transported patients is similar to that of diverting only low-acuity patients. To minimize regional crowdedness, ambulatory patients should be sent to proper EDs when AD is initiated. Based on a queuing model with parameters calibrated by real data, patient flows of EDs in a region were simulated by a computer program. From a regional point of view, randomly diverting ambulatory patients provides almost no benefit. With regards to minimizing the crowdedness of the whole region, the most promising strategy is to divert all patients equally to all other EDs that are not already crowded. This result implies that communication and coordination among regional hospitals are crucial to relieve overall crowdedness. A regional coordination center may prioritize AD strategies to optimize ED utility.