OBJECTIVE: This study aims to explore the correlation between the angle of progression (AOP) and spontaneous vaginal delivery (SVD) for term nulliparous women before the onset of labor. Additionally, it evaluates the diagnostic efficacy of AOP in predicting SVD in term nulliparous women.
METHODS: In this retrospective observational study, data from nulliparous women without contraindications for vaginal delivery, with a singleton pregnancy ≥37 weeks, and before the onset of labor were included. Transperineal ultrasound was performed to collect AOP. The date and mode of delivery were tracked, to assess the correlation between AOP and SVD in term nulliparous women. Receiver operating characteristic (ROC) curve analysis was used to evaluate the diagnostic efficacy of AOP in predicting SVD for term nulliparous women.
RESULTS: The SVD-failure (SVD-f) group exhibited a significantly lower AOP compared with the SVD group (88.43° vs 95.72°, P < .001). Logistic regression analysis revealed that AOP was associated with SVD in term nulliparous women (OR = 1.051). ROC curve analysis demonstrated that the area under the ROC curve with AOP 84° as the threshold was 0.663, with a sensitivity of 85.25% and specificity of 43.18%. Considering a sensitivity and specificity of 90%, the dual cut-off values for term nulliparous women for SVD were 81° and 104°, respectively.
CONCLUSIONS: A positive correlation was identified between AOP and SVD for nulliparous women after 37 weeks and before the onset of labor. Notably, term nulliparous women with AOP exceeding 104° exhibited a higher probability of SVD.

UNASSIGNED: The incidence of sudden unexpected infant death (SUID) in the United States has persisted at roughly the same level since the mid-2000s, despite intensive prevention efforts around safe sleep. Disparities in outcomes across racial and socioeconomic lines also persist. These disparities are reflected in the spatial distribution of cases across neighborhoods. Strategies for prevention should be targeted precisely in space and time to further reduce SUID and correct disparities.
UNASSIGNED: We sought to aid neighborhood-level prevention efforts by characterizing communities where SUID occurred in Cook County, IL, from 2015 to 2019 and predicting where it would occur in 2021-2025 using a semiautomated, reproducible workflow based on open-source software and data.
UNASSIGNED: This cross-sectional retrospective study queried geocoded medical examiner data from 2015-2019 to identify SUID cases in Cook County, IL, and aggregated them to \"communities\" as the unit of analysis. We compared demographic factors in communities affected by SUID versus those unaffected using Wilcoxon rank sum statistical testing. We used social vulnerability indicators from 2014 to train a negative binomial prediction model for SUID case counts in each given community for 2015-2019. We applied indicators from 2020 to the trained model to make predictions for 2021-2025.
UNASSIGNED: Validation of our query of medical examiner data produced 325 finalized cases with a sensitivity of 95% (95% CI 93%-97%) and a specificity of 98% (95% CI 94%-100%). Case counts at the community level ranged from a minimum of 0 to a maximum of 17. A map of SUID case counts showed clusters of communities in the south and west regions of the county. All communities with the highest case counts were located within Chicago city limits. Communities affected by SUID exhibited lower median proportions of non-Hispanic White residents at 17% versus 60% (P<.001) and higher median proportions of non-Hispanic Black residents at 32% versus 3% (P<.001). Our predictive model showed moderate accuracy when assessed on the training data (Nagelkerke R2=70.2% and RMSE=17.49). It predicted Austin (17 cases), Englewood (14 cases), Auburn Gresham (12 cases), Chicago Lawn (12 cases), and South Shore (11 cases) would have the largest case counts between 2021 and 2025.
UNASSIGNED: Sharp racial and socioeconomic disparities in SUID incidence persisted within Cook County from 2015 to 2019. Our predictive model and maps identify precise regions within the county for local health departments to target for intervention. Other jurisdictions can adapt our coding workflows and data sources to predict which of their own communities will be most affected by SUID.

Postacute sequelae of COVID-19 (PASC), also known as long COVID, is a broad grouping of a range of long-term symptoms following acute COVID-19. These symptoms can occur across a range of biological systems, leading to challenges in determining risk factors for PASC and the causal etiology of this disorder. An understanding of characteristics that are predictive of future PASC is valuable, as this can inform the identification of high-risk individuals and future preventative efforts. However, current knowledge regarding PASC risk factors is limited.
Using a sample of 55,257 patients (at a ratio of 1 patient with PASC to 4 matched controls) from the National COVID Cohort Collaborative, as part of the National Institutes of Health Long COVID Computational Challenge, we sought to predict individual risk of PASC diagnosis from a curated set of clinically informed covariates. The National COVID Cohort Collaborative includes electronic health records for more than 22 million patients from 84 sites across the United States.
We predicted individual PASC status, given covariate information, using Super Learner (an ensemble machine learning algorithm also known as stacking) to learn the optimal combination of gradient boosting and random forest algorithms to maximize the area under the receiver operator curve. We evaluated variable importance (Shapley values) based on 3 levels: individual features, temporal windows, and clinical domains. We externally validated these findings using a holdout set of randomly selected study sites.
We were able to predict individual PASC diagnoses accurately (area under the curve 0.874). The individual features of the length of observation period, number of health care interactions during acute COVID-19, and viral lower respiratory infection were the most predictive of subsequent PASC diagnosis. Temporally, we found that baseline characteristics were the most predictive of future PASC diagnosis, compared with characteristics immediately before, during, or after acute COVID-19. We found that the clinical domains of health care use, demographics or anthropometry, and respiratory factors were the most predictive of PASC diagnosis.
The methods outlined here provide an open-source, applied example of using Super Learner to predict PASC status using electronic health record data, which can be replicated across a variety of settings. Across individual predictors and clinical domains, we consistently found that factors related to health care use were the strongest predictors of PASC diagnosis. This indicates that any observational studies using PASC diagnosis as a primary outcome must rigorously account for heterogeneous health care use. Our temporal findings support the hypothesis that clinicians may be able to accurately assess the risk of PASC in patients before acute COVID-19 diagnosis, which could improve early interventions and preventive care. Our findings also highlight the importance of respiratory characteristics in PASC risk assessment.
RR2-10.1101/2023.07.27.23293272.

BACKGROUND: The use of technologies has had a significant impact on patient safety and the quality of care and has increased globally. In the literature, it has been reported that people die annually due to adverse events (AEs), and various methods exist for investigating and measuring AEs. However, some methods have a limited scope, data extraction, and the need for data standardization. In Brazil, there are few studies on the application of trigger tools, and this study is the first to create automated triggers in ambulatory care.
OBJECTIVE: This study aims to develop a machine learning (ML)-based automated trigger for outpatient health care settings in Brazil.
METHODS: A mixed methods research will be conducted within a design thinking framework and the principles will be applied in creating the automated triggers, following the stages of (1) empathize and define the problem, involving observations and inquiries to comprehend both the user and the challenge at hand; (2) ideation, where various solutions to the problem are generated; (3) prototyping, involving the construction of a minimal representation of the best solutions; (4) testing, where user feedback is obtained to refine the solution; and (5) implementation, where the refined solution is tested, changes are assessed, and scaling is considered. Furthermore, ML methods will be adopted to develop automated triggers, tailored to the local context in collaboration with an expert in the field.
RESULTS: This protocol describes a research study in its preliminary stages, prior to any data gathering and analysis. The study was approved by the members of the organizations within the institution in January 2024 and by the ethics board of the University of São Paulo and the institution where the study will take place. in May 2024. As of June 2024, stage 1 commenced with data gathering for qualitative research. A separate paper focused on explaining the method of ML will be considered after the outcomes of stages 1 and 2 in this study.
CONCLUSIONS: After the development of automated triggers in the outpatient setting, it will be possible to prevent and identify potential risks of AEs more promptly, providing valuable information. This technological innovation not only promotes advances in clinical practice but also contributes to the dissemination of techniques and knowledge related to patient safety. Additionally, health care professionals can adopt evidence-based preventive measures, reducing costs associated with AEs and hospital readmissions, enhancing productivity in outpatient care, and contributing to the safety, quality, and effectiveness of care provided. Additionally, in the future, if the outcome is successful, there is the potential to apply it in all units, as planned by the institutional organization.
UNASSIGNED: PRR1-10.2196/55466.

BACKGROUND: Diabetic ketoacidosis (DKA) is the leading cause of morbidity and mortality in pediatric type 1 diabetes (T1D), occurring in approximately 20% of patients, with an economic cost of $5.1 billion/year in the United States. Despite multiple risk factors for postdiagnosis DKA, there is still a need for explainable, clinic-ready models that accurately predict DKA hospitalization in established patients with pediatric T1D.
OBJECTIVE: We aimed to develop an interpretable machine learning model to predict the risk of postdiagnosis DKA hospitalization in children with T1D using routinely collected time-series of electronic health record (EHR) data.
METHODS: We conducted a retrospective case-control study using EHR data from 1787 patients from among 3794 patients with T1D treated at a large tertiary care US pediatric health system from January 2010 to June 2018. We trained a state-of-the-art; explainable, gradient-boosted ensemble (XGBoost) of decision trees with 44 regularly collected EHR features to predict postdiagnosis DKA. We measured the model\'s predictive performance using the area under the receiver operating characteristic curve-weighted F1-score, weighted precision, and recall, in a 5-fold cross-validation setting. We analyzed Shapley values to interpret the learned model and gain insight into its predictions.
RESULTS: Our model distinguished the cohort that develops DKA postdiagnosis from the one that does not (P<.001). It predicted postdiagnosis DKA risk with an area under the receiver operating characteristic curve of 0.80 (SD 0.04), a weighted F1-score of 0.78 (SD 0.04), and a weighted precision and recall of 0.83 (SD 0.03) and 0.76 (SD 0.05) respectively, using a relatively short history of data from routine clinic follow-ups post diagnosis. On analyzing Shapley values of the model output, we identified key risk factors predicting postdiagnosis DKA both at the cohort and individual levels. We observed sharp changes in postdiagnosis DKA risk with respect to 2 key features (diabetes age and glycated hemoglobin at 12 months), yielding time intervals and glycated hemoglobin cutoffs for potential intervention. By clustering model-generated Shapley values, we automatically stratified the cohort into 3 groups with 5%, 20%, and 48% risk of postdiagnosis DKA.
CONCLUSIONS: We have built an explainable, predictive, machine learning model with potential for integration into clinical workflow. The model risk-stratifies patients with pediatric T1D and identifies patients with the highest postdiagnosis DKA risk using limited follow-up data starting from the time of diagnosis. The model identifies key time points and risk factors to direct clinical interventions at both the individual and cohort levels. Further research with data from multiple hospital systems can help us assess how well our model generalizes to other populations. The clinical importance of our work is that the model can predict patients most at risk for postdiagnosis DKA and identify preventive interventions based on mitigation of individualized risk factors.

BACKGROUND: A coordinated care system helps provide timely access to treatment for suspected acute stroke. In Northwestern Ontario (NWO), Canada, communities are widespread with several hospitals offering various diagnostic equipment and services. Thus, resources are limited, and health care providers must often transfer patients with stroke to different hospital locations to ensure the most appropriate care access within recommended time frames. However, health care providers frequently situated temporarily (locum) in NWO or providing care remotely from other areas of Ontario may lack sufficient information and experience in the region to access care for a patient with a time-sensitive condition. Suboptimal decision-making may lead to multiple transfers before definitive stroke care is obtained, resulting in poor outcomes and additional health care system costs.
OBJECTIVE: We aimed to develop a tool to inform and assist NWO health care providers in determining the best transfer options for patients with stroke to provide the most efficient care access. We aimed to develop an app using a comprehensive geomapping navigation and estimation system based on machine learning algorithms. This app uses key stroke-related timelines including the last time the patient was known to be well, patient location, treatment options, and imaging availability at different health care facilities.
METHODS: Using historical data (2008-2020), an accurate prediction model using machine learning methods was developed and incorporated into a mobile app. These data contained parameters regarding air (Ornge) and land medical transport (3 services), which were preprocessed and cleaned. For cases in which Ornge air services and land ambulance medical transport were both involved in a patient transport process, data were merged and time intervals of the transport journey were determined. The data were distributed for training (35%), testing (35%), and validation (30%) of the prediction model.
RESULTS: In total, 70,623 records were collected in the data set from Ornge and land medical transport services to develop a prediction model. Various learning models were analyzed; all learning models perform better than the simple average of all points in predicting output variables. The decision tree model provided more accurate results than the other models. The decision tree model performed remarkably well, with the values from testing, validation, and the model within a close range. This model was used to develop the \"NWO Navigate Stroke\" system. The system provides accurate results and demonstrates that a mobile app can be a significant tool for health care providers navigating stroke care in NWO, potentially impacting patient care and outcomes.
CONCLUSIONS: The NWO Navigate Stroke system uses a data-driven, reliable, accurate prediction model while considering all variations and is simultaneously linked to all required acute stroke management pathways and tools. It was tested using historical data, and the next step will to involve usability testing with end users.

BACKGROUND: Patients with heart failure (HF) are the most commonly readmitted group of adult patients in Germany. Most patients with HF are readmitted for noncardiovascular reasons. Understanding the relevance of HF management outside the hospital setting is critical to understanding HF and factors that lead to readmission. Application of machine learning (ML) on data from statutory health insurance (SHI) allows the evaluation of large longitudinal data sets representative of the general population to support clinical decision-making.
OBJECTIVE: This study aims to evaluate the ability of ML methods to predict 1-year all-cause and HF-specific readmission after initial HF-related admission of patients with HF in outpatient SHI data and identify important predictors.
METHODS: We identified individuals with HF using outpatient data from 2012 to 2018 from the AOK Baden-Württemberg SHI in Germany. We then trained and applied regression and ML algorithms to predict the first all-cause and HF-specific readmission in the year after the first admission for HF. We fitted a random forest, an elastic net, a stepwise regression, and a logistic regression to predict readmission by using diagnosis codes, drug exposures, demographics (age, sex, nationality, and type of coverage within SHI), degree of rurality for residence, and participation in disease management programs for common chronic conditions (diabetes mellitus type 1 and 2, breast cancer, chronic obstructive pulmonary disease, and coronary heart disease). We then evaluated the predictors of HF readmission according to their importance and direction to predict readmission.
RESULTS: Our final data set consisted of 97,529 individuals with HF, and 78,044 (80%) were readmitted within the observation period. Of the tested modeling approaches, the random forest approach best predicted 1-year all-cause and HF-specific readmission with a C-statistic of 0.68 and 0.69, respectively. Important predictors for 1-year all-cause readmission included prescription of pantoprazole, chronic obstructive pulmonary disease, atherosclerosis, sex, rurality, and participation in disease management programs for type 2 diabetes mellitus and coronary heart disease. Relevant features for HF-specific readmission included a large number of canonical HF comorbidities.
CONCLUSIONS: While many of the predictors we identified were known to be relevant comorbidities for HF, we also uncovered several novel associations. Disease management programs have widely been shown to be effective at managing chronic disease; however, our results indicate that in the short term they may be useful for targeting patients with HF with comorbidity at increased risk of readmission. Our results also show that living in a more rural location increases the risk of readmission. Overall, factors beyond comorbid disease were relevant for risk of HF readmission. This finding may impact how outpatient physicians identify and monitor patients at risk of HF readmission.

BACKGROUND: With the progressive increase in aging populations, the use of opportunistic computed tomography (CT) scanning is increasing, which could be a valuable method for acquiring information on both muscles and bones of aging populations.
OBJECTIVE: The aim of this study was to develop and externally validate opportunistic CT-based fracture prediction models by using images of vertebral bones and paravertebral muscles.
METHODS: The models were developed based on a retrospective longitudinal cohort study of 1214 patients with abdominal CT images between 2010 and 2019. The models were externally validated in 495 patients. The primary outcome of this study was defined as the predictive accuracy for identifying vertebral fracture events within a 5-year follow-up. The image models were developed using an attention convolutional neural network-recurrent neural network model from images of the vertebral bone and paravertebral muscles.
RESULTS: The mean ages of the patients in the development and validation sets were 73 years and 68 years, and 69.1% (839/1214) and 78.8% (390/495) of them were females, respectively. The areas under the receiver operator curve (AUROCs) for predicting vertebral fractures were superior in images of the vertebral bone and paravertebral muscles than those in the bone-only images in the external validation cohort (0.827, 95% CI 0.821-0.833 vs 0.815, 95% CI 0.806-0.824, respectively; P<.001). The AUROCs of these image models were higher than those of the fracture risk assessment models (0.810 for major osteoporotic risk, 0.780 for hip fracture risk). For the clinical model using age, sex, BMI, use of steroids, smoking, possible secondary osteoporosis, type 2 diabetes mellitus, HIV, hepatitis C, and renal failure, the AUROC value in the external validation cohort was 0.749 (95% CI 0.736-0.762), which was lower than that of the image model using vertebral bones and muscles (P<.001).
CONCLUSIONS: The model using the images of the vertebral bone and paravertebral muscle showed better performance than that using the images of the bone-only or clinical variables. Opportunistic CT screening may contribute to identifying patients with a high fracture risk in the future.

The need for intubation in methanol-poisoned patients, if not predicted in time, can lead to irreparable complications and even death. Artificial intelligence (AI) techniques like machine learning (ML) and deep learning (DL) greatly aid in accurately predicting intubation needs for methanol-poisoned patients. So, our study aims to assess Explainable Artificial Intelligence (XAI) for predicting intubation necessity in methanol-poisoned patients, comparing deep learning and machine learning models. This study analyzed a dataset of 897 patient records from Loghman Hakim Hospital in Tehran, Iran, encompassing cases of methanol poisoning, including those requiring intubation (202 cases) and those not requiring it (695 cases). Eight established ML (SVM, XGB, DT, RF) and DL (DNN, FNN, LSTM, CNN) models were used. Techniques such as tenfold cross-validation and hyperparameter tuning were applied to prevent overfitting. The study also focused on interpretability through SHAP and LIME methods. Model performance was evaluated based on accuracy, specificity, sensitivity, F1-score, and ROC curve metrics. Among DL models, LSTM showed superior performance in accuracy (94.0%), sensitivity (99.0%), specificity (94.0%), and F1-score (97.0%). CNN led in ROC with 78.0%. For ML models, RF excelled in accuracy (97.0%) and specificity (100%), followed by XGB with sensitivity (99.37%), F1-score (98.27%), and ROC (96.08%). Overall, RF and XGB outperformed other models, with accuracy (97.0%) and specificity (100%) for RF, and sensitivity (99.37%), F1-score (98.27%), and ROC (96.08%) for XGB. ML models surpassed DL models across all metrics, with accuracies from 93.0% to 97.0% for DL and 93.0% to 99.0% for ML. Sensitivities ranged from 98.0% to 99.37% for DL and 93.0% to 99.0% for ML. DL models achieved specificities from 78.0% to 94.0%, while ML models ranged from 93.0% to 100%. F1-scores for DL were between 93.0% and 97.0%, and for ML between 96.0% and 98.27%. DL models scored ROC between 68.0% and 78.0%, while ML models ranged from 84.0% to 96.08%. Key features for predicting intubation necessity include GCS at admission, ICU admission, age, longer folic acid therapy duration, elevated BUN and AST levels, VBG_HCO3 at initial record, and hemodialysis presence. This study as the showcases XAI\'s effectiveness in predicting intubation necessity in methanol-poisoned patients. ML models, particularly RF and XGB, outperform DL counterparts, underscoring their potential for clinical decision-making.

UNASSIGNED: Syndromic surveillance represents a potentially inexpensive supplement to test-based COVID-19 surveillance. By strengthening surveillance of COVID-19-like illness (CLI), targeted and rapid interventions can be facilitated that prevent COVID-19 outbreaks without primary reliance on testing.
UNASSIGNED: This study aims to assess the temporal relationship between confirmed SARS-CoV-2 infections and self-reported and health care provider-reported CLI in university and county settings, respectively.
UNASSIGNED: We collected aggregated COVID-19 testing and symptom reporting surveillance data from Cornell University (2020-2021) and Tompkins County Health Department (2020-2022). We used negative binomial and linear regression models to correlate confirmed COVID-19 case counts and positive test rates with CLI rate time series, lagged COVID-19 cases or rates, and day of the week as independent variables. Optimal lag periods were identified using Granger causality and likelihood ratio tests.
UNASSIGNED: In modeling undergraduate student cases, the CLI rate (P=.003) and rate of exposure to CLI (P<.001) were significantly correlated with the COVID-19 test positivity rate with no lag in the linear models. At the county level, the health care provider-reported CLI rate was significantly correlated with SARS-CoV-2 test positivity with a 3-day lag in both the linear (P<.001) and negative binomial model (P=.005).
UNASSIGNED: The real-time correlation between syndromic surveillance and COVID-19 cases on a university campus suggests symptom reporting is a viable alternative or supplement to COVID-19 surveillance testing. At the county level, syndromic surveillance is also a leading indicator of COVID-19 cases, enabling quick action to reduce transmission. Further research should investigate COVID-19 risk using syndromic surveillance in other settings, such as low-resource settings like low- and middle-income countries.