Search

Background: Malnutrition is associated with increased morbidity, mortality, and healthcare costs. Early detection is important for timely intervention. This paper assesses the ability of a machine learning screening tool (MUST‐Plus) implemented in registered dietitian (RD) workflow to identify malnourished patients early in the hospital stay and to improve the diagnosis and documentation rate of malnutrition. Methods: This retrospective cohort study was conducted in a large, urban health system in New York City comprising six hospitals serving a diverse patient population. The study included all patients aged ≥ 18 years, who were not admitted for COVID‐19 and had a length of stay of ≤ 30 days. Results: Of the 7736 hospitalisations that met the inclusion criteria, 1947 (25.2%) were identified as being malnourished by MUST‐Plus‐assisted RD evaluations. The lag between admission and diagnosis improved with MUST‐Plus implementation. The usability of the tool output by RDs exceeded 90%, showing good acceptance by users. When compared pre‐/post‐implementation, the rate of both diagnoses and documentation of malnutrition showed improvement. Conclusion: MUST‐Plus, a machine learning‐based screening tool, shows great promise as a malnutrition screening tool for hospitalised patients when used in conjunction with adequate RD staffing and training about the tool. It performed well across multiple measures and settings. Other health systems can use their electronic health record data to develop, test and implement similar machine learning‐based processes to improve malnutrition screening and facilitate timely intervention. Key points/Highlights: Malnutrition is prevalent among hospitalised patients and frequently goes unrecognised, with the potential for severe sequelae. Accurate diagnosis, documentation and treatment of malnutrition have the potential of having a positive impact on morbidity rate, mortality rate, length of inpatient stay, readmission rate and hospital revenue. The tool's successful application highlights its potential to optimise malnutrition screening in healthcare systems, offering potential benefits for patient outcomes and hospital finances. [ABSTRACT FROM AUTHOR]

Introduction: Data mining in healthcare is a nascent arena of research in healthcare. Heterogeneity of Diabetes Mellitus in terms of clinical presentation calls for newer methods of research to study potential risk factors. Aim: The paper aims to use clustering techniques to identify the relationship between the four variables, namely the pre-prandial and postprandial sugar level, age and sex. Methods: The data was taken from a diagnostic laboratory in Wagholi, Pune. We conducted K-mean algorithm, EM algorithm, model-based clustering and t-mixture model. Results: It is evidenced that the data was best fitted to the t-mixture model. Our 50% samples were people with diabetes, 17% had prediabetes. Trivial correlation existed between age and sugar level. Males and females were equally at risk of having diabetes. Data presented concludes that age and sex have no effect on the risk of having diabetes. Data mining can be used to deduce meaningful clusters to drive plan-based interventions in the population. Conclusion: Methods of data mining can be used to deduce meaningful clusters in a heterogeneous dataset thus providing policymakers and healthcare researchers with novel information that will potentially contribute in formulating evidence-based policies. [ABSTRACT FROM AUTHOR]

Current suicide risk assessments for predicting suicide attempts are time consuming, of low predictive value and have inadequate reliability. This paper aims to develop a predictive model for suicide attempts among patients with depression using machine learning algorithms as well as presents a comparative study on single predictive models with ensemble predictive models for differentiating depressed patients with suicide attempts from non-suicide attempters. We applied and trained eight different machine learning algorithms using a dataset that consists of 75 patients diagnosed with a depressive disorder. A recursive feature elimination was used to reduce the features via three-fold cross validation. An ensemble predictive models outperformed the single predictive models. Voting and bagging revealed the highest accuracy of 92% compared to other machine learning algorithms. Our findings indicate that history of suicide attempt, religion, race, suicide ideation and severity of clinical depression are useful factors for prediction of suicide attempts. [ABSTRACT FROM AUTHOR]

Background and Aim: Gastric cancer (GC) is the common leading cause of cancer-related death worldwide. Immune-related genes (IRGs) may potentially predict lymph node metastasis (LNM). We aimed to develop a preoperative model to predict LNM based on these IRGs. Methods: In this paper, we compared and evaluated three machine learning models to predict LNM based on publicly available gene expression data from TCGA-STAD. The Pearson correlation coefficient (PCC) method was utilized to feature selection according to its relationships with LN status. The performance of the model was assessed using the area under the curve (AUC) and F1 score. Results: The Naive Bayesian model showed better performance and was constructed based on 26 selected gene features, with AUCs of 0.741 in the training set and 0.688 in the test set. The F1 score in the training set and test set was 0.652 and 0.597, respectively. Furthermore, Naive Bayesian model based on 26 IRGs is the first diagnostic tool for the identification of LNM in advanced GC. Conclusion: These results indicate that our new methods have the value of auxiliary diagnosis with promising clinical potential. [ABSTRACT FROM AUTHOR]

Objectives.To evaluate the positive predictive value of machine learning algorithms for early assessment of adverse birth risk among pregnant women as a means of improving the allocation of social services. Methods. We used administrative data for 6457 women collected by the Illinois Department of Human Services from July 2014 to May 2015 to develop a machine learning model for adverse birth prediction and improve upon the existing paper-based risk assessment. We compared different models and determined the strongest predictors of adverse birth outcomes using positive predictive value as the metric for selection. Results. Machine learning algorithms performed similarly, outperforming the current paper-based risk assessment by up to 36%; a refined paper-based assessment outperformed the current assessment by up to 22%. We estimate that these improvements will allow 100 to 170 additional high-risk pregnant women screened for program eligibility each year to receive services that would have otherwise been unobtainable. Conclusions. Our analysis exhibits the potential for machine learning to move government agencies toward a more data-informed approach to evaluating risk and providing social services. Overall, such efforts will improve the efficiency of allocating resource-intensive interventions. [ABSTRACT FROM AUTHOR]

Background: Tier 1 exposure tools recommended for use under REACH are designed to easily identify situations that may pose a risk to health through conservative exposure predictions. However, no comprehensive evaluation of the performance of the lower tier tools has previously been carried out. The ETEAM project aimed to evaluate several lower tier exposure tools (ECETOC TRA, MEASE, and EMKG-EXPO-TOOL) as well as one higher tier tool (STOFFENMANAGER®). This paper describes the results of the external validation of tool estimates using measurement data. Methods: Measurement data were collected from a range of providers, both in Europe and United States, together with contextual information. Individual measurement and aggregated measurement data were obtained. The contextual information was coded into the tools to obtain exposure estimates. Results were expressed as percentage of measurements exceeding the tool estimates and presented by exposure category (non-volatile liquid, volatile liquid, metal abrasion, metal processing, and powder handling). We also explored tool performance for different process activities as well as different scenario conditions and exposure levels. Results: In total, results from nearly 4000 measurements were obtained, with the majority for the use of volatile liquids and powder handling. The comparisons of measurement results with tool estimates suggest that the tools are generally conservative. However, the tools were more conservative when estimating exposure from powder handling compared to volatile liquids and other exposure categories. In addition, results suggested that tool performance varies between process activities and scenario conditions. For example, tools were less conservative when estimating exposure during activities involving tabletting, compression, extrusion, pelletisation, granulation (common process activity PROC14) and transfer of substance or mixture (charging and discharging) at nondedicated facilities (PROC8a; powder handling only). With the exception of STOFFENMANAGER® (for estimating exposure during powder handling), the tools were less conservative for scenarios with lower estimated exposure levels. Conclusions: This is the most comprehensive evaluation of the performance of REACH exposure tools carried out to date. The results show that, although generally conservative, the tools may not always achieve the performance specified in the REACH guidance, i.e. using the 75th or 90th percentile of the exposure distribution for the risk characterisation. Ongoing development, adjustment, and recalibration of the tools with new measurement data are essential to ensure adequate characterisation and control of worker exposure to hazardous substances. [ABSTRACT FROM AUTHOR]

This paper uses deep (machine) learning techniques to develop and test how motor behaviors, derived from location and movement sensor tracking data, may be associated with falls, delirium, and urinary tract infections (UTIs) in long-term care (LTC) residents. Longitudinal observational study. A total of 23 LTC residents (81,323 observations) with cognitive impairment or dementia in 2 northeast Department of Veterans Affairs LTC facilities. More than 18 months of continuous (24/7) monitoring of motor behavior and activity levels used objective radiofrequency identification sensor data to track and record movement data. Occurrence of acute events was recorded each week. Unsupervised deep learning models were used to classify motor behaviors into 5 clusters; supervised decision tree algorithms used these clusters to predict acute health events (falls, delirium, and UTIs) the week before the week of the event. Motor behaviors were classified into 5 categories (Silhouette score = 0.67), and these were significantly different from each other. Motor behavior classifications were sensitive and specific to falls, delirium, and UTI predictions 1 week before the week of the event (sensitivity range = 0.88–0.91; specificity range = 0.71–0.88). Intraindividual changes in motor behaviors predict some of the most common and detrimental acute events in LTC populations. Study findings suggest real-time locating system sensor data and machine learning techniques may be used in clinical applications to effectively prevent falls and lead to the earlier recognition of risk for delirium and UTIs in this vulnerable population. [ABSTRACT FROM AUTHOR]