Machine-learning guided Venom Induced Dermonecrosis Analysis tooL: VIDAL.

Snakebite envenoming is a global public health issue that causes significant morbidity and mortality, particularly in low-income regions of the world. The clinical manifestations of envenomings vary depending on the snake's venom, with paralysis, haemorrhage, and necrosis being the most common and medically relevant effects. To assess the efficacy of antivenoms against dermonecrosis, a preclinical testing approach involves in vivo mouse models that mimic local tissue effects of cytotoxic snakebites in humans. However, current methods for assessing necrosis severity are time-consuming and susceptible to human error. To address this, we present the Venom Induced Dermonecrosis Analysis tooL (VIDAL), a machine-learning-guided image-based solution that can automatically identify dermonecrotic lesions in mice, adjust for lighting biases, scale the image, extract lesion area and discolouration, and calculate the severity of dermonecrosis. We also introduce a new unit, the dermonecrotic unit (DnU), to better capture the complexity of dermonecrosis severity. Our tool is comparable to the performance of state-of-the-art histopathological analysis, making it an accessible, accurate, and reproducible method for assessing dermonecrosis in mice. Given the urgent need to address the neglected tropical disease that is snakebite, high-throughput technologies such as VIDAL are crucial in developing and validating new and existing therapeutics for this debilitating disease.

Identification of clinical factors related to prediction of alcohol use disorder from electronic health records using feature selection methods.

BACKGROUND: High dimensionality in electronic health records (EHR) causes a significant computational problem for any systematic search for predictive, diagnostic, or prognostic patterns. Feature selection (FS) methods have been indicated to be effective in feature reduction as well as in identifying risk factors related to prediction of clinical disorders. This paper examines the prediction of patients with alcohol use disorder (AUD) using machine learning (ML) and attempts to identify risk factors related to the diagnosis of AUD. METHODS: A FS framework consisting of two operational levels, base selectors and ensemble selectors. The first level consists of five FS methods: three filter methods, one wrapper method, and one embedded method. Base selector outputs are aggregated to develop four ensemble FS methods. The outputs of FS method were then fed into three ML algorithms: support vector machine (SVM), K-nearest neighbor (KNN), and random forest (RF) to compare and identify the best feature subset for the prediction of AUD from EHRs. RESULTS: In terms of feature reduction, the embedded FS method could significantly reduce the number of features from 361 to 131. In terms of classification performance, RF based on 272 features selected by our proposed ensemble method (Union FS) with the highest accuracy in predicting patients with AUD, 96%, outperformed all other models in terms of AUROC, AUPRC, Precision, Recall, and F1-Score. Considering the limitations of embedded and wrapper methods, the best overall performance was achieved by our proposed Union Filter FS, which reduced the number of features to 223 and improved Precision, Recall, and F1-Score in RF from 0.77, 0.65, and 0.71 to 0.87, 0.81, and 0.84, respectively. Our findings indicate that, besides gender, age, and length of stay at the hospital, diagnosis related to digestive organs, bones, muscles and connective tissue, and the nervous systems are important clinical factors related to the prediction of patients with AUD. CONCLUSION: Our proposed FS method could improve the classification performance significantly. It could identify clinical factors related to prediction of AUD from EHRs, thereby effectively helping clinical staff to identify and treat AUD patients and improving medical knowledge of the AUD condition. Moreover, the diversity of features among female and male patients as well as gender disparity were investigated using FS methods and ML techniques.

Short-term atrial fibrillation detection using electrocardiograms: A comparison of machine learning approaches.

BACKGROUND: Atrial fibrillation (AF) is one of the most prevalent cardiac arrhythmias, which challenges the healthcare systems globally.Timely detection of AF can potentially reduce the mortality and morbidity rates as well as alleviate the economic burden caused by this.Digital solutions are shown to enhance the diagnosis of cardiac abnormalities. OBJECTIVES: By the latest advancements in the field of medical informatics and tele-health monitoring, huge amount of electro-physiological signals, such as electrocardiograms (ECG), can be easily collected.One of the most common ways for physicians/cardiologists to analyse these signals is through visual inspection.However, it is not always easy and in most cases cumbersome to analyse these big amounts of ECG data.Therefore, it is of great interest to develop models that are capable of analyzing these data and help physicians making better decisions.This paper proposes and compares well-known machine learning (ML) algorithms to diagnose short episodes of AF. This also paves the way for real-time detection of AF in clinical settings. METHODS: Different ML algorithms such as Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), Stacking Classifier (SC), Extreme Gradient Boosting (XGBoost), and Adaptive Boosting (AdaBoost) were applied to detect AF. These models were trained using extracted statistical features from ECG signals. RESULTS: The proposed ML models were trained on a dataset with 23 ECG records of length approximately 10 h each using leave one group out cross validation (LOGO-CV) technique and achieved the best sensitivity (Se), specificity (Sp), positive predictive value (PPV), false positive rate (FPR), and F1-score of 85.67%, 81.25%, 90.85%, 18.75% and 88.18%, respectively, to classify AF from normal sinus rhythms (NSR) in short ECG segments of 20 heartbeats.Additionally, the models were examined on three unseen datasets, namely the Long Term AF dataset, MIT-BIH Arrhythmia dataset, and MIT-BIH Normal Sinus Rhythm dataset, to assess their robustness and generalization. CONCLUSION: The obtained results show high performance and flexibility of some of the applied ML models compared to other well-known algorithms. In general, the empirical results confirm that ensemble methods, such as AdaBoost, generalized well and perform better than other approaches.

Quantifying the impact of addressing data challenges in prediction of length of stay.

BACKGROUND: Prediction of length of stay (LOS) at admission time can provide physicians and nurses insight into the illness severity of patients and aid them in avoiding adverse events and clinical deterioration. It also assists hospitals with more effectively managing their resources and manpower. METHODS: In this field of research, there are some important challenges, such as missing values and LOS data skewness. Moreover, various studies use a binary classification which puts a wide range of patients with different conditions into one category. To address these shortcomings, first multivariate imputation techniques are applied to fill incomplete records, then two proper resampling techniques, namely Borderline-SMOTE and SMOGN, are applied to address data skewness in the classification and regression domains, respectively. Finally, machine learning (ML) techniques including neural networks, extreme gradient boosting, random forest, support vector machine, and decision tree are implemented for both approaches to predict LOS of patients admitted to the Emergency Department of Odense University Hospital between June 2018 and April 2019. The ML models are developed based on data obtained from patients at admission time, including pulse rate, arterial blood oxygen saturation, respiratory rate, systolic blood pressure, triage category, arrival ICD-10 codes, age, and gender. RESULTS: The performance of predictive models before and after addressing missing values and data skewness is evaluated using four evaluation metrics namely receiver operating characteristic, area under the curve (AUC), R-squared score (R2), and normalized root mean square error (NRMSE). Results show that the performance of predictive models is improved on average by 15.75% for AUC, 32.19% for R2 score, and 11.32% for NRMSE after addressing the mentioned challenges. Moreover, our results indicate that there is a relationship between the missing values rate, data skewness, and illness severity of patients, so it is clinically essential to take incomplete records of patients into account and apply proper solutions for interpolation of missing values. CONCLUSION: We propose a new method comprised of three stages: missing values imputation, data skewness handling, and building predictive models based on classification and regression approaches. Our results indicated that addressing these challenges in a proper way enhanced the performance of models significantly, which led to a more valid prediction of LOS.

Machine learning techniques for mortality prediction in emergency departments: a systematic review.

OBJECTIVES: This systematic review aimed to assess the performance and clinical feasibility of machine learning (ML) algorithms in prediction of in-hospital mortality for medical patients using vital signs at emergency departments (EDs). DESIGN: A systematic review was performed. SETTING: The databases including Medline (PubMed), Scopus and Embase (Ovid) were searched between 2010 and 2021, to extract published articles in English, describing ML-based models utilising vital sign variables to predict in-hospital mortality for patients admitted at EDs. Critical appraisal and data extraction for systematic reviews of prediction modelling studies checklist was used for study planning and data extraction. The risk of bias for included papers was assessed using the prediction risk of bias assessment tool. PARTICIPANTS: Admitted patients to the ED. MAIN OUTCOME MEASURE: In-hospital mortality. RESULTS: Fifteen articles were included in the final review. We found that eight models including logistic regression, decision tree, K-nearest neighbours, support vector machine, gradient boosting, random forest, artificial neural networks and deep neural networks have been applied in this domain. Most studies failed to report essential main analysis steps such as data preprocessing and handling missing values. Fourteen included studies had a high risk of bias in the statistical analysis part, which could lead to poor performance in practice. Although the main aim of all studies was developing a predictive model for mortality, nine articles did not provide a time horizon for the prediction. CONCLUSION: This review provided an updated overview of the state-of-the-art and revealed research gaps; based on these, we provide eight recommendations for future studies to make the use of ML more feasible in practice. By following these recommendations, we expect to see more robust ML models applied in the future to help clinicians identify patient deterioration earlier.

Cross-Cultural Bayesian Network Analysis of Factors Affecting Residents' Concerns About the Spread of an Infectious Disease Caused by Tourism.

COVID-19 has had a severe impact globally, and the recovery can be characterized as a tug of war between fast economic recovery and firm control of further virus-spread. To be prepared for future pandemics, public health policy makers should put effort into fully understanding any complex psychological tensions that inherently arise between opposing human factors such as free enjoyment versus self-restriction. As the COVID-19 crisis is an unusual and complex problem, combinations of diverse factors such as health risk perception, knowledge, norms and beliefs, attitudes and behaviors are closely associated with individuals' intention to enjoy the experience economy but also their concerns that the experience economy will trigger further spread of the infectious diseases. Our aim is to try identifying what factors are associated with their concerns about the spread of the infectious disease caused by the local experience economy. Hence, we have chosen a "data-driven" explanatory approach, "Probabilistic Structural Equational Modeling," based on the principle of Bayesian networks to analyze data collected from the following four countries with indicated sample sizes: Denmark (1,005), Italy (1,005), China (1,013), and Japan (1,091). Our findings highlight the importance of understanding the contextual differences in relations between the target variable and factors such as personal value priority and knowledge. These factors affect the target variable differently depending on the local severity-level of the infections. Relations between pleasure-seeking via the experience economy and individuals' anxiety-level about an infectious hotspot seem to differ between East Asians and Europeans who are known to prioritize so-called interpersonal- and independent self-schemes, respectively. Our study also indicates the heterogeneity in the populations, i.e., these relations differ within the respective populations. Another finding shows that the Japanese population is particularly concerned about their local community potentially becoming an infectious hotspot and hence expecting others to comply with their particular social norms. Summarizing, the obtained insights imply the importance of considering both cultural- and individual contexts when policy makers are going to develop measures to address pandemic dilemmas such as maintaining public health awareness and accelerating the recovery of the local experience economy.

Deep Neural Network to Identify Patients with Alcohol Use Disorder.

This paper presents an application of deep neural networks (DNN) to identify patients with Alcohol Use Disorder based on historical electronic health records. Our methodology consists of four stages including data collection, preprocessing, predictive model development, and validation. Data are collected from two sources and labeled into three classes including Normal, Hazardous, and Harmful drinkers. Moreover, problems such as imbalanced classes, noise, and categorical variables were handled. A four-layer fully-connected feedforward DNN architecture was designed and developed to predict Normal, Hazardous, and Harmful drinkers. Results show that our proposed method could successfully classify about 96%, 82%, and 89% of Normal, Hazardous, and Harmful drinkers, respectively, which is better than classical machine learning approaches.

Data Vizualization Dashboards in Robotic Rehabilitation.

Robotic rehabilitation can offer effective solutions, facilitating physiotherapist work, and helping patients regain their strength. Visualizing results of rehabilitative training could give a better insight into the factors that contribute to progress and measure the exact progress by every session. This paper aims to present a set of prototype dashboards to analyze and visualize data from robotic rehabilitation in order to help the patients measure their exerted force progress throughout the training period. The created visualization dashboards which proved helpful and essential to present achieved measurements, the progress of the patient, and the maximum force in a timeline presentation. The proposed prototypes could give a personalized overview to each patient, fed with the corresponding datasets.

Personalized Predictive Models for Identifying Clinical Deterioration Using LSTM in Emergency Departments.

Early detection of deterioration at hospitals could be beneficial in terms of reducing mortality and morbidity rates and costs. In this paper, we present a model based on Long Short-Term Memory (LSTM) neural network used in deep learning to predict the illness severity of patients in advance. Hence, by predicting health severity, this model can be used to identify deteriorating patients. Our proposed model utilizes continuous monitored vital signs, including heart rate, respiratory rate, oxygen saturation, and blood pressure automatically collected from patients during hospitalization. In this study, a short-time prediction using a sliding window approach is applied. The performance of the proposed model was compared with the Multi-Layer Perceptron (MLP) neural network, a feedforward class of neural network, based on R2 score and Root Mean Square Error (RMSE) metrics. The results showed that the LSTM has a better performance and could predict the illness severity of patients more accurately.

Google Trends and Seasonal Effects in Infodemiology: A Use Case About Obesity.

Google Trends is a free online tool that provides information on the interest on a topic measured as Google searches in the big data era. In this work, we present methods for detection of trends and seasonal effects in online interest for health topics based on Google Trends data. We present data for the term obesity worldwide and in a convenience sample of countries (Denmark, United Kingdom, USA, Japan) over the last five years. Our analysis shows that, despite obesity being one of the global health challenges, there is a decreasing trend in online interest in the topic. We also observed seasonal effects, with less interest for the topic during December and the summer months. Identifying trends and seasonal patterns in online interest can support resource allocation and planning and allows one to evaluate the effectiveness of global and local outreach efforts on public health.

Predicting Dropouts From an Electronic Health Platform for Lifestyle Interventions: Analysis of Methods and Predictors.

BACKGROUND: The increasing prevalence and economic impact of chronic diseases challenge health care systems globally. Digital solutions can potentially improve efficiency and quality of care, but these initiatives struggle with nonusage attrition. Machine learning methods have been proven to predict dropouts in other settings but lack implementation in health care. OBJECTIVE: This study aimed to gain insight into the causes of attrition for patients in an electronic health (eHealth) intervention for chronic lifestyle diseases and evaluate if attrition can be predicted and consequently prevented. We aimed to build predictive models that can identify patients in a digital lifestyle intervention at high risk of dropout by analyzing several predictor variables applied in different models and to further assess the possibilities and impact of implementing such models into an eHealth platform. METHODS: Data from 2684 patients using an eHealth platform were iteratively analyzed using logistic regression, decision trees, and random forest models. The dataset was split into a 79.99% (2147/2684) training and cross-validation set and a 20.0% (537/2684) holdout test set. Trends in activity patterns were analyzed to assess engagement over time. Development and implementation were performed iteratively with health coaches. RESULTS: Patients in the test dataset were classified as dropouts with an 89% precision using a random forest model and 11 predictor variables. The most significant predictors were the provider of the intervention, 2 weeks inactivity, and the number of advices received from the health coach. Engagement in the platform dropped significantly leading up to the time of dropout. CONCLUSIONS: Dropouts from eHealth lifestyle interventions can be predicted using various data mining methods. This can support health coaches in preventing attrition by receiving proactive warnings. The best performing predictive model was found to be the random forest.

A Predictive Model for Acute Admission in Aged Population.

Acute hospital admission among the elderly population is very common and have a high impact on the health services and the community, as well as on the individuals. Several studies have focused on the possible risk factors, however, predicting who is at risk for acute hospitalization associated with disease and symptoms is still an open research question. In this study, we investigate the use of machine learning algorithms for predicting acute admission in older people based on admission data from individual citizens 70 years and older who were hospitalized in the acute medical unit of Svendborg Hospital in Denmark.

An Automated System for Skeletal Maturity Assessment by Extreme Learning Machines.

Assessing skeletal age is a subjective and tedious examination process. Hence, automated assessment methods have been developed to replace manual evaluation in medical applications. In this study, a new fully automated method based on content-based image retrieval and using extreme learning machines (ELM) is designed and adapted to assess skeletal maturity. The main novelty of this approach is it overcomes the segmentation problem as suffered by existing systems. The estimation results of ELM models are compared with those of genetic programming (GP) and artificial neural networks (ANNs) models. The experimental results signify improvement in assessment accuracy over GP and ANN, while generalization capability is possible with the ELM approach. Moreover, the results are indicated that the ELM model developed can be used confidently in further work on formulating novel models of skeletal age assessment strategies. According to the experimental results, the new presented method has the capacity to learn many hundreds of times faster than traditional learning methods and it has sufficient overall performance in many aspects. It has conclusively been found that applying ELM is particularly promising as an alternative method for evaluating skeletal age.

The applicability of Greulich and Pyle atlas to assess skeletal age for four ethnic groups.

BACKGROUND: Recently, determination of skeletal age, defined as the assessment of bone age, has rapidly become an important task between forensic experts and radiologists. The Greulich-Pyle (GP) atlas is one of the most frequently used methods for the assessment of skeletal age around the world. After presentation of the GP approach for the estimation of the bone age, much research has been conducted to examine the usability of this method in various geographic or ethnic categories. This study investigates on a small-scale and compares the reliability of the GP atlas for assessment of the bone age for four ethnic groups - Asian, African/American, Caucasian and Hispanic - for a different range of ages. MATERIALS AND METHODS: Plain radiographs of 184 left hands and wrists for males from the healthy sample between 1 to 18 years of age for four ethnic groups were taken. The skeletal age (SA) was estimated by a radiologist using the GP atlas. The blind method was utilized. The mean (SA) results were compared with mean chronological ages (CA) for the separate ethnic groups. SPSS was used to conduct the analysis and the paired t-test was applied to show the difference between the mean CA and mean SA achieved from the GP atlas. RESULTS: The results from the GP atlas were compared to the CA of the samples. In Asian subjects the mean difference was 0.873 years. The GP atlas showed delayed bone age at 2-7 ages (from 0.2 to 2.3 year) and then advanced bone age for age 8. In the African/American subjects the difference between CA and SA was statistically significant (P-value = 0.048). The mean difference in the Caucasian and Hispanic subjects reflects no considerable distinction with a standard deviation (SD) of 0.3088 and 0.3766, respectively, (P-value >0.05 for both groups). CONCLUSION: According to the present study, it is concluded that although the GP atlas is reliable for Caucasian and Hispanic ethnic groups it is not applicable for other ethnic groups for different ranges of age, especially in the sample of the male African/American group from 8 years to 15 years and Asian during childhood. Although it is not clear whether the other references are more useful than this standard, we believe that some enhancement is vital for the GP atlas to obtain more consistent results.

Automated bone age assessment: motivation, taxonomies, and challenges.

Bone age assessment (BAA) of unknown people is one of the most important topics in clinical procedure for evaluation of biological maturity of children. BAA is performed usually by comparing an X-ray of left hand wrist with an atlas of known sample bones. Recently, BAA has gained remarkable ground from academia and medicine. Manual methods of BAA are time-consuming and prone to observer variability. This is a motivation for developing automated methods of BAA. However, there is considerable research on the automated assessment, much of which are still in the experimental stage. This survey provides taxonomy of automated BAA approaches and discusses the challenges. Finally, we present suggestions for future research.