Atrial fibrillation (AF) is a major cause of hospitalization and death in the United States. Moreover, as the average age of individuals increases around the world, early detection and diagnosis of ...AF become even more pressing. In this paper, we introduce a novel deep learning architecture for the detection of normal sinus rhythm, AF, other abnormal rhythms, and noise.
We have demonstrated through a systematic approach many hyperparameters, input sets, and optimization methods that yielded influence in both training time and performance accuracy. We have focused on these properties to identify an optimal 13-layer convolutional neural network (CNN) model which was trained on 8528 short single-lead ECG recordings and evaluated on a test dataset of 3658 recordings.
The proposed CNN architecture achieved a state-of-the-art performance in identifying normal, AF and other rhythms with an average F
-score of 0.83.
We have presented a robust deep learning-based architecture that can identify abnormal cardiac rhythms using short single-lead ECG recordings. The proposed architecture is computationally fast and can also be used in real-time cardiac arrhythmia detection applications.
Parkinson's Disease (PD) is a clinically diagnosed neurodegenerative disorder that affects both motor and non-motor neural circuits. Speech deterioration (hypokinetic dysarthria) is a common symptom, ...which often presents early in the disease course. Machine learning can help movement disorders specialists improve their diagnostic accuracy using non-invasive and inexpensive voice recordings.
We used "Parkinson Dataset with Replicated Acoustic Features Data Set" from the UCI-Machine Learning repository. The dataset included 44 speech-test based acoustic features from patients with PD and controls. We analyzed the data using various machine learning algorithms including Light and Extreme Gradient Boosting, Random Forest, Support Vector Machines, K-nearest neighborhood, Least Absolute Shrinkage and Selection Operator Regression, as well as logistic regression. We also implemented a variable importance analysis to identify important variables classifying patients with PD.
The cohort included a total of 80 subjects: 40 patients with PD (55% men) and 40 controls (67.5% men). Disease duration was 5 years or less for all subjects, with a mean Unified Parkinson's Disease Rating Scale (UPDRS) score of 19.6 (SD 8.1), and none were taking PD medication. The mean age for PD subjects and controls was 69.6 (SD 7.8) and 66.4 (SD 8.4), respectively. Our best-performing model used Light Gradient Boosting to provide an AUC of 0.951 with 95% confidence interval 0.946-0.955 in 4-fold cross validation using only seven acoustic features.
Machine learning can accurately detect Parkinson's disease using an inexpensive and non-invasive voice recording. Light Gradient Boosting outperformed other machine learning algorithms. Such approaches could be used to inexpensively screen large patient populations for Parkinson's disease.
Combatting the current global epidemic of obesity requires that people have a realistic understanding of what a healthy body size looks like. This is a particular issue in different population ...sub-groups, where there may be increased susceptibility to obesity-related diseases. Prior research has been unable to systematically assess body size judgement due to a lack of attention to gender and race; our study aimed to identify the contribution of these factors. Using a data-driven multi-variate decision tree approach, we varied the gender and race of image stimuli used, and included the same diversity among participants. We adopted a condition-rich categorization visual task and presented participants with 120 unique body images. We show that gender and weight categories of the stimuli affect accuracy of body size perception. The decision pattern reveals biases for male bodies, in which participants showed an increasing number of errors from leaner to bigger bodies, particularly under-estimation errors. Participants consistently mis-categorized overweight male bodies as normal weight, while accurately categorizing normal weight. Overweight male bodies are now perceived as part of an expanded normal: the perceptual boundary of normal weight has become wider than the recognized BMI category. For female bodies, another intriguing pattern emerged, in which participants consistently mis-categorized underweight bodies as normal, whilst still accurately categorizing normal female bodies. Underweight female bodies are now in an expanded normal, in opposite direction to that of males. Furthermore, an impact of race type and gender of participants was also observed. Our results demonstrate that perceptual weight categorization is multi-dimensional, such that categorization decisions can be driven by ultiple factors.
The importance of social components of health has been emphasized both in epidemiology and public health. This paper highlights the significant impact of social components on health outcomes in a ...novel way. Introducing the concept of sociomarkers, which are measurable indicators of social conditions in which a patient is embedded, we employed a machine learning approach that uses both biomarkers and sociomarkers to identify asthma patients at risk of a hospital revisit after an initial visit with an accuracy of 66%. The analysis has been performed over an integrated dataset consisting of individual-level patient information such as gender, race, insurance type, and age, along with ZIP code-level sociomarkers such as poverty level, blight prevalence, and housing quality. Using this uniquely integrated database, we then compare the traditional biomarker-based risk model and the sociomarker-based risk model. A biomarker-based predictive model yields an accuracy of 65% and the sociomarker-based model predicts with an accuracy of 61%. Without knowing specific symptom-related features, the sociomarker-based model can correctly predict two out of three patients at risk. We systematically show that sociomarkers play an important role in predicting health outcomes at the individual level in pediatric asthma cases. Additionally, by merging multiple data sources with detailed neighborhood-level data, we directly measure the importance of residential conditions for predicting individual health outcomes.
Autonomic nervous system involvement precedes the motor features of Parkinson's disease (PD). Our goal was to develop a proof-of-concept model for identifying subjects at high risk of developing PD ...by analysis of cardiac electrical activity. We used standard 10-s electrocardiogram (ECG) recordings of 60 subjects from the Honolulu Asia Aging Study including 10 with prevalent PD, 25 with prodromal PD, and 25 controls who never developed PD. Various methods were implemented to extract features from ECGs including simple heart rate variability (HRV) metrics, commonly used signal processing methods, and a Probabilistic Symbolic Pattern Recognition (PSPR) method. Extracted features were analyzed via stepwise logistic regression to distinguish between prodromal cases and controls. Stepwise logistic regression selected four features from PSPR as predictors of PD. The final regression model built on the entire dataset provided an area under receiver operating characteristics curve (AUC) with 95% confidence interval of 0.90 0.80, 0.99. The five-fold cross-validation process produced an average AUC of 0.835 0.831, 0.839. We conclude that cardiac electrical activity provides important information about the likelihood of future PD not captured by classical HRV metrics. Machine learning applied to ECGs may help identify subjects at high risk of having prodromal PD.
Little is known about electrocardiogram (ECG) markers of Parkinson's disease (PD) during the prodromal stage. The aim of the study was to build a generalizable ECG-based fully automatic artificial ...intelligence (AI) model to predict PD risk during the prodromal stage, up to 5 years before disease diagnosis. This case-control study included samples from Loyola University Chicago (LUC) and University of Tennessee-Methodist Le Bonheur Healthcare (MLH). Cases and controls were matched according to specific characteristics (date, age, sex and race). Clinical data were available from May, 2014 onward at LUC and from January, 2015 onward at MLH, while the ECG data were available as early as 1990 in both institutes. PD was denoted by at least two primary diagnostic codes (ICD9 332.0; ICD10 G20) at least 30 days apart. PD incidence date was defined as the earliest of first PD diagnostic code or PD-related medication prescription. ECGs obtained at least 6 months before PD incidence date were modeled to predict a subsequent diagnosis of PD within three time windows: 6 months-1 year, 6 months-3 years, and 6 months-5 years. We applied a novel deep neural network using standard 10-s 12-lead ECGs to predict PD risk at the prodromal phase. This model was compared to multiple feature engineering-based models. Subgroup analyses for sex, race and age were also performed. Our primary prediction model was a one-dimensional convolutional neural network (1D-CNN) that was built using 131 cases and 1058 controls from MLH, and externally validated on 29 cases and 165 controls from LUC. The model was trained on 90% of the MLH data, internally validated on the remaining 10% and externally validated on LUC data. The best performing model resulted in an external validation AUC of 0.67 when predicting future PD at any time between 6 months and 5 years after the ECG. Accuracy increased when restricted to ECGs obtained within 6 months to 3 years before PD diagnosis (AUC 0.69) and was highest when predicting future PD within 6 months to 1 year (AUC 0.74). The 1D-CNN model based on raw ECG data outperformed multiple models built using more standard ECG feature engineering approaches. These results demonstrate that a predictive model developed in one cohort using only raw 10-s ECGs can effectively classify individuals with prodromal PD in an independent cohort, particularly closer to disease diagnosis. Standard ECGs may help identify individuals with prodromal PD for cost-effective population-level early detection and inclusion in disease-modifying therapeutic trials.
Pneumonia is the leading cause of infectious related death costing 12 billion dollars annually in the United States alone. Despite improvements in clinical care, total mortality remains around 4%, ...with inpatient mortality reaching 5-10%. For unknown reasons, mortality risk remains high even after hospital discharge and there is a need to identify those patients most at risk. Also of importance, clinical symptoms alone do not distinguish viral from bacterial infection which may delay appropriate treatment and may contribute to short-term and long-term mortality. Biomarkers have the potential to provide point of care diagnosis, identify high-risk patients, and increase our understanding of the biology of disease. However, there have been mixed results on the diagnostic performance of many of the analytes tested to date. Urine represents a largely untapped source for biomarker discovery and is highly accessible. To test this hypothesis, we collected urine from hospitalized patients with community-acquired pneumonia (CAP) and performed a comprehensive screen for urinary tract microbiota signatures, metabolite, and cytokine profiles. CAP patients were diagnosed with influenza or bacterial (Streptococcus pneumoniae and Staphylococcus aureus) etiologies and compared with healthy volunteers. Microbiome signatures showed marked shifts in taxonomic levels in patients with bacterial etiology versus influenza and CAP versus normal. Predictive modeling of 291 microbial and metabolite values achieved a + 90% accuracy with LASSO in predicting specific pneumonia etiology. This study demonstrates that urine from patients hospitalized with pneumonia may serve as a reliable and accessible sample to evaluate biomarkers that may diagnose etiology and predict clinical outcomes.
Scientific evidence confirm that significant racial disparities exist in healthcare, including surgery outcomes. However, the causal pathway underlying disparities at preoperative physical condition ...of children is not well-understood.
This research aims to uncover the role of socioeconomic and environmental factors in racial disparities at the preoperative physical condition of children through multidimensional integration of several data sources at the patient and population level.
After the data integration process an unsupervised k-means algorithm on neighborhood quality metrics was developed to split 29 zip-codes from Memphis, TN into good and poor-quality neighborhoods.
An unadjusted comparison of African Americans and white children showed that the prevalence of poor preoperative condition is significantly higher among African Americans compared to whites. No statistically significant difference in surgery outcome was present when adjusted by surgical severity and neighborhood quality.
The socioenvironmental factors affect the preoperative clinical condition of children and their surgical outcomes.