Enrichment of a Data Lake to Support Population Health Outcomes Studies Using Social Determinants Linked EHR Data.

The integration of electronic health records (EHRs) with social determinants of health (SDoH) is crucial for population health outcome research, but it requires the collection of identifiable information and poses security risks. This study presents a framework for facilitating de-identified clinical data with privacy-preserved geocoded linked SDoH data in a Data Lake. A reidentification risk detection algorithm was also developed to evaluate the transmission risk of the data. The utility of this framework was demonstrated through one population health outcomes research analyzing the correlation between socioeconomic status and the risk of having chronic conditions. The results of this study inform the development of evidence-based interventions and support the use of this framework in understanding the complex relationships between SDoH and health outcomes. This framework reduces computational and administrative workload and security risks for researchers and preserves data privacy and enables rapid and reliable research on SDoH-connected clinical data for research institutes.

Quantification of Urbanization Using Night-Time Light Intensity in Relation to Women's Overnutrition in Bangladesh.

Urbanization is accelerating in developing countries, which are simultaneously experiencing a rise in the prevalence of overnutrition (i.e., overweight and obesity), specifically among women. Since urbanization is a dynamic process, a continuous measure may better represent it when examining its association with overnutrition. However, most previous research has used a rural-urban dichotomy-based urbanization measure. This study utilized satellite-based night-time light intensity (NTLI) data to measure urbanization and evaluate its association with body weight in reproductive-aged (15-49) women in Bangladesh. Multilevel models estimated the association between residential area NTLI and women's body mass index (BMI) or overnutrition status using data from the latest Bangladesh Demographic and Health Survey (BDHS 2017-18). Higher area-level NTLI was associated with a higher BMI and increased odds of being overweight and obese in women. Living in areas with moderate NTL intensities was not linked with women's BMI measures, whereas living in areas with high NTL intensities was associated with a higher BMI or higher odds of being overweight and obese. The predictive nature of NTLI suggests that it could be used to study the relationship between urbanization and overnutrition prevalence in Bangladesh, though more longitudinal research is needed. This research emphasizes the necessity for preventive efforts to offset the expected public health implications of urbanization.

A Privacy-Preserved Transfer Learning Concept to Predict Diabetic Kidney Disease at Out-of-Network Siloed Sites Using an In-Network Federated Model on Real-World Data.

Successful implementation of data-driven artificial intelligence (AI) applications requires access to large datasets. Healthcare institutions can establish coordinated data-sharing networks to address the complexity of large clinical data accessibility for scientific advancements. However, persisting challenges from controlled access, safe data transferring, license restrictions from regulatory and legal concerns discourage data sharing among the in-network hospitals. In contrast, out-of-network healthcare institutions are deprived of access to any big EHR database; hence, limiting their research scope. The main objective of this study is to design a privacy-preserved transfer learning architecture that can utilize the knowledge from a federated model developed from in-network hospital-site EHR data for predicting diabetic kidney cases at out-of-network siloed hospital sites. In all our experiments, transfer learning showed improved performance compared to models trained with out-of-network site datasets. Thus, we demonstrate the proof-of-concept of transferring knowledge from established networks to aid data-driven AI discoveries at siloed sites.

ECG and SpO2 Signal-Based Real-Time Sleep Apnea Detection Using Feed-Forward Artificial Neural Network.

Sleep apnea (SA) is a common sleep disorder characterized by respiratory disturbance during sleep. Polysomnography (PSG) is the gold standard for apnea diagnosis, but it is time-consuming, expensive, and requires manual scoring. As an alternative to PSG, we investigated a real-time SA detection system using oxygen saturation level (SpO2) and electrocardiogram (ECG) signals individually as well as a combination of both. A series of R-R intervals were derived from the raw ECG data and a feed-forward deep artificial neural network is employed for the detection of SA. Three different models were built using 1-minute-long sequences of SpO2 and R-R interval signals. The 10-fold cross-validation result showed that the SpO2-based model performed better than the ECG-based model with an accuracy of 90.78 ± 10.12% and 80.04 ± 7.7%, respectively. Once combined, these two signals complemented each other and resulted in a better model with an accuracy of 91.83 ± 1.51%.

Clinicians' Perspectives in Using Patient-Generated Health Data to Improve Ischemic Heart Disease Management.

Patients suffering from ischemic heart disease (IHD) should be monitored closely after being discharged. With recent advances in digital health tools, collecting, using, and sharing patient-generated health data (PGHD) has become more achievable. PGHD can complement the existing clinical data and provide a comprehensive picture of the patient's health status. Despite the potential value of PGHD in healthcare, its implementation currently remains limited due to the clinicians' concern with the reliability and accuracy of the gathered data to support decision-making and concerns regarding the added workload that PGHD might cause to clinical workflow. The main objective of the study was to investigate the clinicians' perspectives towards the use of PGHD for IHD management, focusing on data sharing, interpretation, and efficiency in decision-making. The study consists of semi-structured interviews with seven clinicians. Study results identified four main themes: data generation, data integration, data presentation, data interpretation and utilization in clinical decision-making.

Investigation of the Utility of Features in a Clinical De-identification Model: A Demonstration Using EHR Pathology Reports for Advanced NSCLC Patients.

BACKGROUND: Electronic health record (EHR) systems contain a large volume of texts, including visit notes, discharge summaries, and various reports. To protect the confidentiality of patients, these records often need to be fully de-identified before circulating for secondary use. Machine learning (ML) based named entity recognition (NER) model has emerged as a popular technique of automatic de-identification. OBJECTIVE: The performance of a machine learning model highly depends on the selection of appropriate features. The objective of this study was to investigate the usability of multiple features in building a conditional random field (CRF) based clinical de-identification NER model. METHODS: Using open-source natural language processing (NLP) toolkits, we annotated protected health information (PHI) in 1,500 pathology reports and built supervised NER models using multiple features and their combinations. We further investigated the dependency of a model's performance on the size of training data. RESULTS: Among the 10 feature extractors explored in this study, n-gram, prefix-suffix, word embedding, and word shape performed the best. A model using combination of these four feature sets yielded precision, recall, and F1-score for each PHI as follows: NAME (0.80; 0.79; 0.80), LOCATION (0.85; 0.83; 0.84), DATE (0.86; 0.79; 0.82), HOSPITAL (0.96; 0.93; 0.95), ID (0.99; 0.82; 0.90), and INITIALS (0.97; 0.49; 0.65). We also found that the model's performance becomes saturated when the training data size is beyond 200. CONCLUSION: Manual de-identification of large-scale data is an impractical procedure since it is time-consuming and subject to human errors. Analysis of the NER model's performance in this study sheds light on a semi-automatic clinical de-identification pipeline for enterprise-wide data warehousing.

A Smartphone-Based Decision Support Tool for Predicting Patients at Risk of Chemotherapy-Induced Nausea and Vomiting: Retrospective Study on App Development Using Decision Tree Induction.

BACKGROUND: Chemotherapy-induced nausea and vomiting (CINV) are the two most frightful and unpleasant side effects of chemotherapy. CINV is accountable for poor treatment outcomes, treatment failure, or even death. It can affect patients' overall quality of life, leading to many social, economic, and clinical consequences. OBJECTIVE: This study compared the performances of different data mining models for predicting the risk of CINV among the patients and developed a smartphone app for clinical decision support to recommend the risk of CINV at the point of care. METHODS: Data were collected by retrospective record review from the electronic medical records used at the University of Missouri Ellis Fischel Cancer Center. Patients who received chemotherapy and standard antiemetics at the oncology outpatient service from June 1, 2010, to July 31, 2012, were included in the study. There were six independent data sets of patients based on emetogenicity (low, moderate, and high) and two phases of CINV (acute and delayed). A total of 14 risk factors of CINV were chosen for data mining. For our study, we used five popular data mining algorithms: (1) naive Bayes algorithm, (2) logistic regression classifier, (3) neural network, (4) support vector machine (using sequential minimal optimization), and (5) decision tree. Performance measures, such as accuracy, sensitivity, and specificity with 10-fold cross-validation, were used for model comparisons. A smartphone app called CINV Risk Prediction Application was developed using the ResearchKit in iOS utilizing the decision tree algorithm, which conforms to the criteria of explainable, usable, and actionable artificial intelligence. The app was created using both the bulk questionnaire approach and the adaptive approach. RESULTS: The decision tree performed well in both phases of high emetogenic chemotherapies, with a significant margin compared to the other algorithms. The accuracy measure for the six patient groups ranged from 79.3% to 94.8%. The app was developed using the results from the decision tree because of its consistent performance and simple, explainable nature. The bulk questionnaire approach asks 14 questions in the smartphone app, while the adaptive approach can determine questions based on the previous questions' answers. The adaptive approach saves time and can be beneficial when used at the point of care. CONCLUSIONS: This study solved a real clinical problem, and the solution can be used for personalized and precise evidence-based CINV management, leading to a better life quality for patients and reduced health care costs.

A Federated Mining Approach on Predicting Diabetes-Related Complications: Demonstration Using Real-World Clinical Data.

Chronic diabetes can lead to microvascular complications, including diabetic eye disease, diabetic kidney disease, and diabetic neuropathy. However, the long-term complications often remain undetected at the early stages of diagnosis. Developing a machine learning model to identify the patients at high risk of developing diabetes-related complications can help design better treatment interventions. Building robust machine learning models require large datasets which further requires sharing data among different healthcare systems, hence, involving privacy and confidentiality concerns. The main objective of this study is to design a decentralized privacy-protected federated learning architecture that can deliver comparable performance to centralized learning. We demonstrate the potential of adopting federated learning to address the challenges such as class-imbalance in using real-world clinical data. In all our experiments, federated learning showed comparable performance to the gold-standard of centralized learning, and applying class balancing techniques improved performance across all cohorts.