Real-Time Obstructive Sleep Apnea Detection from Raw ECG and SpO2 Signal Using Convolutional Neural Network.

Obstructive sleep apnea is a sleep disorder that is linked with many health complications and severe form of apnea can even be lethal. Overnight polysomnography is the gold standard for diagnosing apnea, which is expensive, time-consuming, and requires manual analysis by a sleep expert. Recently, there have been numerous studies demonstrating the application of artificial intelligence to detect apnea in real time. But the majority of these studies apply data pre-processing and feature extraction techniques resulting in a longer inference time that makes the real-time detection system inefficient. This study proposes a single convolutional neural network architecture that can automatically extract spatial features and detect apnea from both electrocardiogram (ECG) and blood-oxygen saturation (SpO2) signals. Using segments of 10s, the network classified apnea with an accuracy of 94.2% and 96% for ECG and SpO2 respectively. Moreover, the overall performance of both models was consistent with an AUC score of 0.99.

Pediatric Gastrointestinal Outcomes During the Post-Acute Phase of COVID-19.

Background: The impact of COVID-19 on gastrointestinal (GI) outcomes in children during the post-acute and chronic phases of the disease is not well understood. Methods: We conducted a retrospective cohort study across twenty-nine healthcare institutions from March 2020 to September 2023, including 413,455 pediatric patients with confirmed SARS-CoV-2 infection and 1,163,478 controls without infection. Infection was confirmed via polymerase chain reaction (PCR), serology, antigen tests, or clinical diagnosis of COVID-19 and related conditions. We examined the incidence of predefined GI symptoms and disorders during the post-acute (28 to 179 days post-infection) and chronic (180 to 729 days post-infection) phases. The adjusted risk ratios (aRRs) were calculated using stratified Poisson regression, with stratification based on propensity scores. Results: Our cohort comprised 1,576,933 patients, with females representing 48.0% of the sample. The analysis revealed that children with SARS-CoV-2 infection had an increased risk of developing at least one GI symptom or disorder in both the post-acute (8.64% vs. 6.85%; aRR 1.25, 95% CI 1.24-1.27) and chronic phases (12.60% vs. 9.47%; aRR 1.28, 95% CI 1.26-1.30) compared to uninfected peers. Specifically, the risk of abdominal pain was higher in COVID-19 positive patients during the post-acute phase (2.54% vs. 2.06%; aRR 1.14, 95% CI 1.11-1.17) and chronic phase (4.57% vs. 3.40%; aRR 1.24, 95% CI 1.22-1.27). Interpretation: Children with a history of SARS-CoV-2 infection are at an increased risk of GI symptoms and disorders during the post-acute and chronic phases of COVID-19. This highlights the need for ongoing monitoring and management of GI outcomes in this population.

Post-Acute Cardiovascular Outcomes of COVID-19 in Children and Adolescents: An EHR Cohort Study from the RECOVER Project.

Background: The risk of cardiovascular outcomes in the post-acute phase of SARS-CoV-2 infection has been quantified among adults and children. This paper aimed to assess a multitude of cardiac signs, symptoms, and conditions, as well as focused on patients with and without congenital heart defects (CHDs), to provide a more comprehensive assessment of the post-acute cardiovascular outcomes among children and adolescents after COVID-19. Methods: This retrospective cohort study used data from the RECOVER consortium comprising 19 US children's hospitals and health institutions between March 2020 and September 2023. Every participant had at least a six-month follow-up after cohort entry. Absolute risks of incident post-acute COVID-19 sequelae were reported. Relative risks (RRs) were calculated by contrasting COVID-19-positive with COVID-19-negative groups using a Poisson regression model, adjusting for demographic, clinical, and healthcare utilization factors through propensity scoring stratification. Results: A total of 1,213,322 individuals under 21 years old (mean[SD] age, 7.75[6.11] years; 623,806 male [51.4%]) were included. The absolute rate of any post-acute cardiovascular outcome in this study was 2.32% in COVID-19 positive and 1.38% in negative groups. Patients with CHD post-SARS-CoV-2 infection showed increased risks of any cardiovascular outcome (RR, 1.63; 95% confidence interval (CI), 1.47-1.80), including increased risks of 11 of 18 post-acute sequelae in hypertension, arrhythmias (atrial fibrillation and ventricular arrhythmias), myocarditis, other cardiac disorders (heart failure, cardiomyopathy, and cardiac arrest), thrombotic disorders (thrombophlebitis and thromboembolism), and cardiovascular-related symptoms (chest pain and palpitations). Those without CHDs also experienced heightened cardiovascular risks after SARS-CoV-2 infection (RR, 1.63; 95% CI, 1.57-1.69), covering 14 of 18 conditions in hypertension, arrhythmias (ventricular arrhythmias and premature atrial or ventricular contractions), inflammatory heart disease (pericarditis and myocarditis), other cardiac disorders (heart failure, cardiomyopathy, cardiac arrest, and cardiogenic shock), thrombotic disorders (pulmonary embolism and thromboembolism), and cardiovascular-related symptoms (chest pain, palpitations, and syncope). Conclusions: Both children with and without CHDs showed increased risks for a variety of cardiovascular outcomes after SARS-CoV-2 infection, underscoring the need for targeted monitoring and management in the post-acute phase.

Long COVID incidence in adults and children between 2020 and 2023: a real-world data study from the RECOVER Initiative.

Estimates of post-acute sequelae of SARS-CoV-2 infection (PASC) incidence, also known as Long COVID, have varied across studies and changed over time. We estimated PASC incidence among adult and pediatric populations in three nationwide research networks of electronic health records (EHR) participating in the RECOVER Initiative using different classification algorithms (computable phenotypes). Overall, 7% of children and 8.5%-26.4% of adults developed PASC, depending on computable phenotype used. Excess incidence among SARS-CoV-2 patients was 4% in children and ranged from 4-7% among adults, representing a lower-bound incidence estimation based on two control groups - contemporary COVID-19 negative and historical patients (2019). Temporal patterns were consistent across networks, with peaks associated with introduction of new viral variants. Our findings indicate that preventing and mitigating Long COVID remains a public health priority. Examining temporal patterns and risk factors of PASC incidence informs our understanding of etiology and can improve prevention and management.

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.

Factors Associated With Receipt of Molecular Testing and its Impact on Time to Initial Systemic Therapy in Metastatic Non-Small Cell Lung Cancer.

BACKGROUND: Despite recommendations for molecular testing irrespective of patient characteristics, differences exist in receipt of molecular testing for oncogenic drivers amongst metastatic non-small cell lung cancer (mNSCLC) patients. Exploration into these differences and their effects on treatment is needed to identify opportunities for improvement. PATIENTS AND METHODS: We conducted a retrospective cohort study of adult patients diagnosed with mNSCLC between 2011 and 2018 using PCORnet's Rapid Cycle Research Project dataset (n = 3600). Log-binomial, Cox proportional hazards (PH), and time-varying Cox regression models were used to ascertain whether molecular testing was received, and time from diagnosis to molecular testing and/or initial systemic treatment in the context of patient age, sex, race/ethnicity, and multiple comorbidities status. RESULTS: The majority of patients in this cohort were ≤ 65 years of age (median [25th, 75th]: 64 [57, 71]), male (54.3%), non-Hispanic white individuals (81.6%), with > 2 comorbidities in addition to mNSCLC (54.1%). About half the cohort received molecular testing (49.9%). Patients who received molecular testing had a 59% higher probability of initial systemic treatment than patients who were yet to receive testing. Multiple comorbidity status was positively associated with receipt of molecular testing (RR, 1.27; 95% CI 1.08, 1.49). CONCLUSION: Receipt of molecular testing in academic centers was associated with earlier initiation of systemic treatment. This finding underscores the need to increase molecular testing rates amongst mNSCLC patients during a clinically relevant period. Further studies to validate these findings in community centers are warranted.

Mapping Clinical Documents to the Logical Observation Identifiers, Names and Codes (LOINC) Document Ontology using Electronic Health Record Systems Structured Metadata.

As Electronic Health Record (EHR) systems increase in usage, organizations struggle to maintain and categorize clinical documentation so it can be used for clinical care and research. While prior research has often employed natural language processing techniques to categorize free text documents, there are shortcomings relative to computational scalability and the lack of key metadata within notes' text. This study presents a framework that can allow institutions to map their notes to the LOINC document ontology using a Bag of Words approach. After preliminary manual value- set mapping, an automated pipeline that leverages key dimensions of metadata from structured EHR fields aligns the notes with the dimensions of the document ontology. This framework resulted in 73.4% coverage of EHR documents, while also mapping 132 million notes in less than 2 hours; an order of magnitude more efficient than NLP based methods.

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.

Development and Pilot Analysis of the Nursing Home Health Information Technology Maturity Survey and Staging Model.

The current research includes a psychometric test of a nursing home (NH) health information technology (HIT) maturity survey and staging model. NHs were assembled based on HIT survey scores from a prior study representing NHs with low (20%), medium (60%), and high (20%) HIT scores. Inclusion criteria were NHs that completed at least two annual surveys over 4 years. NH administrators were excluded who participated in the Delphi panel responsible for instrument recommendations. Recruitment occurred from January to May 2019. Administrators from 121 of 429 facilities completed surveys. NHs were characteristically for-profit, medium bed size, and metropolitan. A covariance matrix demonstrated that all dimensions and domains were significantly correlated, except HIT capabilities and integration in administrative activities. Cronbach's alpha was very good (0.86). Principal component analysis revealed all items loaded intuitively onto four components, explaining 80% variance. The HIT maturity survey and staging model can be used to assess nine dimensions and domains, total HIT maturity, and stage, leading to reliable assumptions about NH HIT. [Research in Gerontological Nursing, 15(2), 93-99.].

Medication Identification Device to Reduce Medication Errors in Nursing Homes: A Controlled Pilot Study.

A controlled pilot study was performed to evaluate implementation of a medication identification device intended to reduce errors in nursing homes. Naïve observation was used for data collection of medication errors on an intervention unit using the device and a control unit, along with field notes describing observation details. Ten staff were observed administering medications to 70 residents over the study time-frame. Of the 9,099 medication administrations observed (n = 4,588 intervention; n = 4,511 control), 1,068 (12%) errors were identified. The intervention unit had fewer non-time errors versus the control unit, including dose (n = 21 vs. n = 59; p < 0.01), drug (n = 4 vs. n = 21; p <0.01), route (n = 0 vs. n = 4; p < 0.01), and given without order (n = 1 vs. n = 8; p < 0.01). However, time errors were higher on the intervention unit and were often due to late start and interruptions. Non-time errors were due to reliance on memory and nursing judgment. A combination of technology and staff dedicated solely to medication administration likely affected error rate differences. [Journal of Gerontological Nursing, 48(4), 5-11.].

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.

Standardized Health data and Research Exchange (SHaRE): promoting a learning health system.

Aggregate de-identified data from electronic health records (EHRs) provide a valuable resource for research. The Standardized Health data and Research Exchange (SHaRE) is a diverse group of US healthcare organizations contributing to the Cerner Health Facts (HF) and Cerner Real-World Data (CRWD) initiatives. The 51 facilities at the 7 founding organizations have provided data about more than 4.8 million patients with 63 million encounters to HF and 7.4 million patients and 119 million encounters to CRWD. SHaRE organizations unmask their organization IDs and provide 3-digit zip code (zip3) data to support epidemiology and disparity research. SHaRE enables communication between members, facilitating data validation and collaboration as we demonstrate by comparing imputed EHR module usage to actual usage. Unlike other data sharing initiatives, no additional technology installation is required. SHaRE establishes a foundation for members to engage in discussions that bridge data science research and patient care, promoting the learning health system.

Enhancing PCORnet Clinical Research Network data completeness by integrating multistate insurance claims with electronic health records in a cloud environment aligned with CMS security and privacy requirements.

OBJECTIVE: The Greater Plains Collaborative (GPC) and other PCORnet Clinical Data Research Networks capture healthcare utilization within their health systems. Here, we describe a reusable environment (GPC Reusable Observable Unified Study Environment [GROUSE]) that integrates hospital and electronic health records (EHRs) data with state-wide Medicare and Medicaid claims and assess how claims and clinical data complement each other to identify obesity and related comorbidities in a patient sample. MATERIALS AND METHODS: EHR, billing, and tumor registry data from 7 healthcare systems were integrated with Center for Medicare (2011-2016) and Medicaid (2011-2012) services insurance claims to create deidentified databases in Informatics for Integrating Biology & the Bedside and PCORnet Common Data Model formats. We describe technical details of how this federally compliant, cloud-based data environment was built. As a use case, trends in obesity rates for different age groups are reported, along with the relative contribution of claims and EHR data-to-data completeness and detecting common comorbidities. RESULTS: GROUSE contained 73 billion observations from 24 million unique patients (12.9 million Medicare; 13.9 million Medicaid; 6.6 million GPC patients) with 1 674 134 patients crosswalked and 983 450 patients with body mass index (BMI) linked to claims. Diagnosis codes from EHR and claims sources underreport obesity by 2.56 times compared with body mass index measures. However, common comorbidities such as diabetes and sleep apnea diagnoses were more often available from claims diagnoses codes (1.6 and 1.4 times, respectively). CONCLUSION: GROUSE provides a unified EHR-claims environment to address health system and federal privacy concerns, which enables investigators to generalize analyses across health systems integrated with multistate insurance claims.

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.

HonestChain: Consortium blockchain for protected data sharing in health information systems.

Healthcare innovations are increasingly becoming reliant on high variety and standards-compliant (e.g., HIPAA, common data model) distributed data sets that enable predictive analytics. Consequently, health information systems need to be developed using cooperation and distributed trust principles to allow protected data sharing between multiple domains or entities (e.g., health data service providers, hospitals and research labs). In this paper, we present a novel health information sharing system viz., HonestChain that uses Blockchain technology to allow organizations to have incentive-based and trustworthy cooperation to either access or provide protected healthcare records. More specifically, we use a consortium Blockchain approach coupled with chatbot guided interfaces that allow data requesters to: (a) comply with data access standards, and (b) allow them to gain reputation in a consortium. We also propose a reputation scheme for creation and sustenance of the consortium with peers using Requester Reputation and Provider Reputation metrics. We evaluate HonestChain using Hyperledger Composer in a realistic simulation testbed on a public cloud infrastructure. Our results show that our HonestChain performs better than the state-of-the-art requester reputation schemes for data request handling, while choosing the most appropriate provider peers. We particularly show that HonestChain achieves a better tradeoff in metrics such as service time and request resubmission rate. Additionally, we also demonstrate the scalability of our consortium platform in terms of the Blockchain transaction times.

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.