Natural language processing to identify lupus nephritis phenotype in electronic health records.

BACKGROUND: Systemic lupus erythematosus (SLE) is a rare autoimmune disorder characterized by an unpredictable course of flares and remission with diverse manifestations. Lupus nephritis, one of the major disease manifestations of SLE for organ damage and mortality, is a key component of lupus classification criteria. Accurately identifying lupus nephritis in electronic health records (EHRs) would therefore benefit large cohort observational studies and clinical trials where characterization of the patient population is critical for recruitment, study design, and analysis. Lupus nephritis can be recognized through procedure codes and structured data, such as laboratory tests. However, other critical information documenting lupus nephritis, such as histologic reports from kidney biopsies and prior medical history narratives, require sophisticated text processing to mine information from pathology reports and clinical notes. In this study, we developed algorithms to identify lupus nephritis with and without natural language processing (NLP) using EHR data from the Northwestern Medicine Enterprise Data Warehouse (NMEDW). METHODS: We developed five algorithms: a rule-based algorithm using only structured data (baseline algorithm) and four algorithms using different NLP models. The first NLP model applied simple regular expression for keywords search combined with structured data. The other three NLP models were based on regularized logistic regression and used different sets of features including positive mention of concept unique identifiers (CUIs), number of appearances of CUIs, and a mixture of three components (i.e. a curated list of CUIs, regular expression concepts, structured data) respectively. The baseline algorithm and the best performing NLP algorithm were externally validated on a dataset from Vanderbilt University Medical Center (VUMC). RESULTS: Our best performing NLP model incorporated features from both structured data, regular expression concepts, and mapped concept unique identifiers (CUIs) and showed improved F measure in both the NMEDW (0.41 vs 0.79) and VUMC (0.52 vs 0.93) datasets compared to the baseline lupus nephritis algorithm. CONCLUSION: Our NLP MetaMap mixed model improved the F-measure greatly compared to the structured data only algorithm in both internal and external validation datasets. The NLP algorithms can serve as powerful tools to accurately identify lupus nephritis phenotype in EHR for clinical research and better targeted therapies.

Comparison of State-of-the-Art Neural Network Survival Models with the Pooled Cohort Equations for Cardiovascular Disease Risk Prediction.

BACKGROUND: The Pooled Cohort Equations (PCEs) are race- and sex-specific Cox proportional hazards (PH)-based models used for 10-year atherosclerotic cardiovascular disease (ASCVD) risk prediction with acceptable discrimination. In recent years, neural network models have gained increasing popularity with their success in image recognition and text classification. Various survival neural network models have been proposed by combining survival analysis and neural network architecture to take advantage of the strengths from both. However, the performance of these survival neural network models compared to each other and to PCEs in ASCVD prediction is unknown. METHODS: In this study, we used 6 cohorts from the Lifetime Risk Pooling Project (with 5 cohorts as training/internal validation and one cohort as external validation) and compared the performance of the PCEs in 10-year ASCVD risk prediction with an all two-way interactions Cox PH model (Cox PH-TWI) and three state-of-the-art neural network survival models including Nnet-survival, Deepsurv, and Cox-nnet. For all the models, we used the same 7 covariates as used in the PCEs. We fitted each of the aforementioned models in white females, white males, black females, and black males, respectively. We evaluated models' internal and external discrimination power and calibration. RESULTS: The training/internal validation sample comprised 23216 individuals. The average age at baseline was 57.8 years old (SD = 9.6); 16% developed ASCVD during average follow-up of 10.50 (SD = 3.02) years. Based on 10 × 10 cross-validation, the method that had the highest C-statistics was Deepsurv (0.7371) for white males, Deepsurv and Cox PH-TWI (0.7972) for white females, PCE (0.6981) for black males, and Deepsurv (0.7886) for black females. In the external validation dataset, Deepsurv (0.7032), Cox-nnet (0.7282), PCE (0.6811), and Deepsurv (0.7316) had the highest C-statistics for white male, white female, black male, and black female population, respectively. Calibration plots showed that in 10 × 10 validation, all models had good calibration in all race and sex groups. In external validation, all models overestimated the risk for 10-year ASCVD. CONCLUSIONS: We demonstrated the use of the state-of-the-art neural network survival models in ASCVD risk prediction. Neural network survival models had similar if not superior discrimination and calibration compared to PCEs.

A Cohort Analysis of Statin Treatment Patterns Among Small-Sized Primary Care Practices.

BACKGROUND: Small-sized primary care practices, defined as practices with fewer than 10 clinicians, delivered the majority of outpatient visits in the USA. Statin therapy in high-risk individuals reduces atherosclerotic cardiovascular disease (ASCVD) events, but prescribing patterns in small primary care practices are not well known. This study describes statin treatment patterns in small-sized primary care practices and examines patient- and practice-level factors associated with lack of statin treatment. METHODS: We conducted a retrospective cohort analysis of statin-eligible patients from practices that participated in Healthy Hearts in the Heartland (H3), a quality improvement initiative aimed at improving cardiovascular care measures in small primary care practices. All statin-eligible adults who received care in one of 53 H3 practices from 2013 to 2016. Statin-eligible adults include those aged at least 21 with (1) clinical ASCVD, (2) low-density lipoprotein cholesterol (LDL-C) ≥ 190 mg/dL, or (3) diabetes aged 40-75 and with LDL-C 70-189 mg/dL. Eligible patients with no record of moderate- to high-intensity statin prescription are defined by ACC/AHA guidelines. RESULTS: Among the 13,330 statin-eligible adults, the mean age was 58 years and 52% were women. Overall, there was no record of moderate- to high-intensity statin prescription among 5,780 (43%) patients. Younger age, female sex, and lower LDL-C were independently associated with a lack of appropriate intensity statin therapy. Higher proportions of patients insured by Medicaid and having only family medicine trained physicians (versus having at least one internal medicine trained physician) at the practice were also associated with lower appropriate intensity statin use. Lack of appropriate intensity statin therapy was higher in independent practices than in Federally Qualified Health Centers (FQHCs) (50% vs. 40%, p value < 0.01). CONCLUSIONS: There is an opportunity for improved ASCVD risk reduction in small primary care practices. Statin treatment patterns and factors influencing lack of treatment vary by practice setting, highlighting the importance of tailored approaches to each setting.

Under-specification as the source of ambiguity and vagueness in narrative phenotype algorithm definitions.

INTRODUCTION: Currently, one of the commonly used methods for disseminating electronic health record (EHR)-based phenotype algorithms is providing a narrative description of the algorithm logic, often accompanied by flowcharts. A challenge with this mode of dissemination is the potential for under-specification in the algorithm definition, which leads to ambiguity and vagueness. METHODS: This study examines incidents of under-specification that occurred during the implementation of 34 narrative phenotyping algorithms in the electronic Medical Record and Genomics (eMERGE) network. We reviewed the online communication history between algorithm developers and implementers within the Phenotype Knowledge Base (PheKB) platform, where questions could be raised and answered regarding the intended implementation of a phenotype algorithm. RESULTS: We developed a taxonomy of under-specification categories via an iterative review process between two groups of annotators. Under-specifications that lead to ambiguity and vagueness were consistently found across narrative phenotype algorithms developed by all involved eMERGE sites. DISCUSSION AND CONCLUSION: Our findings highlight that under-specification is an impediment to the accuracy and efficiency of the implementation of current narrative phenotyping algorithms, and we propose approaches for mitigating these issues and improved methods for disseminating EHR phenotyping algorithms.

Up-Regulation of SorCS1, an Important Sorting Receptor, in the Retina of a Form-Deprivation Rat Model.

Visually guided regulation is a sophisticated and active process, whereby sensory input helps to shape ocular development. Here, we sought to investigate the potential involvement of SorCS1, an important protein in synaptic transmission in neuron, in retinal development. A form-deprivation (FD) rat model was established. Ocular variations induced by FD were examined, including changes to eye axial length and retinal thickness. Scotopic electroretinogram (ERG) was used to examine retinal function. RD-PCR assays were screened for differentially expressed genes in FD rat eyes. Immunofluorescence staining identified the expression pattern and localization of SorCS1 in rat retina, with or without FD treatment. Additionally, primary retinal neural cells were cultured and incubated with or without a light-dark cycle, and western blot and real-time PCR assays were used to examine the expression of SorCS1. Retinal neural cells were treated with recombinant SorCS1 (h-SorCS1) coated with beads in serum-free conditions to test for effects on cellular physiology and expression of neurotransmitters involved in visual development. To monitor cell viability, a CCK8 assay was employed. Our data demonstrated that FD led to ocular axial elongation and retinal thinning. ERG tests showed FD impaired electrophysiological function in rat. An age-related expression pattern of SorCS1 was observed in the rat retina, and SorCS1 was significantly up-regulated in the FD rat retina. In addition, in vitro evidence suggested a strong correlation between light exposure and SorCS1 expression. Furthermore, treatment of retinal neural cells with h-SorCS1-beads promoted cell viability, neurite outgrowth, and up-regulation of inhibitory neurotransmitter expression, which implies that over-expression of SorCS1 may cause abnormal retinal development. Our findings suggest that SorCS1 is involved in the physiological processes of light/visually guided ocular growth.

Discordant mRNA and protein expression of CXCR4 under in vitro CoCl2-induced hypoxic conditions.

Cobalt chloride (CoCl2) has long been accepted as a suitable in vitro hypoxia-mimetic agent. The gene CXCR4, which encodes a chemokine receptor, plays a key role in hypoxic retinal disease. Here, we investigated the mRNA and protein expression of CXCR4 in WERI-Rb1 retinoblastoma cells and human umbilical vein endothelial cells (HUVECs) under CoCl2-induced hypoxic conditions, by means of real-time PCR and western blot. We found that CoCl2-induced hypoxia profoundly increased CXCR4 expression at the mRNA level, but not at the protein level, at 12, 24, 48 and 72 h in these cells. Interestingly, this result differed from observations of 1% O2 hypoxic conditions. Additionally, luciferase assays demonstrated that CoCl2-induced hypoxia significantly increased transcription at the CXCR4 promoter. In order to compare our in vitro findings with the effects of hypoxia in vivo, an OIR (Oxygen-induced retinopathy) rat model was constructed. However, both CXCR4 mRNA and protein levels in OIR rats were significantly increased compared to controls. Thus taken together, our findings suggest that the relationship between CXCR4 mRNA and protein expression is not strictly linear under in vitro CoCl2-induced hypoxic conditions. through comparative in vitro and in vivo experiments, this study implies that CoCl2 is an imperfect simulation of hypoxia in retinal disease.

Longitudinal clustering of Life's Essential 8 health metrics: application of a novel unsupervised learning method in the CARDIA study.

OBJECTIVE: Changes in cardiovascular health (CVH) during the life course are associated with future cardiovascular disease (CVD). Longitudinal clustering analysis using subgraph augmented non-negative matrix factorization (SANMF) could create phenotypic risk profiles of clustered CVH metrics. MATERIALS AND METHODS: Life's Essential 8 (LE8) variables, demographics, and CVD events were queried over 15 ears in 5060 CARDIA participants with 18 years of subsequent follow-up. LE8 subgraphs were mined and a SANMF algorithm was applied to cluster frequently occurring subgraphs. K-fold cross-validation and diagnostics were performed to determine cluster assignment. Cox proportional hazard models were fit for future CV event risk and logistic regression was performed for cluster phenotyping. RESULTS: The cohort (54.6% female, 48.7% White) produced 3 clusters of CVH metrics: Healthy & Late Obesity (HLO) (29.0%), Healthy & Intermediate Sleep (HIS) (43.2%), and Unhealthy (27.8%). HLO had 5 ideal LE8 metrics between ages 18 and 39 years, until BMI increased at 40. HIS had 7 ideal LE8 metrics, except sleep. Unhealthy had poor levels of sleep, smoking, and diet but ideal glucose. Race and employment were significantly different by cluster (P < .001) but not sex (P = .734). For 301 incident CV events, multivariable hazard ratios (HRs) for HIS and Unhealthy were 0.73 (0.53-1.00, P = .052) and 2.00 (1.50-2.68, P < .001), respectively versus HLO. A 15-year event survival was 97.0% (HIS), 96.3% (HLO), and 90.4% (Unhealthy, P < .001). DISCUSSION AND CONCLUSION: SANMF of LE8 metrics identified 3 unique clusters of CVH behavior patterns. Clustering of longitudinal LE8 variables via SANMF is a robust tool for phenotypic risk assessment for future adverse cardiovascular events.

Regulation and mechanism of enzyme metabolism in germinated hemp seeds by ultrasound combined with exogenous calcium chloride treatment.

γ-aminobutyric acid (GABA) plays an important role in anti-anxiety by inhibiting neurotransmitter in the central nervous system (CNS) of mammals, which is generated in the germinating seeds. The key enzymes activity of GABA metabolism pathway and nutrients content in hemp seeds during germination were studied after treated with ultrasound and CaCl2. The mechanism of exogenous stress on key enzymes in GABA metabolism pathway was investigated by molecular dynamics simulation. The results showed that ultrasonic combined with 1.5 mmol·L-1CaCl2 significantly increased the activities of glutamate decarboxylase (GAD) and GABA transaminase (GABA-T) in seeds, and promoted the conversion of glutamate to GABA, resulting in the decrease of glutamate content and the accumulation of GABA. Molecular dynamics simulations revealed that Ca2+ environment enhanced the activity of GAD and GABA-T enzymes by altering their secondary structure, exposing their hydrophobic residues. Ultrasound, germination and CaCl2 stress improved the nutritional value of hemp seeds.

Salidroside pretreatment alleviates ferroptosis induced by myocardial ischemia/reperfusion through mitochondrial superoxide-dependent AMPKα2 activation.

BACKGROUND: Ferroptosis, a form of regulated cell death (RCD) that relies on excessive reactive oxygen species (ROS) generation, Fe2+accumulation, abnormal lipid metabolism and is involved in various organ ischemia/reperfusion (I/R) injury, expecially in myocardium. Mitochondria are the powerhouses of eukaryotic cells and essential in regulating multiple RCD. However, the links between mitochondria and ferroptosis are still poorly understood. Salidroside (Sal), a natural phenylpropanoid glycoside isolated from Rhodiola rosea, has mult-bioactivities. However, the effects and mechanism in alleviating ferroptosis caused by myocardial I/R injury remains unclear. PURPOSE: This study aimed to investigate whether pretreated with Sal could protect the myocardium against I/R damage and the underlying mechanisms. In particular, the relationship between Sal pretreatment, AMPKα2 activity, mitochondria and ROS generation was explored. STUDY DESIGN AND METHODS: Firstly, A/R or I/R injury models were employed in H9c2 cells and Sprague-Dawley rats. And then the anti-ferroptotic effects and mechanism of Sal pretreatment was detected using multi-relevant indexes in H9c2 cells. Further, how does Sal pretreatment in AMPKα2 phosphorylation was explored. Finally, these results were validated by I/R injury in rats. RESULTS: Similar to Ferrostatin-1 (a ferroptosis inhibitor) and MitoTEMPO, a mitochondrial free radical scavenger, Sal pretreatment effectively alleviated Fe2+ accumulation, redox disequilibrium and maintained mitochondrial energy production and function in I/R-induced myocardial injury, as demonstrated using multifunctional, enzymatic, and morphological indices. However, these effects were abolished by downregulation of AMPKα2 using an adenovirus, both in vivo and in vitro. Moreover, the results also provided a non-canonical mechanism that, under mild mitochondrial ROS generation, Sal pretreatment upregulated and phosphorylated AMPKα2, which enhanced mitochondrial complex I activity to activate innate adaptive responses and increase cellular tolerance to A/R injury. CONCLUSION: Overall, our work highlighted mitochondria are of great impotance in myocardial I/R-induced ferroptosis and demonstrated that Sal pretreatment activated AMPKα2 against I/R injury, indicating that Sal could become a candidate phytochemical for the treatment of myocardial I/R injury.

Rapid and accurate quantification of trypsin activity using integrated infrared and ultraviolet spectroscopy with data fusion techniques.

Proteases play a crucial role in industrial enzyme formulations, with activity fluctuations significantly impacting product quality and yield. Therefore, developing a method for precise and rapid detection of protease activity is paramount. This study aimed to develop a rapid and accurate method for quantifying trypsin activity using integrated infrared (IR) and ultraviolet (UV) spectroscopy combined with data fusion techniques. The developed method evaluates the enzymatic activity of trypsin under varying conditions, including temperature, pH, and ionic strength. By comparing different data fusion methods, the study identifies the optimal model for accurate enzyme activity prediction. The results demonstrated significant improvements in predictive performance using the feature-level data fusion approach. Additionally, substituting the spectral data of the samples in the validation sets into the best prediction model resulted in a minimal residual difference between predicted and true values, further verifying the model's accuracy and reliability. This innovative approach offers a practical solution for the efficient and precise quantification of enzyme activity, with broad applications in industrial processes.

Endurance exercise preconditioning alleviates ferroptosis induced by doxorubicin-induced cardiotoxicity through mitochondrial superoxide-dependent AMPKα2 activation.

Doxorubicin-induced cardiotoxicity (DIC) adversely impacts patients' long-term health and quality of life. Its underlying mechanism is complex, involving regulatory cell death mechanisms, such as ferroptosis and autophagy. Moreover, it is a challenge faced by patients undergoing cardiac rehabilitation. Endurance exercise (E-Exe) preconditioning effectively counters DIC injury, potentially through the adenosine monophosphate-activated protein kinase (AMPK) pathway. However, detailed studies on this process's mechanisms are scarce. Here, E-Exe preconditioning and DIC models were established using mice and primary cultured adult mouse cardiomyocytes (PAMCs). Akin to ferrostatin-1 (ferroptosis inhibitor), rapamycin (autophagic inducer), and MitoTEMPO (mitochondrial free-radical scavenger), E-Exe preconditioning effectively alleviated Fe2+ accumulation and oxidative stress and improved energy metabolism and mitochondrial dysfunction in DIC injury, as demonstrated by multifunctional, enzymatic, and morphological indices. However, erastin (ferroptosis inducer), 3-methyladenine (autophagic inhibitor), adenovirus-mediated AMPKα2 downregulation, and AMPKα2 inhibition by compound C significantly diminished these effects, both in vivo and in vitro. The results suggest a non-traditional mechanism where E-Exe preconditioning, under mild mitochondrial reactive oxygen species generation, upregulates and phosphorylates AMPKα2, thereby enhancing mitochondrial complex I activity, activating adaptive autophagy, and improving myocardial tolerance to DIC injury. Overall, this study highlighted the pivotal role of mitochondria in myocardial DIC-induced ferroptosis and shows how E-Exe preconditioning activated AMPKα2 against myocardial DIC injury. This suggests that E-Exe preconditioning could be a viable strategy for patients undergoing cardiac rehabilitation.

Astragaloside IV intervenes multi-regulatory cell death forms against doxorubicin-induced cardiotoxicity by regulating AMPKα2 pathway.

The clinical use of doxorubicin has been severely limited by doxorubicin-induced cardiotoxicity (DIC). Its mechanism is extremely complex and involves reactive oxygen species overgeneration, DNA damage, and aberrant inflammatory activity, which also involves multi-regulatory cell death mechanisms, including apoptosis, autophagy, and pyroptosis. These mechanisms overlap and crosstalk, resulting in the poor intervention of DIC injury. Astragaloside IV (Ast) has polybioactivity and mitigates DIC damage; however, the underlying mechanisms remain unknown. This study aimed to investigate whether Ast pretreatment (Ast-pre) could protect the myocardium against DIC damage and the underlying mechanisms. In particular, the relationship between Ast-pre, AMPKα2 activity, autophagy, apoptosis, and pyroptosis was explored. Firstly, DIC injury models were established using neonatal rat cardiomyocytes (NRCMs) and mice. And then the effects of adaptive autophagy, anti-pyroptosis and anti-apoptosis of Ast-pre were detected using multi-relevant indexes in NRCMs. Further, how does Ast-pre in AMPKα2 phosphorylation was explored. Finally, these results were validated by DIC injury in mice. Ast-pre, similar to disulfiram (pyroptosis inhibitor), effectively alleviated the inflammatory response, inhibited oxidative and energy stress, prevented mitochondrial dysfunction, and protected the myocardium resisting DIC damage, as demonstrated using multi-indexes. The protection of Ast-pre to DIC damage was almostly canceled by paclitaxel (pyroptosis inducer), 3-methyladenine (autophagy inhibitor), and pAD/AMPKα2-shRNA or compound C (AMPK inhibitor) to varying degrees. In conclusion, Ast-pre could upregulate and activate AMPKα2, enhance adaptive autophagy, and improve energy metabolism and mitochondrial function, thereby alleviate DIC-induced pyroptosis and apoptosis in NRCMs and mice.

Incorporating longitudinal history of risk factors into atherosclerotic cardiovascular disease risk prediction using deep learning.

It is increasingly clear that longitudinal risk factor levels and trajectories are related to risk for atherosclerotic cardiovascular disease (ASCVD) above and beyond single measures. Currently used in clinical care, the Pooled Cohort Equations (PCE) are based on regression methods that predict ASCVD risk based on cross-sectional risk factor levels. Deep learning (DL) models have been developed to incorporate longitudinal data for risk prediction but its benefit for ASCVD risk prediction relative to the traditional Pooled Cohort Equations (PCE) remain unknown. Our study included 15,565 participants from four cardiovascular disease cohorts free of baseline ASCVD who were followed for adjudicated ASCVD. Ten-year ASCVD risk was calculated in the training set using our benchmark, the PCE, and a longitudinal DL model, Dynamic-DeepHit. Predictors included those incorporated in the PCE: sex, race, age, total cholesterol, high density lipid cholesterol, systolic and diastolic blood pressure, diabetes, hypertension treatment and smoking. The discrimination and calibration performance of the two models were evaluated in an overall hold-out testing dataset. Of the 15,565 participants in our dataset, 2170 (13.9%) developed ASCVD. The performance of the longitudinal DL model that incorporated 8 years of longitudinal risk factor data improved upon that of the PCE [AUROC: 0.815 (CI 0.782-0.844) vs 0.792 (CI 0.760-0.825)] and the net reclassification index was 0.385. The brier score for the DL model was 0.0514 compared with 0.0542 in the PCE. Incorporating longitudinal risk factors in ASCVD risk prediction using DL can improve model discrimination and calibration.

Is more better? The impact of implementing more interventions for hypertension control in a practice facilitation study for small- and medium-sized practices.

Interventions for blood pressure (BP) control have positive effects on outcomes for patients with hypertension. Research on these effects in small- and medium-sized practices is limited. Our retrospective analysis used data from Healthy Hearts in the Heartland (H3), a research program conducted in 2016-2018 as part of the Agency for Healthcare Research and Quality's EvidenceNOW initiative, to examine the impact of implementing more interventions for BP control in these settings. Thirty-eight H3 practices met inclusion criteria and were assigned to an implementer group (high or low) based on the number of interventions implemented with the support of a practice facilitator during the study. Practices in the high-implementer group implemented a mean of 2.2 additional interventions relative to the low-implementer group. Groups were compared on two measures of BP control: (1) mean percentage of hypertensive patients with a most recent BP below 140/90, and (2) mean systolic and diastolic BP of hypertensive patients. In the first measure, practices in the high-implementer group had greater improvement between baseline and the end of the study. Among the 10,150 patients included in the second measure, reductions in mean SBP and DBP were greater for the high-implementer group. These outcomes show that implementing additional interventions had a positive association with measures of BP control, though clinical significance was unknown or limited. Future research is needed to understand the impact of interventions for BP control in small- and medium-sized practices, including the interactions among intervention implementation, practice facilitation, and practice and patient characteristics.

Significance of Intraoperative Medication Data and Predictive Model Selection for Predicting Postoperative First-Time Atrial Fibrillation.

Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia in clinical practice and has a well-established association with coronary artery bypass graft (CABG) surgery. Being able to predict post-operative AF (POAF) may improve surgical outcomes. This study retrospectively assembled a large cohort of 3,807 first-time CABG patients with no prior AF to study factors that contribute to occurrence of POAF, in addition to testing models that may predict its incidence. Several clinical features with established relevance to POAF were extracted from the EHR, along with a record of medications administered intra-operatively. Tests of performance with logistic regression, decision tree, and neural network predictive models showed slight improvements when incorporating medication information. Analysis of the clinical and medications data indicate that there may be effects contributing to POAF incidence captured in the medication administration records. Our results show that improved predictive performance is achievable by incorporating a record of medications administered intra-operatively.

End-to-end deep learning classification of vocal pathology using stacked vowels.

Objectives: Advances in artificial intelligence (AI) technology have increased the feasibility of classifying voice disorders using voice recordings as a screening tool. This work develops upon previous models that take in single vowel recordings by analyzing multiple vowel recordings simultaneously to enhance prediction of vocal pathology. Methods: Voice samples from the Saarbruecken Voice Database, including three sustained vowels (/a/, /i/, /u/) from 687 healthy human participants and 334 dysphonic patients, were used to train 1-dimensional convolutional neural network models for multiclass classification of healthy, hyperfunctional dysphonia, and laryngitis voice recordings. Three models were trained: (1) a baseline model that analyzed individual vowels in isolation, (2) a stacked vowel model that analyzed three vowels (/a/, /i/, /u/) in the neutral pitch simultaneously, and (3) a stacked pitch model that analyzed the /a/ vowel in three pitches (low, neutral, and high) simultaneously. Results: For multiclass classification of healthy, hyperfunctional dysphonia, and laryngitis voice recordings, the stacked vowel model demonstrated higher performance compared with the baseline and stacked pitch models (F1 score 0.81 vs. 0.77 and 0.78, respectively). Specifically, the stacked vowel model achieved higher performance for class-specific classification of hyperfunctional dysphonia voice samples compared with the baseline and stacked pitch models (F1 score 0.56 vs. 0.49 and 0.50, respectively). Conclusions: This study demonstrates the feasibility and potential of analyzing multiple sustained vowel recordings simultaneously to improve AI-driven screening and classification of vocal pathology. The stacked vowel model architecture in particular offers promise to enhance such an approach. Lay Summary: AI analysis of multiple vowel recordings can improve classification of voice pathologies compared with models using a single sustained vowel and offer a strategy to enhance AI-driven screening of voice disorders. Level of Evidence: 3.

Incorporating longitudinal history of risk factors into atherosclerotic cardiovascular disease risk prediction using deep learning.

Background: It is increasingly clear that longitudinal risk factor levels and trajectories are related to risk for atherosclerotic cardiovascular disease (ASCVD) above and beyond single measures. Currently used in clinical care, the Pooled Cohort Equations (PCE) are based on regression methods that predict ASCVD risk based on cross-sectional risk factor levels. Deep learning (DL) models have been developed to incorporate longitudinal data for risk prediction but its benefit for ASCVD risk prediction relative to the traditional Pooled Cohort Equations (PCE) remain unknown. Objective: To develop a ASCVD risk prediction model that incorporates longitudinal risk factors using deep learning. Methods: Our study included 15,565 participants from four cardiovascular disease cohorts free of baseline ASCVD who were followed for adjudicated ASCVD. Ten-year ASCVD risk was calculated in the training set using our benchmark, the PCE, and a longitudinal DL model, Dynamic-DeepHit. Predictors included those incorporated in the PCE: sex, race, age, total cholesterol, high density lipid cholesterol, systolic and diastolic blood pressure, diabetes, hypertension treatment and smoking. The discrimination and calibration performance of the two models were evaluated in an overall hold-out testing dataset. Results: Of the 15,565 participants in our dataset, 2,170 (13.9%) developed ASCVD. The performance of the longitudinal DL model that incorporated 8 years of longitudinal risk factor data improved upon that of the PCE [AUROC: 0.815 (CI: 0.782-0.844) vs 0.792 (CI: 0.760-0.825)] and the net reclassification index was 0.385. The brier score for the DL model was 0.0514 compared with 0.0542 in the PCE. Conclusion: Incorporating longitudinal risk factors in ASCVD risk prediction using DL can improve model discrimination and calibration.

Comparison of Sodium-Glucose Cotransporter-2 Inhibitor and Glucagon-Like Peptide-1 Receptor Agonist Prescribing in Patients With Diabetes Mellitus With and Without Cardiovascular Disease.

Sodium-glucose cotransporter-2 inhibitors (SGLT2is) and glucagon-like peptide-1 receptor agonists (GLP1-RAs) reduce cardiovascular events and mortality in patients with type 2 diabetes mellitus (T2DM). We sought to describe trends in prescribing for SGLT2is and GLP1-RAs in diverse care settings, including (1) the outpatient clinics of a midwestern integrated health system and (2) small- and medium-sized community-based primary care practices and health centers in 3 midwestern states. We included adults with T2DM and ≥1 outpatient clinic visit. The outcomes of interest were annual active prescription rates for SGLT2is and GLP1-RAs (separately). In the integrated health system, 22,672 patients met the case definition of T2DM. From 2013 to 2019, the overall prescription rate for SGLT2is increased from 1% to 15% (absolute difference [AD] 14%, 95% confidence interval [CI] 13% to 15%, p <0.01). The GLP1-RA prescription rate was stable at 10% (AD 0%, 95% CI -1% to 1%, p = 0.9). In community-based primary care practices, 43,340 patients met the case definition of T2DM. From 2013 to 2017, the SGLT2i prescription rate increased from 3% to 7% (AD 4%, 95% CI 3% to 6%, p <0.01), whereas the GLP1-RA prescription rate was stable at 2% to 3% (AD 1%, 95% CI -1 to 1%, p = 0.40). In a fully adjusted regression model, non-Hispanic Black patients had lower odds of SGLT2i or GLP1-RA prescription (odds ratio 0.56, 95% CI 0.34 to 0.89, p = 0.016). In conclusion, the increase in prescription rates was greater for SGLT2is than for GLP1-RAs in patients with T2DM in a large integrated medical center and community primary care practices. Overall, prescription rates for eligible patients were low, and racial disparities were observed.

Predicting Avoidable Emergency Department Visits Using the NHAMCS Dataset.

Despite the important role avoidable emergency department (ED) visits play in healthcare costs and quality of care, there has been little work in development of predictive models to identify patients likely to present with an avoidable ED visit. We use a conservative definition of 'avoidable' ED visits defined as visits that do not require diagnostic or screening services, procedures, or medications, and were discharged home to classify visits as avoidable. Models trained using data from emergency departments across the US yielded a training AUC of 0.723 and a testing AUC of 0.703. Models trained using the full dataset were tested on demographic groups (race, gender, insurance status), finding comparable performance between white/black patients and male/female with reductions in performance in Hispanic populations and patients with Medicaid. Predictors strongly associated with non-avoidable ED visits included increased age, increasing number of total chronic diseases, and general as well as digestive symptoms. Reasons for visit stated as injuries and psychiatric symptoms influenced the model to predict an avoidable visit.

Use of real-world evidence data to evaluate the comparative effectiveness of second-line type 2 diabetes medications on chronic kidney disease.

Chronic kidney disease (CKD) is a common complication of type 2 diabetes mellitus (T2DM). Approximately-one-third of patients with T2DM also have CKD. In clinical trial studies, several anti-diabetic medications (ADM) show evidence of preventing the progression of CKD. Biguanides (e.g., metformin) are widely accepted as the first line medication. However, the comparative effectiveness of second line ADMs on CKD outcomes in T2DM is unclear. In addition, results from clinical trials may not generalize into routine clinical practice. In this study, we aimed to investigate the association of second line ADMs with diagnosed incident CKD, CKD hospitalization, and eGFR < 45 mL/min in T2DM patients using real-world data from electronic health records. Our study found that treatment with sodium-glucose cotransporter 2 (SGLT-2) inhibitors was significantly associated with lower risk of diagnosed CKD incidence in both primary analysis (hazard ratio, 0.43; 95 % CI, [0.22;0.87]; p-value,0.02) and secondary analysis (hazard ratio, 0.42; 95 % CI, [0.19;0.92]; p-value, 0.03) compared to use of Sulfonylureas (SU) as a second-line ADM. However, significant associations were not observed when using eGFR < 45 mL/min as the endpoint. Treatment with a dipeptidyl peptidase 4 (DPP-4) inhibitor was significantly associated with lower risk of diagnosed incident CKD (hazard ratio, 0.7; 95 % CI, [0.53;0.96]; p-value, 0.03) and lower risk of CKD hospitalization (hazard ratio, 0.6; 95 % CI, [0.37; 0.96]; p-value, 0.04) in the primary analysis. However, both associations were not significant in the sensitivity analysis. We did not observe significant association between use of glucagon-like peptide 1 receptor agonists (GLP-1RA), Thiazolidinediones (TZD), insulin and diagnosed CKD incidence, hospitalization or eGFR < 45 mL/min compared to use of SU as a second-line ADM.