Recent trends in tranexamic acid use during postpartum hemorrhage in the United States.

INTRODUCTION: Postpartum hemorrhage (PPH) was the second leading cause of maternal death, accounting for approximately 14% of all pregnancy-related deaths between 2017 and 2019 in the United States. Several large multi-center studies have demonstrated decreased PPH rates with the use of tranexamic acid (TXA). Little data exists regarding the prevalence of TXA use in obstetric patients. METHODS: We identified over 1.2 million US pregnancies between January 1, 2015 and June 30, 2021, with and without PPH by International Statistical Classification of Disease and Related Health Problems, Tenth Revision codes using Cerner Real-World Database™. TXA use and patient characteristics were abstracted from the electronic medical record. RESULTS: During delivery, TXA was used approximately 1% of the time (12,394 / 1,262,574). Pregnant patients who did and did not receive TXA during delivery had similar demographic characteristics. Pregnant patients who underwent cesarean delivery (4,356 / 12,394), had a term delivery (10,199 / 12,394), and had comorbid conditions were more likely to receive TXA during hospitalization for delivery. The majority of TXA was use was concentrated in Arizona, Colorado, Idaho, New Mexico, Nevada, Utah, and Wyoming. During the study period the use of TXA increased in both patients with PPH and those without. CONCLUSION: The data illustrate a rapid increase in the use of TXA after 2017 while the total number of pregnancies remained relatively constant. The observed increase in TXA use may reflect changing practicing patterns as the support for use of TXA in the setting of PPH prophylaxis increases.

The Sacred Sites of Houston: A Novel Experiential Course for Undergraduate Medical Education on Religion and Spirituality.

Medical schools are charged to deliver a curriculum on religion and spirituality (R/S), so a novel experiential course, the Sacred Sites of Houston, was developed. Sixty students completed the course consisting of 6 site visits. Post-course, participants described more general knowledge and knowledge of how each faith tradition describes medicine and health (p < 0.05 for all) except for Catholicism (p = 0.564 and p = 0.058). Ten course participants and 6 control non-course participants were interviewed following clinical rotations to assess the impact of the experiential course on R/S in the clinical setting. Themes from qualitative interviews such as R/S, barriers, interactions, and the course impact emerged. The importance of R/S in the patient-provider relationship and end-of-life care was prominent in course participant interviews compared to non-course participant control subjects. Participation in the course resulted in increased chaplain engagement and significant personal impact. These qualitative and quantitative findings indicate that an experiential course may be effective at addressing the deficit in R/S undergraduate medical education and help enhance the spiritually and religiously competent care of patients.

LocalControl: An R Package for Comparative Safety and Effectiveness Research.

The LocalControl R package implements novel approaches to address biases and confounding when comparing treatments or exposures in observational studies of outcomes. While designed and appropriate for use in comparative safety and effectiveness research involving medicine and the life sciences, the package can be used in other situations involving outcomes with multiple confounders. LocalControl is an open-source tool for researchers whose aim is to generate high quality evidence using observational data. The package implements a family of methods for non-parametric bias correction when comparing treatments in observational studies, including survival analysis settings, where competing risks and/or censoring may be present. The approach extends to bias-corrected personalized predictions of treatment outcome differences, and analysis of heterogeneity of treatment effect-sizes across patient subgroups.

DrugCentral: online drug compendium.

DrugCentral (http://drugcentral.org) is an open-access online drug compendium. DrugCentral integrates structure, bioactivity, regulatory, pharmacologic actions and indications for active pharmaceutical ingredients approved by FDA and other regulatory agencies. Monitoring of regulatory agencies for new drugs approvals ensures the resource is up-to-date. DrugCentral integrates content for active ingredients with pharmaceutical formulations, indexing drugs and drug label annotations, complementing similar resources available online. Its complementarity with other online resources is facilitated by cross referencing to external resources. At the molecular level, DrugCentral bridges drug-target interactions with pharmacological action and indications. The integration with FDA drug labels enables text mining applications for drug adverse events and clinical trial information. Chemical structure overlap between DrugCentral and five online drug resources, and the overlap between DrugCentral FDA-approved drugs and their presence in four different chemical collections, are discussed. DrugCentral can be accessed via the web application or downloaded in relational database format.

Will Artificial Intelligence Translate Big Data Into Improved Medical Care or Be a Source of Confusing Intrusion? A Discussion Between a (Cautious) Physician Informatician and an (Optimistic) Medical Informatics Researcher.

Artificial intelligence (AI), the computerized capability of doing tasks, which until recently was thought to be the exclusive domain of human intelligence, has demonstrated great strides in the past decade. The abilities to play games, provide piloting for an automobile, and respond to spoken language are remarkable successes. How are the challenges and opportunities of medicine different from these challenges and how can we best apply these data-driven techniques to patient care and outcomes? A New England Journal of Medicine paper published in 1980 suggested that more well-defined "specialized" tasks of medical care were more amenable to computer assistance, while the breadth of approach required for defining a problem and narrowing down the problem space was less so, and perhaps, unachievable. On the other hand, one can argue that the modern version of AI, which uses data-driven approaches, will be the most useful in tackling tasks such as outcome prediction that are often difficult for clinicians and patients. The ability today to collect large volumes of data about a single individual (eg, through a wearable device) and the accumulation of large datasets about multiple persons receiving medical care has the potential to apply to the care of individuals. As these techniques of analysis, enumeration, aggregation, and presentation are brought to bear in medicine, the question arises as to their utility and applicability in that domain. Early efforts in decision support were found to be helpful; as the systems proliferated, later experiences have shown difficulties such as alert fatigue and physician burnout becoming more prevalent. Will something similar arise from data-driven predictions? Will empowering patients by equipping them with information gained from data analysis help? Patients, providers, technology, and policymakers each have a role to play in the development and utilization of AI in medicine. Some of the challenges, opportunities, and tradeoffs implicit here are presented as a dialog between a clinician (SJN) and an informatician (QZT).

Comprehensive comparison of monotherapies for psychiatric hospitalization risk in bipolar disorders.

OBJECTIVES: This study compared 29 drugs for risk of psychiatric hospitalization in bipolar disorders, addressing the evidence gap on the >50 drugs used by US patients for treatment. METHODS: The Truven Health Analytics MarketScan® database was used to identify 190 894 individuals with bipolar or schizoaffective disorder who filled a prescription for one of 29 drugs of interest: lithium, first- or second-generation antipsychotics, mood-stabilizing anticonvulsants, and antidepressants. Competing risks regression survival analysis was used to compare drugs for risk of psychiatric hospitalization, adjusting for patient age, sex, comorbidities, and pretreatment medications. Other competing risks were ending monotherapy and non-psychiatric hospitalization. RESULTS: Three drugs were associated with significantly lower risk of psychiatric hospitalization than lithium: valproate (relative risk [RR] = 0.80, P = 3.20 × 10-4 ), aripiprazole (RR = 0.80, P = 3.50 × 10-4 ), and bupropion (RR = 0.80, P = 2.80 × 10-4 ). Eight drugs were associated with significantly higher risk of psychiatric hospitalization: haloperidol (RR = 1.57, P = 9.40 × 10-4 ), clozapine (RR = 1.52, P = .017), fluoxetine (RR = 1.17, P = 3.70 × 10-3 ), sertraline (RR = 1.17, P = 3.20 × 10-3 ), citalopram (RR = 1.14, P = .013), duloxetine (RR = 1.24, P = 5.10 × 10-4 ), venlafaxine (RR = 1.33; P = 1.00 × 10-6 ), and ziprasidone (RR = 1.25; P = 6.20 × 10-3 ). CONCLUSIONS: This largest reported retrospective observational study on bipolar disorders pharmacotherapy to date demonstrates that the majority of patients end monotherapy within 2 months after treatment start. The risk of psychiatric hospitalization varied almost two-fold across individual medications. The data add to the evidence favoring lithium and mood stabilizer use in short-term bipolar disorder management. The findings that the dopaminergic drugs aripiprazole and bupropion had better outcomes than other members of their respective classes and that antidepressant outcomes may vary by baseline mood polarity merit further investigation.

Systemic challenges in bipolar disorder management: A patient-centered approach.

OBJECTIVES: As part of a series of Patient-Centered Outcomes Research Institute-funded large-scale retrospective observational studies on bipolar disorder (BD) treatments and outcomes, we sought the input of patients with BD and their family members to develop research questions. We aimed to identify systemic root causes of patient-reported challenges with BD management in order to guide subsequent studies and initiatives. METHODS: Three focus groups were conducted where patients and their family members (total n = 34) formulated questions around the central theme, "What do you wish you had known in advance or over the course of treatment for BD?" In an affinity mapping exercise, participants clustered their questions and ranked the resulting categories by importance. The research team and members of our patient partner advisory council further rated the questions by expected impact on patients. Using a Theory of Constraints systems thinking approach, several causal models of BD management challenges and their potential solution were developed with patients using the focus group data. RESULTS: A total of 369 research questions were mapped to 33 categories revealing 10 broad themes. The top priorities for patient stakeholders involved pharmacotherapy and treatment alternatives. Analysis of causal relationships underlying 47 patient concerns revealed two core conflicts: for patients, whether or not to take pharmacotherapy, and for mental health services, the dilemma of care quality vs quantity. CONCLUSIONS: To alleviate the core conflicts identified, BD management requires a coordinated multidisciplinary approach including: improved access to mental health services, objective diagnostics, sufficient provider visit time, evidence-based individualized treatment, and psychosocial support.

Fractional epidermal grafting in combination with laser therapy as a novel approach in treating radiation dermatitis.

Radiation injury to the skin is a major source of dysfunction, disfigurement, and complications for thousands of patients undergoing adjunctive treatment for internal cancers. Despite the great potential for affecting quality of life, radiation injury has received little attention from dermatologists and is primarily being managed by radiation oncologists. During our volunteer work in Vietnam, we encountered numerous children with significant scarring and depigmentation of skin from the outdated use of radioactive phosphorus P32 in the treatment of hemangiomas. This dangerous practice has left thousands of children with significant fibrosis and disfigurement. Currently, there is no treatment for radiation dermatitis. Here, we report a case series using the combination of laser treatment, including pulsed-dye laser, fractional CO2 laser, and epidermal grafting to improve the appearance and function of the radiation scars in these young patients. We hope that by improving the appearance and function of these scars, we can improve the quality of life for these young patients and potentially open up a new avenue of treatment for cancer patients affected with chronic radiation dermatitis, potentially improving their range of motion, cosmesis, and reducing their risk of secondary skin malignancies.

A Novel Explainable AI Method to Assess Associations between Temporal Patterns in Patient Trajectories and Adverse Outcome Risks: Analyzing Fitness as a Risk Factor of ADRD.

We present a novel explainable artificial intelligence (XAI) method to assess the associations between the temporal patterns in the patient trajectories recorded in longitudinal clinical data and the adverse outcome risks, through explanations for a type of deep neural network model called Hybrid Value-Aware Transformer (HVAT) model. The HVAT models can learn jointly from longitudinal and non-longitudinal clinical data, and in particular can leverage the time-varying numerical values associated with the clinical codes or concepts within the longitudinal data for outcome prediction. The key component of the XAI method is the definitions of two derived variables, the temporal mean and the temporal slope, which are defined for the clinical concepts with associated time-varying numerical values. The two variables represent the overall level and the rate of change over time, respectively, in the trajectory formed by the values associated with the clinical concept. Two operations on the original values are designed for changing the values of the two derived variables separately. The effects of the two variables on the outcome risks learned by the HVAT model are calculated in terms of impact scores and impacts. Interpretations of the impact scores and impacts as being similar to those of odds ratios are also provided. We applied the XAI method to the study of cardiorespiratory fitness (CRF) as a risk factor of Alzheimer's disease and related dementias (ADRD). Using a retrospective case-control study design, we found that each one-unit increase in the overall CRF level is associated with a 5% reduction in ADRD risk, while each one-unit increase in the changing rate of CRF over time is associated with a 1% reduction. A closer investigation revealed that the association between the changing rate of CRF level and the ADRD risk is nonlinear, or more specifically, approximately piecewise linear along the axis of the changing rate on two pieces: the piece of negative changing rates and the piece of positive changing rates.

Hybrid Value-Aware Transformer Architecture for Joint Learning from Longitudinal and Non-Longitudinal Clinical Data.

Transformer is the latest deep neural network (DNN) architecture for sequence data learning, which has revolutionized the field of natural language processing. This success has motivated researchers to explore its application in the healthcare domain. Despite the similarities between longitudinal clinical data and natural language data, clinical data presents unique complexities that make adapting Transformer to this domain challenging. To address this issue, we have designed a new Transformer-based DNN architecture, referred to as Hybrid Value-Aware Transformer (HVAT), which can jointly learn from longitudinal and non-longitudinal clinical data. HVAT is unique in the ability to learn from the numerical values associated with clinical codes/concepts such as labs, and in the use of a flexible longitudinal data representation called clinical tokens. We have also trained a prototype HVAT model on a case-control dataset, achieving high performance in predicting Alzheimer's disease and related dementias as the patient outcome. The results demonstrate the potential of HVAT for broader clinical data-learning tasks.

Hybrid Value-Aware Transformer Architecture for Joint Learning from Longitudinal and Non-Longitudinal Clinical Data.

Transformer is the latest deep neural network (DNN) architecture for sequence data learning that has revolutionized the field of natural language processing. This success has motivated researchers to explore its application in the healthcare domain. Despite the similarities between longitudinal clinical data and natural language data, clinical data presents unique complexities that make adapting Transformer to this domain challenging. To address this issue, we have designed a new Transformer-based DNN architecture, referred to as Hybrid Value-Aware Transformer (HVAT), which can jointly learn from longitudinal and non-longitudinal clinical data. HVAT is unique in the ability to learn from the numerical values associated with clinical codes/concepts such as labs, and also the use of a flexible longitudinal data representation called clinical tokens. We trained a prototype HVAT model on a case-control dataset, achieving high performance in predicting Alzheimer’s disease and related dementias as the patient outcome. The result demonstrates the potential of HVAT for broader clinical data learning tasks.

Seroprevalence of canine influenza virus (H3N8) in Iditarod racing sled dogs.

We conducted a cross-sectional convenience sampling study of dogs racing in the 2010 Iditarod to determine the seroprevalence of canine influenza virus (CIV) in the sled dog population. Questionnaires were completed detailing medical and CIV vaccination history, kennel size and location, travel history, and social interactions for each team. A total of 399 dogs were tested for CIV antibodies by hemagglutination inhibition assay. None of these, including 39 samples from dogs reported as CIV vaccinated, were seropositive for CIV antibodies. All of the vaccinated dogs were also negative on virus microneutralization assay. Risk factors for CIV seropositivity could not be determined due to a lack of positive samples. This is the first published study investigating the prevalence of CIV in sled dogs and additional studies are warranted to assess CIV infection among racing sled dogs and to evaluate the ecology of CIV and the vaccine efficacy in this population of dogs.

Séroprévalence du virus de la grippe canine (H3N8) chez les chiens de traîneau de la course Iditarod. Nous avons réalisé une étude par sondage des chiens de la course Iditarod 2010 afin de déterminer la séroprévalence du virus de la grippe canine (VGC) dans la population de chiens de traîneau. Les questionnaires remplis fournissaient des détails complets sur les antécédents médicaux et l'historique de vaccination contre le VGC, la taille du chenil et l'emplacement, l'historique des déplacements et les interactions sociales entre chaque équipe. Un total de 399 chiens a été testé pour les anticorps du VGC par un test d'inhibition de l'hémagglutination. Aucun de ces tests, incluant les 39 échantillons provenant de chiens déclarés comme étant vaccinés contre le VGC, étaient séropositifs pour les anticorps de la VGC. Tous les chiens vaccinés ont aussi eu des résultats négatifs au test de microneutralisation. Les facteurs de risque pour la séropositivité au VGC n'ont pas pu être déterminés en raison d'une absence d'échantillons positifs. Il s'agit de la première étude publiée étudiant la prévalence du VGC chez les chiens de traîneaux et des études additionnelles sont nécessaires pour évaluer l'infection par le VGC chez les chiens de traîneau de course et déterminer l'écologie du VGC et l'efficacité du vaccin chez cette population de chiens.(Traduit par Isabelle Vallières).

Factors influencing the dielectric properties of agricultural and food products.

Dielectric properties of materials are defined, and the major factors that influence these properties of agricultural and food materials, namely, frequency of the applied radiofrequency or microwave electric fields, and water content, temperature, and density of the materials, are discussed on the basis of fundamental concepts. The dependence of measured dielectric properties on these factors is illustrated graphically and discussed for a number of agricultural and food products, including examples of grain, peanuts, fruit, eggs, fresh chicken meat, whey protein gel, and a macaroni and cheese preparation. General observations are provided on the nature of the variation of the dielectric properties with the major variables.

Adverse perinatal outcomes in a large United States birth cohort during the COVID-19 pandemic.

BACKGROUND: The impact of coronavirus disease 2019 (COVID-19) on adverse perinatal outcomes remains unclear. OBJECTIVE: This study aimed to investigate whether COVID-19 is associated with adverse perinatal outcomes in a large national dataset and to examine the rates of adverse outcomes during the pandemic compared with the rates of adverse outcomes during the prepandemic period. STUDY DESIGN: This observational cohort study included 683,905 patients, between the ages of 12 and 50, hospitalized for childbirth and abortion between January 1, 2019, and May 31, 2021. During the prepandemic period, 271,444 women were hospitalized for childbirth. During the pandemic, 308,532 women were hospitalized for childbirth, and 2708 women had COVID-19. The associations between COVID-19 and inhospital adverse perinatal outcomes were examined using propensity score-adjusted logistic regression. RESULTS: Women with COVID-19 were more likely to experience both early and late preterm birth (adjusted odds ratios, 1.38 [95% confidence interval, 1.1-1.7] and 1.62 [95% confidence interval, 1.3-1.7], respectively), preeclampsia (adjusted odds ratio, 1.2 [95% confidence interval, 1.0-1.4]), disseminated intravascular coagulopathy (adjusted odds ratio, 1.57 [95% confidence interval, 1.1-2.2]), pulmonary edema (adjusted odds ratio, 2.7 [95% confidence interval, 1.1-6.3]), and need for mechanical ventilation (adjusted odds ratio, 8.1 [95% confidence interval, 3.8-17.3]) than women without COVID-19. There was no significant difference in the prevalence of stillbirth among women with COVID-19 (16/2708) and women without COVID-19 (174/39,562) (P=.257). There was no difference in adverse outcomes among women who delivered during the pandemic vs prepandemic period. Combined inhospital mortality was significantly higher for women with COVID-19 (147 [95% confidence interval, 3.0-292.0] vs 2.5 [95% confidence interval, 0.0-7.5] deaths per 100,000 women). Women diagnosed with COVID-19 within 30 days before hospitalization were more likely to experience early preterm birth, placental abruption, and mechanical ventilation than women diagnosed with COVID-19 >30 days before hospitalization for childbirth (4.0% vs 2.4% for early preterm birth [adjusted odds ratio, 1.7; 95% confidence interval, 1.1-2.7]; 2.2% vs 1.2% for placental abruption [adjusted odds ratio, 1.86; 95% confidence interval, 1.0-3.4]; and 0.9% vs 0.1% for mechanical ventilation [adjusted odds ratio, 13.7; 95% confidence interval, 1.8-107.2]). CONCLUSION: Women with COVID-19 had a higher prevalence of adverse perinatal outcomes and increased in-hospital mortality, with the highest risk occurring when the diagnosis was within 30 days of hospitalization, raising the possibility of a high-risk period.

Identification of colorectal cancer using structured and free text clinical data.

Colorectal cancer incidence has continually fallen among those 50 years old and over. However, the incidence has increased in those under 50. Even with the recent screening guidelines recommending that screening begins at age 45, nearly half of all early-onset colorectal cancer will be missed. Methods are needed to identify high-risk individuals in this age group for targeted screening. Colorectal cancer studies, as with other clinical studies, have required labor intensive chart review for the identification of those affected and risk factors. Natural language processing and machine learning can be used to automate the process and enable the screening of large numbers of patients. This study developed and compared four machine learning and statistical models: logistic regression, support vector machine, random forest, and deep neural network, in their performance in classifying colorectal cancer patients. Excellent classification performance is achieved with AUCs over 97%.

The microtubule depolymerizing agent CYT997 causes extensive ablation of tumor vasculature in vivo.

The orally active microtubule-disrupting agent (S)-1-ethyl-3-(2-methoxy-4-(5-methyl-4-((1-(pyridin-3-yl)butyl)amino)pyrimidin-2-yl)phenyl)urea (CYT997), reported previously by us (Bioorg Med Chem Lett 19:4639-4642, 2009; Mol Cancer Ther 8:3036-3045, 2009), is potently cytotoxic to a variety of cancer cell lines in vitro and shows antitumor activity in vivo. In addition to its cytotoxic activity, CYT997 possesses antivascular effects on tumor vasculature. To further characterize the vascular disrupting activity of CYT997 in terms of dose and temporal effects, we studied the activity of the compound on endothelial cells in vitro and on tumor blood flow in vivo by using a variety of techniques. In vitro, CYT997 is shown to potently inhibit the proliferation of vascular endothelial growth factor-stimulated human umbilical vein endothelial cells (IC(50) 3.7 ± 1.8 nM) and cause significant morphological changes at 100 nM, including membrane blebbing. Using the method of corrosion casting visualized with scanning electron microscopy, a single dose of CYT997 (7.5 mg/kg i.p.) in a metastatic cancer model was shown to cause destruction of tumor microvasculature in metastatic lesions. Furthermore, repeat dosing of CYT997 at 10 mg/kg and above (intraperitoneally, b.i.d.) was shown to effectively inhibit development of liver metastases. The time and dose dependence of the antivascular effects were studied in a DLD-1 colon adenocarcinoma xenograft model using the fluorescent dye Hoechst 33342. CYT997 demonstrated rapid and dose-dependent vascular shutdown, which persists for more than 24 h after a single oral dose. Together, the data demonstrate that CYT997 possesses potent antivascular activity and support continuing development of this promising compound.

A bottom-up approach to creating an ontology for medication indications.

OBJECTIVES: The study sought to learn if it were possible to develop an ontology that would allow the Food and Drug Administration approved indications to be expressed in a manner computable and comparable to what is expressed in an electronic health record. MATERIALS AND METHODS: A random sample of 1177 of the 3000+ extant, distinct medical products (identified by unique new drug application numbers) was selected for investigation. Close manual examination of the indication portion of the labels for these drugs led to the development of a formal model of indications. RESULTS: The model represents each narrative indication as a disjunct of conjuncts of assertions about an individual. A desirable attribute is that each assertion about an individual should be testable without reference to other contextual information about the situation. The logical primitives are chosen from 2 categories (context and conditions) and are linked to an enumeration of uses, such as prevention. We found that more than 99% of approved label indications for treatment or prevention could be so represented. DISCUSSION: While some indications are straightforward to represent, difficulties stem from the need to represent temporal or sequential references. In addition, there is a mismatch of terminologies between what is present in an electronic health record and in the label narrative. CONCLUSIONS: A workable model for formalizing drug indications is possible. Remaining challenges include designing workflow to model narrative label indications for all approved drug products and incorporation of standard vocabularies.

A model-agnostic approach for understanding heart failure risk factors.

OBJECTIVE: Understanding the risk factors for developing heart failure among patients with type 2 diabetes can contribute to preventing deterioration of quality of life for those persons. Electronic health records (EHR) provide an opportunity to use sophisticated machine learning models to understand and compare the effect of different risk factors for developing HF. As the complexity of the model increases, however, the transparency of the model often decreases. To interpret the results, we aimed to develop a model-agnostic approach to shed light on complex models and interpret the effect of features on developing heart failure. Using the HealthFacts EHR database of the Cerner EHR, we extracted the records of 723 patients with at least 6 yeas of follow up of type 2 diabetes, of whom 134 developed heart failure. Using age and comorbidities as features and heart failure as the outcome, we trained logistic regression, random forest, XGBoost, neural network, and then applied our proposed approach to rank the effect of each factor on developing heart failure. RESULTS: Compared to the "importance score" built-in function of XGBoost, our proposed approach was more accurate in ranking the effect of the different risk factors on developing heart failure.

Using multivariate long short-term memory neural network to detect aberrant signals in health data for quality assurance.

BACKGROUND: The data quality of electronic health records (EHR) has been a topic of increasing interest to clinical and health services researchers. One indicator of possible errors in data is a large change in the frequency of observations in chronic illnesses. In this study, we built and demonstrated the utility of a stacked multivariate LSTM model to predict an acceptable range for the frequency of observations. METHODS: We applied the LSTM approach to a large EHR dataset with over 400 million total encounters. We computed sensitivity and specificity for predicting if the frequency of an observation in a given week is an aberrant signal. RESULTS: Compared with the simple frequency monitoring approach, our proposed multivariate LSTM approach increased the sensitivity of finding aberrant signals in 6 randomly selected diagnostic codes from 75 to 88% and the specificity from 68 to 91%. We also experimented with two different LSTM algorithms, namely, direct multi-step and recursive multi-step. Both models were able to detect the aberrant signals while the recursive multi-step algorithm performed better. CONCLUSIONS: Simply monitoring the frequency trend, as is the common practice in systems that do monitor the data quality, would not be able to distinguish between the fluctuations caused by seasonal disease changes, seasonal patient visits, or a change in data sources. Our study demonstrated the ability of stacked multivariate LSTM models to recognize true data quality issues rather than fluctuations that are caused by different reasons, including seasonal changes and outbreaks.

Understanding Demographic Risk Factors for Adverse Outcomes in COVID-19 Patients: Explanation of a Deep Learning Model.

This study was to understand the impacts of three key demographic variables, age, gender, and race, on the adverse outcome of all-cause hospitalization or all-cause mortality in patients with COVID-19, using a deep neural network (DNN) analysis. We created a cohort of Veterans who were tested positive for COVID-19, extracted data on age, gender, and race, and clinical characteristics from their electronic health records, and trained a DNN model for predicting the adverse outcome. Then, we analyzed the association of the demographic variables with the risks of the adverse outcome using the impact scores and interaction scores for explaining DNN models. The results showed that, on average, older age and African American race were associated with higher risks while female gender was associated with lower risks. However, individual-level impact scores of age showed that age was a more impactful risk factor in younger patients and in older patients with fewer comorbidities. The individual-level impact scores of gender and race variables had a wide span covering both positive and negative values. The interaction scores between the demographic variables showed that the interaction effects were minimal compared to the impact scores associated with them. In conclusion, the DNN model is able to capture the non-linear relationship between the risk factors and the adverse outcome, and the impact scores and interaction scores can help explain the complicated non-linear effects between the demographic variables and the risk of the outcome.