A large-scale comparison of two voice synthesis techniques on intelligibility, naturalness, preferences, and attitudes toward voices banked by individuals with amyotrophic lateral sclerosis.

Amyotrophic lateral sclerosis (ALS) commonly results in the inability to produce natural speech, making speech-generating devices (SGDs) important. Historically, synthetic voices generated by SGDs were neither unique, nor age- or dialect-appropriate, which depersonalized SGD use. Voices generated by SGDs can now be customized via voice banking and should ideally sound uniquely like the individual's natural speech, be intelligible, and elicit positive reactions from communication partners. This large-scale 2 x 2 mixed between- and within-participants design examined perceptions of 831 adult listeners regarding custom synthetic voices created for two individuals diagnosed with ALS via two synthesis systems in common clinical use (waveform concatenation and statistical parametric synthesis). The study explored relationships among synthesis system, dysarthria severity, synthetic speech intelligibility, naturalness, and preferences, and also provided a preliminary examination of attitudes regarding the custom synthetic voices. Synthetic voices generated via statistical parametric synthesis trained on deep neural networks were more intelligible, natural, and preferred than voices produced via waveform concatenation, and were associated with more positive attitudes. The custom synthetic voice created from moderately dysarthric speech was more intelligible than the voice created from mildly dysarthric speech. Clinical implications and factors that may have contributed to the relative intelligibilities are discussed.

Voice banking to support individuals who use speech-generating devices: development and evaluation of Singaporean-accented English synthetic voices and a Singapore Colloquial English recording inventory.

Voice banking involves recording an inventory of sentences produced via natural speech. The recordings are used to create a synthetic text-to-speech voice that can be installed on speech-generating devices. This study highlights a minimally researched, clinically relevant issue surrounding the development and evaluation of Singaporean-accented English synthetic voices that were created using readily available voice banking software and hardware. Processes used to create seven unique synthetic voices that produce Singaporean-accented English, and the development of a custom Singaporean Colloquial English (SCE) recording inventory, are reviewed. The perspectives of adults who spoke SCE and banked their voices for this project are summarized and were generally positive. Finally, 100 adults familiar with SCE participated in an experiment that evaluated the intelligibility and naturalness of the Singaporean-accented synthetic voices, as well as the effect of the SCE custom inventory on listener preferences. The addition of the custom SCE inventory did not affect intelligibility or naturalness of the synthetic speech, and listeners tended to prefer the voice created with the SCE inventory when the stimulus was an SCE passage. The procedures used in this project may be helpful for interventionists who wish to create synthetic voices with accents that are not commercially available.

Online patient portal use by caregivers in pediatric oncology: Are we widening sociodemographic disparities?

BACKGROUND: Financial and regulatory incentives have encouraged and increased the availability of online patient portals that provide caregivers access to their child's electronic health records (EHR). Such access is believed to promote better engagement and outcomes of care. Little is known about the use of portals by caregivers of children with cancer. This study sought to examine whether sociodemographic and clinical care variables are associated with portal activation in a pediatric oncology sample. METHODS: Sociodemographic and clinical characteristics were extracted from the EHR of pediatric oncology patients treated for their first cancer in the Nemours Center for Cancer and Blood Disorders between 2012 and 2017. A Child Opportunity Index (COI) was calculated based on home zip code. Characteristics of children whose caregivers did and did not activate the portal were compared. RESULTS: Sixty-six percent of caregivers activated a portal account with a peak within 90 days of diagnosis. In logistic regression, caregivers with a younger aged child, spoke English, lived closer to the hospital, lived in higher COI area, with longer treatment length, and more radiology tests had greater odds of portal activation. Those with private health insurance or White race were overrepresented among those who activated an account in univariate analysis. CONCLUSION: The majority of caregivers of children with cancer activate portal accounts; however, differences in sociodemographic and clinical variables across those who did and did not activate accounts emerged. As portals become ubiquitous, we must understand how they are used and mitigate widening inequities caused by disparate portal use.

A cognitive approach for design of a multimedia informed consent video and website in pediatric research.

OBJECTIVE: Poor participant comprehension of research procedures following the conventional face-to-face consent process for biomedical research is common. We describe the development of a multimedia informed consent video and website that incorporates cognitive strategies to enhance comprehension of study related material directed to parents and adolescents. MATERIALS AND METHODS: A multidisciplinary team was assembled for development of the video and website that included human subjects professionals; psychologist researchers; institutional video and web developers; bioinformaticians and programmers; and parent and adolescent stakeholders. Five learning strategies that included Sensory-Modality view, Coherence, Signaling, Redundancy, and Personalization were integrated into a 15-min video and website material that describes a clinical research trial. RESULTS: A diverse team collaborated extensively over 15months to design and build a multimedia platform for obtaining parental permission and adolescent assent for participant in as asthma clinical trial. Examples of the learning principles included, having a narrator describe what was being viewed on the video (sensory-modality); eliminating unnecessary text and graphics (coherence); having the initial portion of the video explain the sections of the video to be viewed (signaling); avoiding simultaneous presentation of text and graphics (redundancy); and having a consistent narrator throughout the video (personalization). DISCUSSION: Existing conventional and multimedia processes for obtaining research informed consent have not actively incorporated basic principles of human cognition and learning in the design and implementation of these processes. The present paper illustrates how this can be achieved, setting the stage for rigorous evaluation of potential benefits such as improved comprehension, satisfaction with the consent process, and completion of research objectives. CONCLUSION: New consent strategies that have an integrated cognitive approach need to be developed and tested in controlled trials.

Towards personalized speech synthesis for augmentative and alternative communication.

Text-to-speech options on augmentative and alternative communication (AAC) devices are limited. Often, several individuals in a group setting use the same synthetic voice. This lack of customization may limit technology adoption and social integration. This paper describes our efforts to generate personalized synthesis for users with profoundly limited speech motor control. Existing voice banking and voice conversion techniques rely on recordings of clearly articulated speech from the target talker, which cannot be obtained from this population. Our VocaliD approach extracts prosodic properties from the target talker's source function and applies these features to a surrogate talker's database, generating a synthetic voice with the vocal identity of the target talker and the clarity of the surrogate talker. Promising intelligibility results suggest areas of further development for improved personalization.

Bilateral Buccal Flap Revision Palatoplasty to Correct Velopharyngeal Dysfunction: Perceptual Speech, Acoustic, and Aerodynamic Outcomes.

BACKGROUND: The purpose of this study was to analyze perceptual, acoustic, and aerodynamic changes in speech and velopharyngeal function after bilateral buccal flap revision palatoplasty (BBFRP) in patients with repaired cleft palate. METHODS: Ten consecutive patients ages 4 to 18 years with velopharyngeal dysfunction treated with BBFRP by a single surgeon were evaluated. Using a visual analog scale, nine blinded speech-language pathologists independently rated hypernasality, hyponasality, audible nasal emission, and speech acceptability. Measurements of the acoustic speech signal were used to quantify changes in hypernasality and nasal emission. The pressure flow technique was used to determine changes in velopharyngeal gap size. RESULTS: Complete records were available for eight patients. After surgery, hypernasality decreased ( P < 0.001) and speech acceptability increased ( P < 0.001) significantly. Audible nasal emission was significantly reduced ( P < 0.001). Postoperative acoustic measures showed a reduction of nasal emission and nasalization. Velopharyngeal gap size significantly decreased after BBFRP ( P < 0.001), correlating with lower visual analog scale ratings of hypernasality ( P = 0.015). Hyponasality did not change significantly after surgery ( P = 0.964). No patient developed sleep-disordered breathing. CONCLUSION: BBFRP resulted in a measurable improvement in hypernasal speech, audible nasal emission, and speech acceptability without significant changes in hyponasality or risk of obstructive sleep apnea. CLINICAL QUESTION/LEVEL OF EVIDENCE: Therapeutic, IV.

Associations between COVID-19 therapies and outcomes in rural and urban America: A multisite, temporal analysis from the Alpha to Omicron SARS-CoV-2 variants.

PURPOSE: To investigate the enduring disparities in adverse COVID-19 events between urban and rural communities in the United States, focusing on the effects of SARS-CoV-2 vaccination and therapeutic advances on patient outcomes. METHODS: Using National COVID Cohort Collaborative (N3C) data from 2021 to 2023, this retrospective cohort study examined COVID-19 hospitalization, inpatient death, and other adverse events. Populations were categorized into urban, urban-adjacent rural (UAR), and nonurban-adjacent rural (NAR). Adjustments included demographics, variant-dominant waves, comorbidities, region, and SARS-CoV-2 treatment and vaccination. Statistical methods included Kaplan-Meier survival estimates, multivariable logistic, and Cox regression. FINDINGS: The study included 3,018,646 patients, with rural residents constituting 506,204. These rural dwellers were older, had more comorbidities, and were less vaccinated than their urban counterparts. Adjusted analyses revealed higher hospitalization odds in UAR and NAR (aOR 1.07 [1.05-1.08] and 1.06 [1.03-1.08]), greater inpatient death hazard (aHR 1.30 [1.26-1.35] UAR and 1.37 [1.30-1.45] NAR), and greater risk of other adverse events compared to urban dwellers. Delta increased, while Omicron decreased, inpatient adverse events relative to pre-Delta, with rural disparities persisting throughout. Treatment effectiveness and vaccination were similarly protective across all cohorts, but dexamethasone post-ventilation was effective only in urban areas. Nirmatrelvir/ritonavir and molnupiravir better protected rural residents against hospitalization. CONCLUSIONS: Despite advancements in treatment and vaccinations, disparities in adverse COVID-19 outcomes persist between urban and rural communities. The effectiveness of some therapeutic agents appears to vary based on rurality, suggesting a nuanced relationship between treatment and geographic location while highlighting the need for targeted rural health care strategies.

Systematic data quality assessment of electronic health record data to evaluate study-specific fitness: Report from the PRESERVE research study.

Study-specific data quality testing is an essential part of minimizing analytic errors, particularly for studies making secondary use of clinical data. We applied a systematic and reproducible approach for study-specific data quality testing to the analysis plan for PRESERVE, a 15-site, EHR-based observational study of chronic kidney disease in children. This approach integrated widely adopted data quality concepts with healthcare-specific evaluation methods. We implemented two rounds of data quality assessment. The first produced high-level evaluation using aggregate results from a distributed query, focused on cohort identification and main analytic requirements. The second focused on extended testing of row-level data centralized for analysis. We systematized reporting and cataloguing of data quality issues, providing institutional teams with prioritized issues for resolution. We tracked improvements and documented anomalous data for consideration during analyses. The checks we developed identified 115 and 157 data quality issues in the two rounds, involving completeness, data model conformance, cross-variable concordance, consistency, and plausibility, extending traditional data quality approaches to address more complex stratification and temporal patterns. Resolution efforts focused on higher priority issues, given finite study resources. In many cases, institutional teams were able to correct data extraction errors or obtain additional data, avoiding exclusion of 2 institutions entirely and resolving 123 other gaps. Other results identified complexities in measures of kidney function, bearing on the study's outcome definition. Where limitations such as these are intrinsic to clinical data, the study team must account for them in conducting analyses. This study rigorously evaluated fitness of data for intended use. The framework is reusable and built on a strong theoretical underpinning. Significant data quality issues that would have otherwise delayed analyses or made data unusable were addressed. This study highlights the need for teams combining subject-matter and informatics expertise to address data quality when working with real world data.

Postacute Sequelae of SARS-CoV-2 in Children.

The coronavirus disease 2019 (COVID-19) pandemic has caused significant medical, social, and economic impacts globally, both in the short and long term. Although most individuals recover within a few days or weeks from an acute infection, some experience longer lasting effects. Data regarding the postacute sequelae of severe acute respiratory syndrome coronavirus 2 infection (PASC) in children, or long COVID, are only just emerging in the literature. These symptoms and conditions may reflect persistent symptoms from acute infection (eg, cough, headaches, fatigue, and loss of taste and smell), new symptoms like dizziness, or exacerbation of underlying conditions. Children may develop conditions de novo, including postural orthostatic tachycardia syndrome, myalgic encephalomyelitis/chronic fatigue syndrome, autoimmune conditions and multisystem inflammatory syndrome in children. This state-of-the-art narrative review provides a summary of our current knowledge about PASC in children, including prevalence, epidemiology, risk factors, clinical characteristics, underlying mechanisms, and functional outcomes, as well as a conceptual framework for PASC based on the current National Institutes of Health definition. We highlight the pediatric components of the National Institutes of Health-funded Researching COVID to Enhance Recovery Initiative, which seeks to characterize the natural history, mechanisms, and long-term health effects of PASC in children and young adults to inform future treatment and prevention efforts. These initiatives include electronic health record cohorts, which offer rapid assessments at scale with geographical and demographic diversity, as well as longitudinal prospective observational cohorts, to estimate disease burden, illness trajectory, pathobiology, and clinical manifestations and outcomes.

Vaccine Effectiveness Against Long COVID in Children.

OBJECTIVES: Vaccination reduces the risk of acute coronavirus disease 2019 (COVID-19) in children, but it is less clear whether it protects against long COVID. We estimated vaccine effectiveness (VE) against long COVID in children aged 5 to 17 years. METHODS: This retrospective cohort study used data from 17 health systems in the RECOVER PCORnet electronic health record program for visits after vaccine availability. We examined both probable (symptom-based) and diagnosed long COVID after vaccination. RESULTS: The vaccination rate was 67% in the cohort of 1 037 936 children. The incidence of probable long COVID was 4.5% among patients with COVID-19, whereas diagnosed long COVID was 0.8%. Adjusted vaccine effectiveness within 12 months was 35.4% (95 CI 24.5-44.7) against probable long COVID and 41.7% (15.0-60.0) against diagnosed long COVID. VE was higher for adolescents (50.3% [36.6-61.0]) than children aged 5 to 11 (23.8% [4.9-39.0]). VE was higher at 6 months (61.4% [51.0-69.6]) but decreased to 10.6% (-26.8% to 37.0%) at 18-months. CONCLUSIONS: This large retrospective study shows moderate protective effect of severe acute respiratory coronavirus 2 vaccination against long COVID. The effect is stronger in adolescents, who have higher risk of long COVID, and wanes over time. Understanding VE mechanism against long COVID requires more study, including electronic health record sources and prospective data.

Using automatic alignment to analyze endangered language data: testing the viability of untrained alignment.

While efforts to document endangered languages have steadily increased, the phonetic analysis of endangered language data remains a challenge. The transcription of large documentation corpora is, by itself, a tremendous feat. Yet, the process of segmentation remains a bottleneck for research with data of this kind. This paper examines whether a speech processing tool, forced alignment, can facilitate the segmentation task for small data sets, even when the target language differs from the training language. The authors also examined whether a phone set with contextualization outperforms a more general one. The accuracy of two forced aligners trained on English (hmalign and p2fa) was assessed using corpus data from Yoloxóchitl Mixtec. Overall, agreement performance was relatively good, with accuracy at 70.9% within 30 ms for hmalign and 65.7% within 30 ms for p2fa. Segmental and tonal categories influenced accuracy as well. For instance, additional stop allophones in hmalign's phone set aided alignment accuracy. Agreement differences between aligners also corresponded closely with the types of data on which the aligners were trained. Overall, using existing alignment systems was found to have potential for making phonetic analysis of small corpora more efficient, with more allophonic phone sets providing better agreement than general ones.

Associations of longitudinal BMI percentile classification patterns in early childhood with neighborhood-level social determinants of health.

Background: Understanding social determinants of health (SDOH) that may be risk factors for childhood obesity is important to developing targeted interventions to prevent obesity. Prior studies have examined these risk factors, mostly examining obesity as a static outcome variable. Objectives: This study aimed to identify distinct subpopulations based on BMI percentile classification or changes in BMI percentile classifications over time and explore these longitudinal associations with neighborhood-level SDOH factors in children from 0 to 7 years of age. Methods: Using Latent Class Growth (Mixture) Modelling (LCGMM) we identify distinct BMI% classification groups in children from 0 to 7 years of age. We used multinomial logistic regression to study associations between SDOH factors with each BMI% classification group. Results: From the study cohort of 36,910 children, five distinct BMI% classification groups emerged: always having obesity (n=429; 1.16%), overweight most of the time (n=15,006; 40.65%), increasing BMI% (n=9,060; 24.54%), decreasing BMI% (n=5,058; 13.70%), and always normal weight (n=7,357; 19.89%). Compared to children in the decreasing BMI% and always normal weight groups, children in the other three groups were more likely to live in neighborhoods with higher rates of poverty, unemployment, crowded households, and single-parent households, and lower rates of preschool enrollment. Conclusions: Neighborhood-level SDOH factors have significant associations with children's BMI% classification and changes in classification over time. This highlights the need to develop tailored obesity interventions for different groups to address the barriers faced by communities that can impact the weight and health of the children living within them.

Comprehension by Caregivers and Adolescents of Clinical Trial Information Delivered via Multimedia Video Versus Conventional Practice: Nonrandomized Controlled Trial.

BACKGROUND: Research participants often misunderstand the required elements of informed consent information, whether provided in written or oral format. Informed consent instruments with embedded evidence-based learning theory principles administered in multimedia electronic formats may improve comprehension and retention. OBJECTIVE: This study aims to determine whether study information comprehension and retention using an interactive multimedia video consent process was noninferior to comprehension and retention after an in-person face-to-face interaction with a conventional written consent document for caregivers and adolescents enrolled in a clinical trial. METHODS: Participants were caregivers and children aged 12 to 17 years who were enrolled in a clinical trial of asthma treatment. Consent information was presented as a multimedia web-based video consent interaction or as a conventional written consent document with in-person interaction between the prospective participants and the study staff. The trial used a parallel nonrandomized noninferiority design that compared the 2 consent methods. Caregivers and adolescents completed a 17-item open-ended comprehension questionnaire (score range 17-51) at enrollment and at the end of the study 20 weeks later. Comprehension and retention were compared between the consent formats. Noninferiority was established if the 95% CI upper bound of the difference in scores (conventional format minus web-based) was less than the noninferiority margin of 2.4; superiority was established if the upper bound of the CI was <0. RESULTS: In total, 54 caregiver and adolescent dyads completed the interactive multimedia web-based video consent, and 25 dyads completed the conventional consent. Overall, 33% (26/79) of all adolescents were Black, 57% (45/79) were male, and 61% (48/79) had a household income of

Assessing the effects of therapeutic combinations on SARS-CoV-2 infected patient outcomes: A big data approach.

BACKGROUND: The COVID-19 pandemic has demonstrated the need for efficient and comprehensive, simultaneous assessment of multiple combined novel therapies for viral infection across the range of illness severity. Randomized Controlled Trials (RCT) are the gold standard by which efficacy of therapeutic agents is demonstrated. However, they rarely are designed to assess treatment combinations across all relevant subgroups. A big data approach to analyzing real-world impacts of therapies may confirm or supplement RCT evidence to further assess effectiveness of therapeutic options for rapidly evolving diseases such as COVID-19. METHODS: Gradient Boosted Decision Tree, Deep and Convolutional Neural Network classifiers were implemented and trained on the National COVID Cohort Collaborative (N3C) data repository to predict the patients' outcome of death or discharge. Models leveraged the patients' characteristics, the severity of COVID-19 at diagnosis, and the calculated proportion of days on different treatment combinations after diagnosis as features to predict the outcome. Then, the most accurate model is utilized by eXplainable Artificial Intelligence (XAI) algorithms to provide insights about the learned treatment combination impacts on the model's final outcome prediction. RESULTS: Gradient Boosted Decision Tree classifiers present the highest prediction accuracy in identifying patient outcomes with area under the receiver operator characteristic curve of 0.90 and accuracy of 0.81 for the outcomes of death or sufficient improvement to be discharged. The resulting model predicts the treatment combinations of anticoagulants and steroids are associated with the highest probability of improvement, followed by combined anticoagulants and targeted antivirals. In contrast, monotherapies of single drugs, including use of anticoagulants without steroid or antivirals are associated with poorer outcomes. CONCLUSIONS: This machine learning model by accurately predicting the mortality provides insights about the treatment combinations associated with clinical improvement in COVID-19 patients. Analysis of the model's components suggests benefit to treatment with combination of steroids, antivirals, and anticoagulant medication. The approach also provides a framework for simultaneously evaluating multiple real-world therapeutic combinations in future research studies.

Community risks for SARS-CoV-2 infection among fully vaccinated US adults by rurality: A retrospective cohort study from the National COVID Cohort Collaborative.

BACKGROUND: While COVID-19 vaccines reduce adverse outcomes, post-vaccination SARS-CoV-2 infection remains problematic. We sought to identify community factors impacting risk for breakthrough infections (BTI) among fully vaccinated persons by rurality. METHODS: We conducted a retrospective cohort study of US adults sampled between January 1 and December 20, 2021, from the National COVID Cohort Collaborative (N3C). Using Kaplan-Meier and Cox-Proportional Hazards models adjusted for demographic differences and comorbid conditions, we assessed impact of rurality, county vaccine hesitancy, and county vaccination rates on risk of BTI over 180 days following two mRNA COVID-19 vaccinations between January 1 and September 21, 2021. Additionally, Cox Proportional Hazards models assessed the risk of infection among adults without documented vaccinations. We secondarily assessed the odds of hospitalization and adverse COVID-19 events based on vaccination status using multivariable logistic regression during the study period. RESULTS: Our study population included 566,128 vaccinated and 1,724,546 adults without documented vaccination. Among vaccinated persons, rurality was associated with an increased risk of BTI (adjusted hazard ratio [aHR] 1.53, 95% confidence interval [CI] 1.42-1.64, for urban-adjacent rural and 1.65, 1.42-1.91, for nonurban-adjacent rural) compared to urban dwellers. Compared to low vaccine-hesitant counties, higher risks of BTI were associated with medium (1.07, 1.02-1.12) and high (1.33, 1.23-1.43) vaccine-hesitant counties. Compared to counties with high vaccination rates, a higher risk of BTI was associated with dwelling in counties with low vaccination rates (1.34, 1.27-1.43) but not medium vaccination rates (1.00, 0.95-1.07). Community factors were also associated with higher odds of SARS-CoV-2 infection among persons without a documented vaccination. Vaccinated persons with SARS-CoV-2 infection during the study period had significantly lower odds of hospitalization and adverse events across all geographic areas and community exposures. CONCLUSIONS: Our findings suggest that community factors are associated with an increased risk of BTI, particularly in rural areas and counties with high vaccine hesitancy. Communities, such as those in rural and disproportionately vaccine hesitant areas, and certain groups at high risk for adverse breakthrough events, including immunosuppressed/compromised persons, should continue to receive public health focus, targeted interventions, and consistent guidance to help manage community spread as vaccination protection wanes.

Vaccine Effectiveness Against Long COVID in Children: A Report from the RECOVER EHR Cohort.

Objective: Vaccination reduces the risk of acute COVID-19 in children, but it is less clear whether it protects against long COVID. We estimated vaccine effectiveness (VE) against long COVID in children aged 5-17 years. Methods: This retrospective cohort study used data from 17 health systems in the RECOVER PCORnet electronic health record (EHR) Program for visits between vaccine availability, and October 29, 2022. Conditional logistic regression was used to estimate VE against long COVID with matching on age group (5-11, 12-17) and time period and adjustment for sex, ethnicity, health system, comorbidity burden, and pre-exposure health care utilization. We examined both probable (symptom-based) and diagnosed long COVID in the year following vaccination. Results: The vaccination rate was 56% in the cohort of 1,037,936 children. The incidence of probable long COVID was 4.5% among patients with COVID-19, while diagnosed long COVID was 0.7%. Adjusted vaccine effectiveness within 12 months was 35.4% (95 CI 24.5 - 44.5) against probable long COVID and 41.7% (15.0 - 60.0) against diagnosed long COVID. VE was higher for adolescents 50.3% [36.3 - 61.0]) than children aged 5-11 (23.8% [4.9 - 39.0]). VE was higher at 6 months (61.4% [51.0 - 69.6]) but decreased to 10.6% (-26.8 - 37.0%) at 18-months. Discussion: This large retrospective study shows a moderate protective effect of SARS-CoV-2 vaccination against long COVID. The effect is stronger in adolescents, who have higher risk of long COVID, and wanes over time. Understanding VE mechanism against long COVID requires more study, including EHR sources and prospective data. Article Summary: Vaccination against COVID-19 has a protective effect against long COVID in children and adolescents. The effect wanes over time but remains significant at 12 months. What's Known on This Subject: Vaccines reduce the risk and severity of COVID-19 in children. There is evidence for reduced long COVID risk in adults who are vaccinated, but little information about similar effects for children and adolescents, who have distinct forms of long COVID. What This Study Adds: Using electronic health records from US health systems, we examined large cohorts of vaccinated and unvaccinated patients <18 years old and show that vaccination against COVID-19 is associated with reduced risk of long COVID for at least 12 months. Contributors' Statement: Drs. Hanieh Razzaghi and Charles Bailey conceptualized and designed the study, supervised analyses, drafted the initial manuscript, and critically reviewed and revised the manuscript.Drs. Christopher Forrest and Yong Chen designed the study and critically reviewed and revised the manuscript.Ms. Kathryn Hirabayashi, Ms. Andrea Allen, and Dr. Qiong Wu conducted analyses, and critically reviewed and revised the manuscript.Drs. Suchitra Rao, H Timothy Bunnell, Elizabeth A. Chrischilles, Lindsay G. Cowell, Mollie R. Cummins, David A. Hanauer, Benjamin D. Horne, Carol R. Horowitz, Ravi Jhaveri, Susan Kim, Aaron Mishkin, Jennifer A. Muszynski, Susanna Nagie, Nathan M. Pajor, Anuradha Paranjape, Hayden T. Schwenk, Marion R. Sills, Yacob G. Tedla, David A. Williams, and Ms. Miranda Higginbotham critically reviewed and revised the manuscript.All authors approved the final manuscript as submitted and agree to be accountable for all aspects of the work. Authorship statement: Authorship has been determined according to ICMJE recommendations.

Obesity Prediction with EHR Data: A deep learning approach with interpretable elements.

Childhood obesity is a major public health challenge. Early prediction and identification of the children at an elevated risk of developing childhood obesity may help in engaging earlier and more effective interventions to prevent and manage obesity. Most existing predictive tools for childhood obesity primarily rely on traditional regression-type methods using only a few hand-picked features and without exploiting longitudinal patterns of children's data. Deep learning methods allow the use of high-dimensional longitudinal datasets. In this paper, we present a deep learning model designed for predicting future obesity patterns from generally available items on children's medical history. To do this, we use a large unaugmented electronic health records dataset from a large pediatric health system in the US. We adopt a general LSTM network architecture and train our proposed model using both static and dynamic EHR data. To add interpretability, we have additionally included an attention layer to calculate the attention scores for the timestamps and rank features of each timestamp. Our model is used to predict obesity for ages between 3-20 years using the data from 1-3 years in advance. We compare the performance of our LSTM model with a series of existing studies in the literature and show it outperforms their performance in most age ranges.

Predicting Attrition Patterns from Pediatric Weight Management Programs.

Obesity is a major public health concern. Multidisciplinary pediatric weight management programs are considered standard treatment for children with obesity who are not able to be successfully managed in the primary care setting. Despite their great potential, high dropout rates (referred to as attrition) are a major hurdle in delivering successful interventions. Predicting attrition patterns can help providers reduce the alarmingly high rates of attrition (up to 80%) by engaging in earlier and more personalized interventions. Previous work has mainly focused on finding static predictors of attrition on smaller datasets and has achieved limited success in effective prediction. In this study, we have collected a five-year comprehensive dataset of 4,550 children from diverse backgrounds receiving treatment at four pediatric weight management programs in the US. We then developed a machine learning pipeline to predict (a) the likelihood of attrition, and (b) the change in body-mass index (BMI) percentile of children, at different time points after joining the weight management program. Our pipeline is greatly customized for this problem using advanced machine learning techniques to process longitudinal data, smaller-size data, and interrelated prediction tasks. The proposed method showed strong prediction performance as measured by AUROC scores (average AUROC of 0.77 for predicting attrition, and 0.78 for predicting weight outcomes).

Flexible-Window Predictions on Electronic Health Records.

Various types of machine learning techniques are available for analyzing electronic health records (EHRs). For predictive tasks, most existing methods either explicitly or implicitly divide these time-series datasets into predetermined observation and prediction windows. Patients have different lengths of medical history and the desired predictions (for purposes such as diagnosis or treatment) are required at different times in the future. In this paper, we propose a method that uses a sequence-to-sequence generator model to transfer an input sequence of EHR data to a sequence of user-defined target labels, providing the end-users with "flexible" observation and prediction windows to define. We use adversarial and semi-supervised approaches in our design, where the sequence-to-sequence model acts as a generator and a discriminator distinguishes between the actual (observed) and generated labels. We evaluate our models through an extensive series of experiments using two large EHR datasets from adult and pediatric populations. In an obesity predicting case study, we show that our model can achieve superior results in flexible-window prediction tasks, after being trained once and even with large missing rates on the input EHR data. Moreover, using a number of attention analysis experiments, we show that the proposed model can effectively learn more relevant features in different prediction tasks.

An ordinal severity scale for COVID-19 retrospective studies using Electronic Health Record data.

Objectives: Although the World Health Organization (WHO) Clinical Progression Scale for COVID-19 is useful in prospective clinical trials, it cannot be effectively used with retrospective Electronic Health Record (EHR) datasets. Modifying the existing WHO Clinical Progression Scale, we developed an ordinal severity scale (OS) and assessed its usefulness in the analyses of COVID-19 patient outcomes using retrospective EHR data. Materials and Methods: An OS was developed to assign COVID-19 disease severity using the Observational Medical Outcomes Partnership common data model within the National COVID Cohort Collaborative (N3C) data enclave. We then evaluated usefulness of the developed OS using heterogenous EHR data from January 2020 to October 2021 submitted to N3C by 63 healthcare organizations across the United States. Principal component analysis (PCA) was employed to characterize changes in disease severity among patients during the 28-day period following COVID-19 diagnosis. Results: The data set used in this analysis consists of 2 880 456 patients. PCA of the day-to-day variation in OS levels over the totality of the 28-day period revealed contrasting patterns of variation in disease severity within the first and second 14 days and illustrated the importance of evaluation over the full 28-day period. Discussion: An OS with well-defined, robust features, based on discrete EHR data elements, is useful for assessments of COVID-19 patient outcomes, providing insights on the progression of COVID-19 disease severity over time. Conclusions: The OS provides a framework that can facilitate better understanding of the course of acute COVID-19, informing clinical decision-making and resource allocation.