Timing and co-occurrence of symptoms prior to a diagnosis of light chain (AL) amyloidosis.

It is well-established that most patients with systemic light chain (AL) amyloidosis have multi-organ involvement and are often diagnosed after a lag period of increasing symptoms. We leverage electronic health record (EHR) data from the TriNetX research network to describe the incidence, timing, and co-occurrence of precursor conditions of interests in a cohort of AL amyloidosis patients identified between October 2015-December 2020. Nineteen precursor diagnoses of interest representing features of AL amyloidosis were identified using ICD codes up to 36 months prior to AL amyloidosis diagnosis. Among 1,401 patients with at least 36 months of EHR data prior to AL amyloidosis diagnosis, 46% were females, 16% were non-Hispanic Black, and 6% were Hispanic. The median age was 71 (range, 21-91) years. The median number of precursor diagnoses was 5 with dyspnea and fatigue being the most prevalent. The time from the first occurrence of a precursor to AL diagnosis ranged from 3.2 to 21.4 months. Analyses of pairwise co-occurrence of specific diagnoses indicated a high association (Cole's coefficient >0.6) among the examined precursor diagnoses. These findings provide novel information about the timing and co-occurrence of key precursor conditions and could be used to develop algorithms for early identification of AL amyloidosis.

Acute care utilization among individuals with sickle cell disease and related cardiopulmonary and renal complications.

Cardiopulmonary and renal end organ (CPR) complications are associated with early mortality among individuals with sickle cell disease (SCD). However, there is limited knowledge regarding acute care utilization for individuals with SCD and CPR complications. Our objective was to determine the prevalence of CPR complications in a state specific SCD population and compare acute care utilization among individuals with and without CPR complications. We leveraged 2017-2020 data for individuals with SCD identified by the Sickle Cell Data Collection program in Wisconsin. The prevalence of CPR complications is determined for distinct age groups. Generalized linear models adjusted for age compared the rate of acute care visits/person/year among individuals who had cardiopulmonary only, renal only, both cardiopulmonary and renal, or no CPR complications. There were 1378 individuals with SCD, 52% females, mean (SD) age 28.3 (18.5) years; 48% had at least one CPR complication during the study period. The prevalence of CPR complications was higher in adults (69%) compared to pediatric (15%) and transition (51%) groups. Individuals with SCD and cardiopulmonary complications had higher acute visit rates than those without CPR complications (5.4 (IQR 5.0-5.8) vs 2.4 (IQR 2.1-2.5), p <0.001)). Acute care visit rates were similar between individuals with SCD who had renal only complications and no CPR complications (2.7 (IQR 2.5-3.0) vs 2.4 (2.1-2.5), p = 0.24). The high acute care visit rates, especially for those with cardiopulmonary complications, warrant further investigation to understand risk factors for CPR complications, the underlying reasons and identify effective disease management strategies.

Birth Prevalence of Sickle Cell Disease and County-Level Social Vulnerability - Sickle Cell Data Collection Program, 11 States, 2016-2020.

Sickle cell disease (SCD) remains a public health priority in the United States because of its association with complex health needs, reduced life expectancy, lifelong disabilities, and high cost of care. A cross-sectional analysis was conducted to calculate the crude and race-specific birth prevalence for SCD using state newborn screening program records during 2016-2020 from 11 Sickle Cell Data Collection program states. The percentage distribution of birth mother residence within Social Vulnerability Index quartiles was derived. Among 3,305 newborns with confirmed SCD (including 57% with homozygous hemoglobin S or sickle ß-null thalassemia across 11 states, 90% of whom were Black or African American [Black], and 4% of whom were Hispanic or Latino), the crude SCD birth prevalence was 4.83 per 10,000 (one in every 2,070) live births and 28.54 per 10,000 (one in every 350) non-Hispanic Black newborns. Approximately two thirds (67%) of mothers of newborns with SCD lived in counties with high or very high levels of social vulnerability; most mothers lived in counties with high or very high levels of vulnerability for racial and ethnic minority status (89%) and housing type and transportation (64%) themes. These findings can guide public health, health care systems, and community program planning and implementation that address social determinants of health for infants with SCD. Implementation of tailored interventions, including increasing access to transportation, improving housing, and advancing equity in high vulnerability areas, could facilitate care and improve health outcomes for children with SCD.

Timing and co-occurrence of symptoms prior to a diagnosis of light chain (AL) amyloidosis.

It is well-established that light chain (AL) amyloidosis patients have multi-organ involvement and are often diagnosed after a lag period of increasing symptoms. We leverage electronic health record (EHR) data from the TriNetX research network to describe the incidence, timing, and co-occurrence of precursor conditions of interests in a cohort of AL amyloidosis patients identified between October 2015-December 2020. Nineteen precursor diagnoses of interest representing features of AL amyloidosis were identified using ICD codes up to 36 months prior to AL amyloidosis diagnosis. Among 1,401 patients with at least 36 months of EHR data prior to AL amyloidosis diagnosis, 46% were females, 16% were non-Hispanic Black, and 6% were Hispanic. The median age was 71 (range, 21-91) years. The median number of precursor diagnoses was 5 with dyspnea and fatigue being the most prevalent. The time from the first occurrence of a precursor to AL diagnosis ranged from 3.2 to 21.4 months. Analyses of pairwise co-occurrence of specific diagnoses indicated a high association (Cole's coefficient > 0.6) among the examined precursor diagnoses. These findings provide novel information about the timing and co-occurrence of key precursor conditions and could be used to develop algorithms for early identification of AL amyloidosis.

OmicPredict: a framework for omics data prediction using ANOVA-Firefly algorithm for feature selection.

High-throughput technologies and machine learning (ML), when applied to a huge pool of medical data such as omics data, result in efficient analysis. Recent research aims to apply and develop ML models to predict a disease well in time using available omics datasets. The present work proposed a framework, 'OmicPredict', deploying a hybrid feature selection method and deep neural network (DNN) model to predict multiple diseases using omics data. The hybrid feature selection method is developed using the Analysis of Variance (ANOVA) technique and firefly algorithm. The OmicPredict framework is applied to three case studies, Alzheimer's disease, Breast cancer, and Coronavirus disease 2019 (COVID-19). In the case study of Alzheimer's disease, the framework predicts patients using GSE33000 and GSE44770 dataset. In the case study of Breast cancer, the framework predicts human epidermal growth factor receptor 2 (HER2) subtype status using Molecular Taxonomy of Breast Cancer International Consortium (METABRIC) dataset. In the case study of COVID-19, the framework performs patients' classification using GSE157103 dataset. The experimental results show that DNN model achieved an Area Under Curve (AUC) score of 0.949 for the Alzheimer's (GSE33000 and GSE44770) dataset. Furthermore, it achieved an AUC score of 0.987 and 0.989 for breast cancer (METABRIC) and COVID-19 (GSE157103) datasets, respectively, outperforming Random Forest, Naïve Bayes models, and the existing research.

Perspectives on Virtual Care for Childhood Cancer Survivors in Non-Metropolitan Areas during the COVID-19 Pandemic.

The COVID-19 pandemic paved the way for the widespread use of virtual care for childhood cancer survivors (CCSs). CCSs were virtual recipients of diverse care, including long-term follow-up (LTFU), primary care, mental health care, and several others. Virtual care comes with well-documented benefits and challenges. These are further magnified for CCSs living in rural or non-metropolitan areas. Here, we describe the virtual care of CCSs from two Upper Midwest cities with well-established childhood cancer survivor programs within large comprehensive cancer centers in the United States. CCSs from non-metropolitan areas, especially CCSs with two or more late effects, used virtual care more often during the COVID-19 pandemic compared to CCSs from metropolitan areas. A review of the related literature is also included and the identified challenges in providing virtual care, such as privacy concerns, technology-connectivity constraints, and medical license restrictions. Despite these limitations, the care of CCSs has evolved to leverage virtual care and its ability to increase access for patients and promote continuity of care for CCSs living in rural areas.

Evaluating the Discriminatory Ability of the Sickle Cell Data Collection Program's Administrative Claims Case Definition in Identifying Adults With Sickle Cell Disease: Validation Study.

BACKGROUND: Sickle cell disease (SCD) was first recognized in 1910 and identified as a genetic condition in 1949. However, there is not a universal clinical registry that can be used currently to estimate its prevalence. The Sickle Cell Data Collection (SCDC) program, funded by the Centers for Disease Control and Prevention, funds state-level grantees to compile data within their states from various sources including administrative claims to identify individuals with SCD. The performance of the SCDC administrative claims case definition has been validated in a pediatric population with SCD, but it has not been tested in adults. OBJECTIVE: The objective of our study is to evaluate the discriminatory ability of the SCDC administrative claims case definition to accurately identify adults with SCD using Medicaid insurance claims data. METHODS: Our study used Medicaid claims data in combination with hospital-based medical record data from the Alabama, Georgia, and Wisconsin SCDC programs to identify individuals aged 18 years or older meeting the SCDC administrative claims case definition. In order to validate this definition, our study included only those individuals who were identified in both Medicaid's and the partnering clinical institution's records. We used clinical laboratory tests and diagnostic algorithms to determine the true SCD status of this subset of patients. Positive predictive values (PPV) are reported overall and by state under several scenarios. RESULTS: There were 1219 individuals (354 from Alabama and 865 from Georgia) who were identified through a 5-year time period. The 5-year time period yielded a PPV of 88.4% (91% for data from Alabama and 87% for data from Georgia), when only using data with laboratory-confirmed (gold standard) cases as true positives. With a narrower time period (3-year period) and data from 3 states (Alabama, Georgia, and Wisconsin), a total of 1432 individuals from these states were included in our study. The overall 3-year PPV was 89.4% (92%, 93%, and 81% for data from Alabama, Georgia, and Wisconsin, respectively) when only considering laboratory-confirmed cases as true cases. CONCLUSIONS: Adults identified as having SCD from administrative claims data based on the SCDC case definition have a high probability of truly having the disease, especially if those hospitals have active SCD programs. Administrative claims are thus a valuable data source to identify adults with SCD in a state and understand their epidemiology and health care service usage.

Common data model for sickle cell disease surveillance: considerations and implications.

Objective: Population-level data on sickle cell disease (SCD) are sparse in the United States. The Centers for Disease Control and Prevention (CDC) is addressing the need for SCD surveillance through state-level Sickle Cell Data Collection Programs (SCDC). The SCDC developed a pilot common informatics infrastructure to standardize processes across states. Materials and Methods: We describe the process for establishing and maintaining the proposed common informatics infrastructure for a rare disease, starting with a common data model and identify key data elements for public health SCD reporting. Results: The proposed model is constructed to allow pooling of table shells across states for comparison. Core Surveillance Data reports are compiled based on aggregate data provided by states to CDC annually. Discussion and Conclusion: We successfully implemented a pilot SCDC common informatics infrastructure to strengthen our distributed data network and provide a blueprint for similar initiatives in other rare diseases.

Preliminary construct validity of patient-reported outcomes to assess chronic pain in adults with sickle cell disease.

Chronic pain affects 30% to 40% of individuals with sickle cell disease (SCD) and impairs patient functioning. Clinically meaningful, practical, and valid assessment tools for investigation, evaluation, and management of chronic pain are limited, representing a barrier for advancing SCD care. We sought to determine whether patient-reported outcomes (PROs) show preliminary construct validity in identifying individuals with SCD who were a priori defined as suggestive of having chronic pain based on previously published criteria. All individuals completed the Patient-Reported Outcomes Measurement Information System (PROMIS) domains: pain interference, pain behavior, pain quality (nociceptive, neuropathic), fatigue, sleep disturbance, depression, and anxiety; the Adult Sickle Cell Quality of Life Measurement Information System (ASCQ-Me) domains: pain impact and emotional impact; and the painDETECT questionnaire. Thirty-three adults living with SCD were enrolled, and 42.4% had chronic pain. Pain-related PROs scores distinctly differentiated individuals with chronic pain from those without. Individuals with chronic pain had significantly worse pain-related PROs scores: PROMIS pain interference (64.2 vs 54.3), PROMIS pain behavior (63.2 vs 50), and ASCQ-Me pain impact (42.9 vs 53.2). According to published PROMIS clinical cut scores for the pain-related domains, individuals with chronic pain were categorized as having moderate impairment, whereas those without chronic pain had mild or no impairment. Individuals with chronic pain had PRO pain features consistent with neuropathic pain and worse scores in fatigue, depression, sleep disturbance, and emotional impact. Pain-related PROs show preliminary construct validity in differentiating individuals with and without chronic SCD pain and could be used as valuable tools for research and clinical monitoring of chronic pain.

Comparison of CAT and short forms for PROMIS pain and physical health domains in children with sickle cell disease.

BACKGROUND: Pain and physical health domains included in Patient-Reported Outcomes Measurement Information System® (PROMIS®) can be administered as short forms (SF) or as computer adaptive tests (CAT). CAT is ideal in many settings but cannot be administered without specialized technology. We compared SF and CAT to identify items for customized SFs to improve the SF performance for children with sickle cell disease (SCD). METHODS: Eligible children 8-17 years old were administered CATs for 5 domains of physical health and 2 domains of pain, followed by any items on the corresponding SF that were not included in the CAT assessments. We describe the range of scores on the CAT and SFs, including the percentage of participants with floor or ceiling effects using the SF. The agreement and correlation between CAT and SF scores were assessed using Bland-Altman plots. Items frequently offered on CAT that had variable responses and were not already present on SF are recommended as additional items for customized SFs. RESULTS: Among 90 children with SCD, there were strong correlations between CAT and SF scores (Concordance Correlation Coefficient > 0.8) however, the SFs for fatigue, mobility, strength impact, pain behavior, and pain interference had substantial floor/ceiling effects. Fatigue, mobility, physical stress experience, and pain behavior domains had items that were frequently offered on CAT, variable responses, and were not present on the SF. CONCLUSIONS: Adding items to the SFs for the fatigue, mobility, physical stress experience, and pain behavior domains may improve these domains' SFs performance for children with SCD.

A perspective on the sickle cell disease international COVID-19 registry.

To understand the risks and outcomes of COVID-19 in the sickle cell disease (SCD) population, our team established a rapid reporting registry to collect data on the course of COVID-19 illness in individuals with SCD. The registry includes cases reported voluntarily by providers. All data are collected through an online case report form available at covidsicklecell.org. The registry helped to recognize patients with SCD as a population at risk of severe COVID-19 illness and to identify comorbidities that put them at higher risk. In this report, we present data on 1045 reported COVID-19 cases based during a two-year long data collection period. Data include 590 (56.5%) children and 455 (43.5%) adults; 51.2% of total population were female. Most individuals (63.1%) had HbSS genotype. Majority of individuals experienced mild symptoms (62.2% of children, 55.6% of adults). We also present a perspective on setting up the registry and experiences through its growth.

Artificial intelligence opportunities in cardio-oncology: Overview with spotlight on electrocardiography.

Cardiovascular disease is a leading cause of death among cancer survivors, second only to cancer recurrence or development of new tumors. Cardio-oncology has therefore emerged as a relatively new specialty focused on prevention and management of cardiovascular consequences of cancer therapies. Yet challenges remain regarding precision and accuracy with predicting individuals at highest risk for cardiotoxicity. Barriers such as access to care also limit screening and early diagnosis to improve prognosis. Thus, developing innovative approaches for prediction and early detection of cardiovascular illness in this population is critical. In this review, we provide an overview of the present state of machine learning applications in cardio-oncology. We begin by outlining some factors that should be considered while utilizing machine learning algorithms. We then examine research in which machine learning has been applied to improve prediction of cardiac dysfunction in cancer survivors. We also highlight the use of artificial intelligence (AI) in conjunction with electrocardiogram (ECG) to predict cardiac malfunction and also atrial fibrillation (AF), and we discuss the potential role of wearables. Additionally, the article summarizes future prospects and critical takeaways for the application of machine learning in cardio-oncology. This study is the first in a series on artificial intelligence in cardio-oncology, and complements our manuscript on echocardiography and other forms of imaging relevant to cancer survivors cared for in cardiology clinical practice.

COVID-19 and venous thromboembolism risk in patients with sickle cell disease.

Venous thromboembolism (VTE) is a life-threatening complication observed among patients with sickle cell disease (SCD) and also among those with severe COVID-19 infection. Although prior studies show that patients with SCD are at risk of severe COVID-19 illness, it remains unclear if COVID-19 infection further increases VTE risk for this population. We hypothesized that patients with SCD hospitalized for COVID-19 would have higher VTE rates than those hospitalized for other causes. Using electronic health record data from a multisite research network, TriNetX, we identified 2 groups of patients with SCD hospitalized during 2020: (1) with COVID-19 and (2) without COVID-19. We compared VTE rates using risk ratios estimated based on adjusted Poisson regression model with log link and robust error variances. Of the 281 SCD patients hospitalized with COVID-19 and 4873 SCD patients hospitalized without COVID-19 , 35 (12.46%) and 418 (8.58%) had incident VTE within 6 months of the index hospitalization respectively. After adjusting for differences in baseline characteristics, no significant differences in VTE rates within 6 months were found between the 2 groups (adjusted relative risk, 1.06 [95% confidence interval, 0.79-1.41]). These data suggest that hospitalization with COVID-19 does not further increase VTE risk in patients with SCD.

Elizabethkingia anophelis Infections: A Case Series From a Tertiary Care Hospital in Uttar Pradesh.

Elizabethkingia anophelis is a gram-negative, aerobic, non-motile rod belonging to the ​​​​​Flavobacteriaceae family. Elizabethkingia is a genus of bacteria commonly found in the environment worldwide and has been detected in soil, river, water, and reservoirs. Over the period, it has emerged as an opportunistic human pathogen involved in neonatal meningitis and sepsis, as well as nosocomial outbreaks in adults with underlying medical conditions, including malignancies, diabetes, and chronic obstructive pulmonary disease. Here, we present a series of three cases of infection of E. anophelis in different clinical samples. These three cases were referred from different departments of King George's Medical University (KGMU), Lucknow, India to the Critical Care Medicine Department of KGMU, and finally succumbed to the infection.

Detection of changes of functioning over time after asthma exacerbation in children with the use of PROMIS domains.

OBJECTIVES: Patient reported outcome measures, such as the Patient Reported Outcomes Measurement Information System (PROMIS) may be utilized to understand experiences of patients. The purpose of this study was to determine the ability of PROMIS domains to detect changes in pain, physical functioning, and asthma impact over time for children experiencing asthma exacerbation. METHODS: Our prospective cohort study included children presenting to the emergency department (ED) for asthma exacerbation. Children completed PROMIS surveys in the ED, 7-10 days, and 1-3 months post-discharge. We used linear mixed models adjusted for age, gender, acute care utilization, and child global health to determine changes in PROMIS T-scores. We used self-reported child health response (Much better now versus a little better now or worse) at discharge as an anchor to determine if change in PROMIS scores corresponded with changes in health. A change was statistically significant if the 95% CI did not include 0. RESULTS: Our study included 63 children who presented to the ED for acute asthma exacerbation. We identified that children improved significantly in all domains over time. There was improvement over time following discharge from ED for all pain and physical functioning domains, and asthma impact. Using the clinical anchor, those with considerable improvement in asthma symptoms had improved T scores from 4-17. CONCLUSIONS: PROMIS domains of pain, physical functioning, depression, fatigue, peer relationships, and asthma impact are responsive to changes in health states over time. These domains may be used to measure clinically significant change in children experiencing asthma exacerbation.

Software system to predict the infection in COVID-19 patients using deep learning and web of things.

Since the end of 2019, computed tomography (CT) images have been used as an important substitute for the time-consuming Reverse Transcriptase polymerase chain reaction (RT-PCR) test; a new coronavirus 2019 (COVID-19) disease has been detected and has quickly spread through many countries across the world. Medical imaging such as computed tomography provides great potential due to growing skepticism toward the sensitivity of RT-PCR as a screening tool. For this purpose, automated image segmentation is highly desired for a clinical decision aid and disease monitoring. However, there is limited publicly accessible COVID-19 image knowledge, leading to the overfitting of conventional approaches. To address this issue, the present paper focuses on data augmentation techniques to create synthetic data. Further, a framework has been proposed using WoT and traditional U-Net with EfficientNet B0 to segment the COVID Radiopedia and Medseg datasets automatically. The framework achieves an F-score of 0.96, which is best among state-of-the-art methods. The performance of the proposed framework also computed using Sensitivity, Specificity, and Dice-coefficient, achieves 84.5%, 93.9%, and 65.0%, respectively. Finally, the proposed work is validated using three quality of service (QoS) parameters such as server latency, response time, and network latency which improves the performance by 8%, 7%, and 10%, respectively.

Surveillance for the Rare Condition of Sickle Cell Disease in Wisconsin.

INTRODUCTION: Despite universal newborn screening, there is no comprehensive surveillance system to understand the sickle cell disease population in Wisconsin. METHODS: We initiated the development of a sickle cell disease surveillance system by linking newborn screening data and electronic health records from 2 large tertiary health care institutions in Wisconsin: Children's Wisconsin and Froedtert Hospital. RESULTS: There were 1478 individuals within the 3 data sources. One hundred thirty-two (82%) of 159 identified by newborn screening from 2013 through 2019 received care at Children's Wisconsin. The majority of individuals with sickle cell disease at Children's Wisconsin and Froedtert Hospital resided in Milwaukee County. DISCUSSION: The new surveillance program will increase our understanding of the sickle cell disease population in Wisconsin and help improve quality of care and health outcomes.

Comorbidities are risk factors for hospitalization and serious COVID-19 illness in children and adults with sickle cell disease.

Patients with sickle cell disease (SCD) are at high risk of developing serious infections, therefore, understanding the impact that severe acute respiratory syndrome coronavirus 2 infection has on this population is important. We sought to identify factors associated with hospitalization and serious COVID-19 illness in children and adults with SCD.We established the international SECURE-SCD Registry to collect data on patients with SCD and COVID-19 illness. We used multivariable logistic models to estimate the independent effects of age, sex, genotype, hydroxyurea, and SCD-related and -nonrelated comorbidities on hospitalization, serious COVID-19 illness, and pain as a presenting symptom during COVID-19 illness. As of 23 March 2021, 750 COVID-19 illness cases in patients with SCD were reported to the registry. We identified history of pain (relative risk [RR], 2.15; P < .0001) and SCD heart/lung comorbidities (RR, 1.61; P = .0001) as risk factors for hospitalization in children. History of pain (RR, 1.78; P = .002) was also a risk factor for hospitalization in adults. Children with history of pain (RR, 3.09; P = .009), SCD heart/lung comorbidities (RR, 1.76; P = .03), and SCD renal comorbidities (RR, 3.67; P < .0001) and adults with history of pain (RR 1.94, P = .02) were at higher risk of developing serious COVID-19 illness. History of pain and SCD renal comorbidities also increased risk of pain during COVID-19 in children; history of pain, SCD heart/lung comorbidities, and female sex increased risk of pain during COVID-19 in adults. Hydroxyurea showed no effect on hospitalization and COVID-19 severity, but it lowered the risk of presenting with pain in adults during COVID-19.

COVID-19 in individuals with sickle cell disease/trait compared with other Black individuals.

In the United States, COVID-19 has disproportionately affected Black persons. Sickle cell disease (SCD) and sickle cell trait (SCT) are genetic conditions that occur predominantly among Black individuals. It is unknown if individuals with SCD/SCT are at higher risk of severe COVID-19 illness compared with Black individuals who do not have SCD/SCT. The objective of our study was to compare COVID-19 outcomes, including the disease manifestations, hospitalization, and death, among individuals with SCD/SCT vs Black individuals who do not have SCD/SCT. We leveraged electronic health record data from a multisite research network to identify Black patients with COVID-19 who have SCD/SCT and those who do not have SCD/SCT. During the study period of 20 January 2020 to 20 September 2020, there were 312 patients with COVID-19 and SCD and 449 patients with COVID-19 and SCT. There were 45 517 Black persons who were diagnosed with COVID-19 but who did not have SCD/SCT. After 1:1 propensity score matching (based on age, sex, and other preexisting comorbidities), patients with COVID-19 and SCD remained at a higher risk of hospitalization (relative risk [RR], 2.0; 95% CI, 1.5-2.7) and development of pneumonia (RR, 2.4; 95% CI, 1.6-3.4) and pain (RR, 3.4; 95% CI, 2.5-4.8) compared with Black persons without SCD/SCT. The case fatality rates for those with SCD compared with Black persons without SCD/SCT were not significantly different. There also were no significant differences in COVID-19 outcomes between individuals with SCT and Black persons without SCD/SCT within the matched cohorts.