Development and evaluation of a computable phenotype to identify pediatric patients with leukemia and lymphoma treated with chemotherapy using electronic health record data

Using electronic health records for clinical pharmacology research: Challenges and considerations

Electronic health records (EHRs) contain a vast array of phenotypic data on large numbers of individuals, often collected over decades. Due to the wealth of information, EHR data have emerged as a powerful resource to make first discoveries and identify disparities in our healthcare system. While the number of EHR-based studies has exploded in recent years, most of these studies are directed at associations with disease rather than pharmacotherapeutic outcomes, such as drug response or adverse drug reactions. This is largely due to challenges specific to deriving drug-related phenotypes from the EHR. There is great potential for EHR-based discovery in clinical pharmacology research, and there is a critical need to address specific challenges related to accurate and reproducible derivation of drug-related phenotypes from the EHR. This review provides a detailed evaluation of challenges and considerations for deriving drug-related data from EHRs. We provide an examination of EHR-based computable phenotypes and discuss cutting-edge approaches to map medication information for clinical pharmacology research, including medication-based computable phenotypes and natural language processing. We also discuss additional considerations such as data structure, heterogeneity and missing data, rare phenotypes, and diversity within the EHR. By further understanding the complexities associated with conducting clinical pharmacology research using EHR-based data, investigators will be better equipped to design thoughtful studies with more reproducible results. Progress in utilizing EHRs for clinical pharmacology research should lead to significant advances in our ability to understand differential drug response and predict adverse drug reactions.

Development and validation of a computable phenotype for Turner syndrome utilizing electronic health records from a national pediatric network

Turner syndrome (TS) is a genetic condition occurring in ~1 in 2000 females characterized by the complete or partial absence of the second sex chromosome. TS research faces similar challenges to many other pediatric rare disease conditions, with homogenous, single-center, underpowered studies. Secondary data analyses utilizing electronic health record (EHR) have the potential to address these limitations; however, an algorithm to accurately identify TS cases in EHR data is needed. We developed a computable phenotype to identify patients with TS using PEDSnet, a pediatric research network. This computable phenotype was validated through chart review; true positives and negatives and false positives and negatives were used to assess accuracy at both primary and external validation sites. The optimal algorithm consisted of the following criteria: female sex, ≥1 outpatient encounter, and ≥3 encounters with a diagnosis code that maps to TS, yielding an average sensitivity of 0.97, specificity of 0.88, and C-statistic of 0.93 across all sites. The accuracy of any estradiol prescriptions yielded an average C-statistic of 0.91 across sites and 0.80 for transdermal and oral formulations separately. PEDSnet and computable phenotyping are powerful tools in providing large, diverse samples to pragmatically study rare pediatric conditions like TS.

Rapid identification of inflammatory arthritis and associated adverse events following immune checkpoint therapy: a machine learning approach

Introduction

Immune checkpoint inhibitor-induced inflammatory arthritis (ICI-IA) poses a major clinical challenge to ICI therapy for cancer, with 13% of cases halting ICI therapy and ICI-IA being difficult to identify for timely referral to a rheumatologist. The objective of this study was to rapidly identify ICI-IA patients in clinical data and assess associated immune-related adverse events (irAEs) and risk factors.

Methods

We conducted a retrospective study of the electronic health records (EHRs) of 89 patients who developed ICI-IA out of 2451 cancer patients who received ICI therapy at Northwestern University between March 2011 to January 2021. Logistic regression and random forest machine learning models were trained on all EHR diagnoses, labs, medications, and procedures to identify ICI-IA patients and EHR codes indicating ICI-IA. Multivariate logistic regression was then used to test associations between ICI-IA and cancer type, ICI regimen, and comorbid irAEs.

Results

Logistic regression and random forest models identified ICI-IA patients with accuracies of 0.79 and 0.80, respectively. Key EHR features from the random forest model included ICI-IA relevant features (joint pain, steroid prescription, rheumatoid factor tests) and features suggesting comorbid irAEs (thyroid function tests, pruritus, triamcinolone prescription). Compared to 871 adjudicated ICI patients who did not develop arthritis, ICI-IA patients had higher odds of developing cutaneous (odds ratio [OR]=2.66; 95% Confidence Interval [CI] 1.63-4.35), endocrine (OR=2.09; 95% CI 1.15-3.80), or gastrointestinal (OR=2.88; 95% CI 1.76-4.72) irAEs adjusting for demographics, cancer type, and ICI regimen. Melanoma (OR=1.99; 95% CI 1.08-3.65) and renal cell carcinoma (OR=2.03; 95% CI 1.06-3.84) patients were more likely to develop ICI-IA compared to lung cancer patients. Patients on nivolumab+ipilimumab were more likely to develop ICI-IA compared to patients on pembrolizumab (OR=1.86; 95% CI 1.01-3.43).

Discussion

Our machine learning models rapidly identified patients with ICI-IA in EHR data and elucidated clinical features indicative of comorbid irAEs. Patients with ICI-IA were significantly more likely to also develop cutaneous, endocrine, and gastrointestinal irAEs during their clinical course compared to ICI therapy patients without ICI-IA.

Applying machine learning to identify pediatric patients with newly diagnosed acute lymphoblastic leukemia using administrative data

Case identification in administrative databases is challenging as diagnosis codes alone are not adequate for case ascertainment. We utilized machine learning (ML) to efficiently identify pediatric patients with newly diagnosed acute lymphoblastic leukemia. We tested nine ML models and validated the best model internally and externally. The optimal model had 97% positive predictive value (PPV) and 99% sensitivity in internal validation; 94% PPV and 82% sensitivity in external validation. Our ML model identified a large cohort of 21,044 patients, demonstrating an efficient approach for cohort assembly and enhancing the usability of administrative data.

Distinguishing characteristics of pediatric patients with primary hyperoxaluria type 1 in PEDSnet

BACKGROUND

Primary hyperoxaluria type 1 (PH1) is an autosomal recessive inborn error of metabolism that causes oxalate deposition, leading to recurrent calcium oxalate kidney stones, chronic kidney disease and systemic oxalosis, which produces a broad range of serious life-threatening complications. Patients with PH1 have delayed diagnosis due to the rarity of the disease and the overlap with early-onset kidney stone disease not due to primary hyperoxaluria.

OBJECTIVE

The objective of this study was to determine the clinical features of individuals <21 years of age with PH1 that precede its diagnosis. We hypothesized that a parsimonious set of features could be identified that differentiate patients with PH1 from patients with non-primary hyperoxaluria-associated causes of early-onset kidney stone disease.

STUDY DESIGN

We determined the association between clinical characteristics and PH1 diagnosis in a case-control study conducted between 2009 and 2021 in PEDSnet, a clinical research network of eight US pediatric health systems. Each patient with genetically confirmed PH1 was matched by sex and PEDSnet institution to up to 4 control patients with kidney stones without PH of any type. We obtained patient characteristics and diagnostic test results occurring before to less than 6 months after study entrance from a centralized database query and from manual chart review. Differences were examined using standardized differences and multivariable regression.

RESULTS

The study sample included 37 patients with PH1 and 147 controls. Patients with PH1 were younger at diagnosis (median age of 3 vs 13.5 years); 75 % of children with PH1 were less than 8 years-old. Patients with PH1 were more likely to have combinations of nephrocalcinosis on ultrasound or CT (43 % vs 3 %), lower eGFR at diagnosis (median = 52 mL/min/1.73 m2 vs 114 mL/min/1.73 m2), and have normal mobility. Patients with PH1 had higher proportion of calcium oxalate monohydrate kidney stones than controls (median = 100 % vs 10 %). There were no differences in diagnosis of failure to thrive, stone size, or echocardiography results.

CONCLUSIONS

Children with PH1 are characterized by presentation before adolescence, nephrocalcinosis, decreased eGFR at diagnosis, and calcium oxalate monohydrate stone composition. If externally validated, these characteristics could facilitate earlier diagnosis and treatment of children with PH1.

Electronic health records identify timely trends in childhood mental health conditions

BACKGROUND

Electronic health records (EHRs) data provide an opportunity to collect patient information rapidly, efficiently and at scale. National collaborative research networks, such as PEDSnet, aggregate EHRs data across institutions, enabling rapid identification of pediatric disease cohorts and generating new knowledge for medical conditions. To date, aggregation of EHR data has had limited applications in advancing our understanding of mental health (MH) conditions, in part due to the limited research in clinical informatics, necessary for the translation of EHR data to child mental health research.

METHODS

In this cohort study, a comprehensive EHR-based typology was developed by an interdisciplinary team, with expertise in informatics and child and adolescent psychiatry, to query aggregated, standardized EHR data for the full spectrum of MH conditions (disorders/symptoms and exposure to adverse childhood experiences (ACEs), across 13 years (2010-2023), from 9 PEDSnet centers. Patients with and without MH disorders/symptoms (without ACEs), were compared by age, gender, race/ethnicity, insurance, and chronic physical conditions. Patients with ACEs alone were compared with those that also had MH disorders/symptoms. Prevalence estimates for patients with 1+ disorder/symptoms and for specific disorders/symptoms and exposure to ACEs were calculated, as well as risk for developing MH disorder/symptoms.

RESULTS

The EHR study data set included 7,852,081 patients < 21 years of age, of which 52.1% were male. Of this group, 1,552,726 (19.8%), without exposure to ACEs, had a lifetime MH disorders/symptoms, 56.5% being male. Annual prevalence estimates of MH disorders/symptoms (without exposure to ACEs) rose from 10.6% to 2010 to 15.1% in 2023, a 44% relative increase, peaking to 15.4% in 2019, prior to the Covid-19 pandemic. MH categories with the largest increases between 2010 and 2023 were exposure to ACEs (1.7, 95% CI 1.6-1.8), anxiety disorders (2.8, 95% CI 2.8-2.9), eating/feeding disorders (2.1, 95% CI 2.1-2.2), gender dysphoria/sexual dysfunction (43.6, 95% CI 35.8-53.0), and intentional self-harm/suicidality (3.3, 95% CI 3.2-3.5). White youths had the highest rates in most categories, except for disruptive behavior disorders, elimination disorders, psychotic disorders, and standalone symptoms which Black youths had higher rates. Median age of detection was 8.1 years (IQR 3.5-13.5) with all standalone symptoms recorded earlier than the corresponding MH disorder categories.

CONCLUSIONS

These results support EHRs' capability in capturing the full spectrum of MH disorders/symptoms and exposure to ACEs, identifying the proportion of patients and groups at risk, and detecting trends throughout a 13-year period that included the Covid-19 pandemic. Standardized EHR data, which capture MH conditions is critical for health systems to examine past and current trends for future surveillance. Our publicly available EHR-mental health typology codes can be used in other studies to further advance research in this area.

The real world experience of pediatric primary hyperoxaluria patients in the PEDSnet clinical research network

The rarity of primary hyperoxaluria (PH) challenges our understanding of the disease. The purpose of our study was to describe the course of clinical care in a United States cohort of PH pediatric patients, highlighting health service utilization. We performed a retrospective cohort study of PH patients < 18 years old in the PEDSnet clinical research network from 2009 to 2021. Outcomes queried included diagnostic imaging and testing related to known organ involvement of PH, surgical and medical interventions specific to PH-related renal disease, and select PH-related hospital service utilization. Outcomes were evaluated relative to cohort entrance date (CED), defined as date of first PH-related diagnostic code. Thirty-three patients were identified: 23 with PH type 1; 4 with PH type 2; 6 with PH type 3. Median age at CED was 5.0 years (IQR 1.4, 9.3 years) with the majority being non-Hispanic white (73%) males (70%). Median follow-up between CED and most recent encounter was 5.1 years (IQR 1.2, 6.8). Nephrology and Urology were the most common specialties involved in care, with low utilization of other sub-specialties (12%-36%). Most patients (82%) had diagnostic imaging used to evaluate kidney stones; 11 (33%) had studies of extra-renal involvement. Stone surgery was performed in 15 (46%) patients. Four patients (12%) required dialysis, begun in all prior to CED; four patients required renal or renal/liver transplant.    Conclusion: In this large cohort of U.S. PH children, patients required heavy health care utilization with room for improvement in involving multi-disciplinary specialists. What is Known: • Primary hyperoxaluria (PH) is rare with significant implications on patient health. Typical involvement includes the kidneys; however, extra-renal manifestations occur. • Most large population studies describe clinical manifestations and involve registries. What is New: • We report the clinical journey, particularly related to diagnostic studies, interventions, multispecialty involvement, and hospital utilization, of a large cohort of PH pediatric patients in the PEDSnet clinical research network. • There are missed opportunities, particularly in that of specialty care, that could help in the diagnosis, treatment, and even prevention of known clinical manifestations.

Assessing Detection of Children With Suicide-Related Emergencies: Evaluation and Development of Computable Phenotyping Approaches

BACKGROUND

Although suicide is a leading cause of death among children, the optimal approach for using health care data sets to detect suicide-related emergencies among children is not known.

OBJECTIVE

This study aimed to assess the performance of suicide-related International Classification of Diseases, Tenth Revision, Clinical Modification (ICD-10-CM) codes and suicide-related chief complaint in detecting self-injurious thoughts and behaviors (SITB) among children compared with clinician chart review. The study also aimed to examine variations in performance by child sociodemographics and type of self-injury, as well as develop machine learning models trained on codified health record data (features) and clinician chart review (gold standard) and test model detection performance.

METHODS

A gold standard classification of suicide-related emergencies was determined through clinician manual review of clinical notes from 600 emergency department visits between 2015 and 2019 by children aged 10 to 17 years. Visits classified with nonfatal suicide attempt or intentional self-harm using the Centers for Disease Control and Prevention surveillance case definition list of ICD-10-CM codes and suicide-related chief complaint were compared with the gold standard classification. Machine learning classifiers (least absolute shrinkage and selection operator-penalized logistic regression and random forest) were then trained and tested using codified health record data (eg, child sociodemographics, medications, disposition, and laboratory testing) and the gold standard classification. The accuracy, sensitivity, and specificity of each detection approach and relative importance of features were examined.

RESULTS

SITB accounted for 47.3% (284/600) of the visits. Suicide-related diagnostic codes missed nearly one-third (82/284, 28.9%) and suicide-related chief complaints missed more than half (153/284, 53.9%) of the children presenting to emergency departments with SITB. Sensitivity was significantly lower for male children than for female children (0.69, 95% CI 0.61-0.77 vs 0.84, 95% CI 0.78-0.90, respectively) and for preteens compared with adolescents (0.66, 95% CI 0.54-0.78 vs 0.86, 95% CI 0.80-0.92, respectively). Specificity was significantly lower for detecting preparatory acts (0.68, 95% CI 0.64-0.72) and attempts (0.67, 95% CI 0.63-0.71) than for detecting ideation (0.79, 95% CI 0.75-0.82). Machine learning-based models significantly improved the sensitivity of detection compared with suicide-related codes and chief complaint alone. Models considering all 84 features performed similarly to models considering only mental health-related ICD-10-CM codes and chief complaints (34 features) and models considering non-ICD-10-CM code indicators and mental health-related chief complaints (53 features).

CONCLUSIONS

The capacity to detect children with SITB may be strengthened by applying a machine learning-based approach to codified health record data. To improve integration between clinical research informatics and child mental health care, future research is needed to evaluate the potential benefits of implementing detection approaches at the point of care and identifying precise targets for suicide prevention interventions in children.

Trends and opportunities in computable clinical phenotyping: A scoping review

Identifying patient cohorts meeting the criteria of specific phenotypes is essential in biomedicine and particularly timely in precision medicine. Many research groups deliver pipelines that automatically retrieve and analyze data elements from one or more sources to automate this task and deliver high-performing computable phenotypes. We applied a systematic approach based on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines to conduct a thorough scoping review on computable clinical phenotyping. Five databases were searched using a query that combined the concepts of automation, clinical context, and phenotyping. Subsequently, four reviewers screened 7960 records (after removing over 4000 duplicates) and selected 139 that satisfied the inclusion criteria. This dataset was analyzed to extract information on target use cases, data-related topics, phenotyping methodologies, evaluation strategies, and portability of developed solutions. Most studies supported patient cohort selection without discussing the application to specific use cases, such as precision medicine. Electronic Health Records were the primary source in 87.1 % (N = 121) of all studies, and International Classification of Diseases codes were heavily used in 55.4 % (N = 77) of all studies, however, only 25.9 % (N = 36) of the records described compliance with a common data model. In terms of the presented methods, traditional Machine Learning (ML) was the dominant method, often combined with natural language processing and other approaches, while external validation and portability of computable phenotypes were pursued in many cases. These findings revealed that defining target use cases precisely, moving away from sole ML strategies, and evaluating the proposed solutions in the real setting are essential opportunities for future work. There is also momentum and an emerging need for computable phenotyping to support clinical and epidemiological research and precision medicine.

Data standards in pediatric oncology: Past, present, and future

In this commentary, we highlight the central role that data standards play in facilitating data-driven efforts to advance research in pediatric oncology. We discuss the current state of data standards for pediatric oncology and propose five steps to achieve an improved future state with benefits for clinicians, researchers, and patients.

Leveraging electronic health record data for clinical trial planning by assessing eligibility criteria's impact on patient count and safety

OBJECTIVE

To present an approach on using electronic health record (EHR) data that assesses how different eligibility criteria, either individually or in combination, can impact patient count and safety (exemplified by all-cause hospitalization risk) and further assist with criteria selection for prospective clinical trials.

MATERIALS AND METHODS

Trials in three disease domains - relapsed/refractory (r/r) lymphoma/leukemia; hepatitis C virus (HCV); stages 3 and 4 chronic kidney disease (CKD) - were analyzed as case studies for this approach. For each disease domain, criteria were identified and all criteria combinations were used to create EHR cohorts. Per combination, two values were derived: (1) number of eligible patients meeting the selected criteria; (2) hospitalization risk, measured as the hazard ratio between those that qualified and those that did not. From these values, k-means clustering was applied to derive which criteria combinations maximized patient counts but minimized hospitalization risk.

RESULTS

Criteria combinations that reduced hospitalization risk without substantial reductions on patient counts were as follows: for r/r lymphoma/leukemia (23 trials; 9 criteria; 623 patients), applying no infection and adequate absolute neutrophil count while forgoing no prior malignancy; for HCV (15; 7; 751), applying no human immunodeficiency virus and no hepatocellular carcinoma while forgoing no decompensated liver disease/cirrhosis; for CKD (10; 9; 23893), applying no congestive heart failure.

CONCLUSIONS

Within each disease domain, the more drastic effects were generally driven by a few criteria. Similar criteria across different disease domains introduce different changes. Although results are contingent on the trial sample and the EHR data used, this approach demonstrates how EHR data can inform the impact on safety and available patients when exploring different criteria combinations for designing clinical trials.

Positive predictive value and sensitivity of ICD-9-CM codes for identifying pediatric leukemia

BACKGROUND

To facilitate community-based epidemiologic studies of pediatric leukemia, we validated use of ICD-9-CM diagnosis codes to identify pediatric leukemia cases in electronic medical records of six U.S. integrated health plans from 1996-2015 and evaluated the additional contributions of procedure codes for diagnosis/treatment.

PROCEDURES

Subjects (N = 408) were children and adolescents born in the health systems and enrolled for at least 120 days after the date of the first leukemia ICD-9-CM code or tumor registry diagnosis. The gold standard was the health system tumor registry and/or medical record review. We calculated positive predictive value (PPV) and sensitivity by number of ICD-9-CM codes received in the 120-day period following and including the first code. We evaluated whether adding chemotherapy and/or bone marrow biopsy/aspiration procedure codes improved PPV and/or sensitivity.

RESULTS

Requiring receipt of one or more codes resulted in 99% sensitivity (95% confidence interval [CI]: 98-100%) but poor PPV (70%; 95% CI: 66-75%). Receipt of two or more codes improved PPV to 90% (95% CI: 86-93%) with 96% sensitivity (95% CI: 93-98%). Requiring at least four codes maximized PPV (95%; 95% CI: 92-98%) without sacrificing sensitivity (93%; 95% CI: 89-95%). Across health plans, PPV for four codes ranged from 84-100% and sensitivity ranged from 83-95%. Including at least one code for a bone marrow procedure or chemotherapy treatment had minimal impact on PPV or sensitivity.

CONCLUSIONS

The use of diagnosis codes from the electronic health record has high PPV and sensitivity for identifying leukemia in children and adolescents if more than one code is required.

Medication based machine learning to identify subpopulations of pediatric hemodialysis patients in an electronic health record database

Electronic health records (EHRs) have given rise to large and complex databases of medical information that have the potential to become powerful tools for clinical research. However, differences in coding systems and the detail and accuracy of the information within EHRs can vary across institutions. This makes it challenging to identify subpopulations of patients and limits the widespread use of multi-institutional databases. In this study, we leveraged machine learning to identify patterns in medication usage among hospitalized pediatric patients receiving renal replacement therapy and created a predictive model that successfully differentiated between intermittent (iHD) and continuous renal replacement therapy (CRRT) hemodialysis patients. We trained six machine learning algorithms (logistical regression, Naïve Bayes, k-nearest neighbor, support vector machine, random forest, and gradient boosted trees) using patient records from a multi-center database (n = 533) and prescribed medication ingredients (n = 228) as features to discriminate between the two hemodialysis types. Predictive skill was assessed using a 5-fold cross-validation, and the algorithms showed a range of performance from 0.7 balanced accuracy (logistical regression) to 0.86 (random forest). The two best performing models were further tested using an independent single-center dataset and achieved 84–87% balanced accuracy. This model overcomes issues inherent within large databases and will allow us to utilize and combine historical records, significantly increasing population size and diversity within both iHD and CRRT populations for future clinical studies. Our work demonstrates the utility of using medications alone to accurately differentiate subpopulations of patients in large datasets, allowing codes to be transferred between different coding systems. This framework has the potential to be used to distinguish other subpopulations of patients where discriminatory ICD codes are not available, permitting more detailed insights and new lines of research.

Using a Multi-Institutional Pediatric Learning Health System to Identify Systemic Lupus Erythematosus and Lupus Nephritis: Development and Validation of Computable Phenotypes

BACKGROUND AND OBJECTIVES

Performing adequately powered clinical trials in pediatric diseases, such as SLE, is challenging. Improved recruitment strategies are needed for identifying patients.

DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS

Electronic health record algorithms were developed and tested to identify children with SLE both with and without lupus nephritis. We used single-center electronic health record data to develop computable phenotypes composed of diagnosis, medication, procedure, and utilization codes. These were evaluated iteratively against a manually assembled database of patients with SLE. The highest-performing phenotypes were then evaluated across institutions in PEDSnet, a national health care systems network of >6.7 million children. Reviewers blinded to case status used standardized forms to review random samples of cases (n=350) and noncases (n=350).

RESULTS

Final algorithms consisted of both utilization and diagnostic criteria. For both, utilization criteria included two or more in-person visits with nephrology or rheumatology and ≥60 days follow-up. SLE diagnostic criteria included absence of neonatal lupus, one or more hydroxychloroquine exposures, and either three or more qualifying diagnosis codes separated by ≥30 days or one or more diagnosis codes and one or more kidney biopsy procedure codes. Sensitivity was 100% (95% confidence interval [95% CI], 99 to 100), specificity was 92% (95% CI, 88 to 94), positive predictive value was 91% (95% CI, 87 to 94), and negative predictive value was 100% (95% CI, 99 to 100). Lupus nephritis diagnostic criteria included either three or more qualifying lupus nephritis diagnosis codes (or SLE codes on the same day as glomerular/kidney codes) separated by ≥30 days or one or more SLE diagnosis codes and one or more kidney biopsy procedure codes. Sensitivity was 90% (95% CI, 85 to 94), specificity was 93% (95% CI, 89 to 97), positive predictive value was 94% (95% CI, 89 to 97), and negative predictive value was 90% (95% CI, 84 to 94). Algorithms identified 1508 children with SLE at PEDSnet institutions (537 with lupus nephritis), 809 of whom were seen in the past 12 months.

CONCLUSIONS

Electronic health record-based algorithms for SLE and lupus nephritis demonstrated excellent classification accuracy across PEDSnet institutions.

Evaluating Completeness of Discrete Data on Physical Functioning for Children With Cerebral Palsy in a Pediatric Rehabilitation Learning Health System

OBJECTIVE

The purpose of this study was to determine the extent that physical function discrete data elements (DDE) documented in electronic health records (EHR) are complete within pediatric rehabilitation settings.

METHODS

A descriptive analysis on completeness of EHR-based DDEs detailing physical functioning for children with cerebral palsy was conducted. Data from an existing pediatric rehabilitation research learning health system data network, consisting of EHR data from 20 care sites in a pediatric specialty health care system, were leveraged. Completeness was calculated for unique data elements, unique outpatient visits, and unique outpatient records.

RESULTS

Completeness of physical function DDEs was low across 5766 outpatient records (10.5%, approximately 2 DDEs documented). The DDE for Gross Motor Function Classification System level was available for 21% (n = 3746) outpatient visits and 38% of patient records. Ambulation level was the most frequently documented DDE. Intercept only mixed effects models demonstrated that 21.4% and 45% of the variance in completeness for DDEs and the Gross Motor Function Classification System, respectively, across unique patient records could be attributed to factors at the individual care site level.

CONCLUSION

Values of physical function DDEs are missing in designated fields of the EHR infrastructure for pediatric rehabilitation providers. Although completeness appears limited for these DDEs, our observations indicate that data are not missing at random and may be influenced by system-level standards in clinical documentation practices between providers and factors specific to individual care sites. The extent of missing data has significant implications for pediatric rehabilitation quality measurement. More research is needed to understand why discrete data are missing in EHRs and to further elucidate the professional and system-level factors that influence completeness and missingness.

IMPACT

Completeness of DDEs reported in this study is limited and presents a significant opportunity to improve documentation and standards to optimize EHR data for learning health system research and quality measurement in pediatric rehabilitation settings.

Clinical data for paediatric research: the Swiss approach : Proceedings of the National Symposium in Bern, Switzerland, Dec 5-6, 2019

BACKGROUND AND PURPOSE

Continuous improvement of health and healthcare system is hampered by inefficient processes of generating new evidence, particularly in the case of rare diseases and paediatrics. Currently, most evidence is generated through specific research projects, which typically require extra encounters with patients, are costly and entail long delays between the recognition of specific needs in healthcare and the generation of necessary evidence to address those needs. The Swiss Personalised Health Network (SPHN) aims to improve the use of data obtained during routine healthcare encounters by harmonizing data across Switzerland and facilitating accessibility for research. The project "Harmonising the collection of health-related data and biospecimens in paediatric hospitals throughout Switzerland (SwissPedData)" was an infrastructure development project funded by the SPHN, which aimed to identify and describe available data on child health in Switzerland and to agree on a standardised core dataset for electronic health records across all paediatric teaching hospitals. Here, we describe the results of a two-day symposium that aimed to summarise what had been achieved in the SwissPedData project, to put it in an international context, and to discuss the next steps for a sustainable future. The target audience included clinicians and researchers who produce and use health-related data on children in Switzerland.

KEY HIGHLIGHTS

The symposium consisted of state-of-the-art lectures from national and international keynote speakers, workshops and plenary discussions. This manuscript summarises the talks and discussions in four sections: (I) a description of the Swiss Personalized Health Network and the results of the SwissPedData project; (II) examples of similar initiatives from other countries; (III) an overview of existing health-related datasets and projects in Switzerland; and (IV) a summary of the lessons learned and future prospective from workshops and plenary discussions.

IMPLICATIONS

Streamlined processes linking initial collection of information during routine healthcare encounters, standardised recording of this information in electronic health records and fast accessibility for research are essential to accelerate research in child health and make it affordable. Ongoing projects prove that this is feasible in Switzerland and elsewhere. International collaboration is vital to success. The next steps include the implementation of the SwissPedData core dataset in the clinical information systems of Swiss hospitals, the use of this data to address priority research questions, and the acquisition of sustainable funding to support a slim central infrastructure and local support in each hospital. This will lay the foundation for a national paediatric learning health system in Switzerland.

The effects of solution-focused nursing on leukemia chemotherapy patients' moods, cancer-related fatigue, coping styles, self-efficacy, and quality of life

OBJECTIVE

To explore the effects of solution-focused nursing on leukemia chemotherapy patients' moods, cancer-related fatigue, coping styles, self-efficacy, and quality of life.

METHODS

A total of 103 patients who underwent leukemia chemotherapy in our hospital were analyzed retrospectively and were divided into two groups based on the intervention method. Group A underwent routine nursing intervention, and group B underwent solution-focused nursing. The Hamilton Anxiety Rating Scale (HAMA) scores, the Montgomery-Asberg Depression Rating Scale (MADRS) scores, the Trait Coping Style Questionnaire (TCSQ) scores, the cancer-related fatigue self-rating scores, the General Self-Efficacy Scale (GSES) scores, and the Spitzer Quality of Life Index scores were compared between the two groups.

RESULTS

Compared with group A, group B had lower HAMA scores, lower MADRS scores, lower cognitive, behavioral, perception, and emotional scores, and higher self-efficacy scores (P<0.05). Group B had higher activity scores, and better psychological statuses, support from family and friends, health perception, and outlook on life than group A after the intervention (P<0.05).

CONCLUSION

Solution-focused nursing can alleviate leukemia chemotherapy patients' negative emotions and cancer-related fatigue, improve their coping styles, and increase their self-efficacy and quality of life.

Clinical comparison between trial participants and potentially eligible patients using electronic health record data: A generalizability assessment method

OBJECTIVE

To present a generalizability assessment method that compares baseline clinical characteristics of trial participants (TP) to potentially eligible (PE) patients as presented in their electronic health record (EHR) data while controlling for clinical setting and recruitment period.

METHODS

For each clinical trial, a clinical event was defined to identify patients of interest using available EHR data from one clinical setting during the trial's recruitment timeframe. The trial's eligibility criteria were then applied and patients were separated into two mutually exclusive groups: (1) TP, which were patients that participated in the trial per trial enrollment data; (2) PE, the remaining patients. The primary outcome was standardized differences in clinical characteristics between TP and PE per trial. A standardized difference was considered prominent if its absolute value was greater than or equal to 0.1. The secondary outcome was the difference in mean propensity scores (PS) between TP and PE per trial, in which the PS represented prediction for a patient to be in the trial. Three diverse trials were selected for illustration: one focused on hepatitis C virus (HCV) patients receiving a liver transplantation; one focused on leukemia patients and lymphoma patients; and one focused on appendicitis patients.

RESULTS

For the HCV trial, 43 TP and 83 PE were found, with 61 characteristics evaluated. Prominent differences were found among 69% of characteristics, with a mean PS difference of 0.13. For the leukemia/lymphoma trial, 23 TP and 23 PE were found, with 39 characteristics evaluated. Prominent differences were found among 82% of characteristics, with a mean PS difference of 0.76. For the appendicitis trial, 123 TP and 242 PE were found, with 52 characteristics evaluated. Prominent differences were found among 52% of characteristics, with a mean PS difference of 0.15.

CONCLUSIONS

Differences in clinical characteristics were observed between TP and PE among all three trials. In two of the three trials, not all of the differences necessarily compromised trial generalizability and subsets of PE could be considered similar to their corresponding TP. In the remaining trial, lack of generalizability appeared present, but may be a result of other factors such as small sample size or site recruitment strategy. These inconsistent findings suggest eligibility criteria alone are sometimes insufficient in defining a target group to generalize to. With caveats in limited scalability, EHR data quality, and lack of patient perspective on trial participation, this generalizability assessment method that incorporates control for temporality and clinical setting promise to better pinpoint clinical patterns and trial considerations.

Assessment of 135 794 Pediatric Patients Tested for Severe Acute Respiratory Syndrome Coronavirus 2 Across the United States

IMPORTANCE

There is limited information on severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) testing and infection among pediatric patients across the United States.

OBJECTIVE

To describe testing for SARS-CoV-2 and the epidemiology of infected patients.

DESIGN, SETTING, AND PARTICIPANTS

A retrospective cohort study was conducted using electronic health record data from 135 794 patients younger than 25 years who were tested for SARS-CoV-2 from January 1 through September 8, 2020. Data were from PEDSnet, a network of 7 US pediatric health systems, comprising 6.5 million patients primarily from 11 states. Data analysis was performed from September 8 to 24, 2020.

EXPOSURE

Testing for SARS-CoV-2.

MAIN OUTCOMES AND MEASURES

SARS-CoV-2 infection and coronavirus disease 2019 (COVID-19) illness.

RESULTS

A total of 135 794 pediatric patients (53% male; mean [SD] age, 8.8 [6.7] years; 3% Asian patients, 15% Black patients, 11% Hispanic patients, and 59% White patients; 290 per 10 000 population [range, 155-395 per 10 000 population across health systems]) were tested for SARS-CoV-2, and 5374 (4%) were infected with the virus (12 per 10 000 population [range, 7-16 per 10 000 population]). Compared with White patients, those of Black, Hispanic, and Asian race/ethnicity had lower rates of testing (Black: odds ratio [OR], 0.70 [95% CI, 0.68-0.72]; Hispanic: OR, 0.65 [95% CI, 0.63-0.67]; Asian: OR, 0.60 [95% CI, 0.57-0.63]); however, they were significantly more likely to have positive test results (Black: OR, 2.66 [95% CI, 2.43-2.90]; Hispanic: OR, 3.75 [95% CI, 3.39-4.15]; Asian: OR, 2.04 [95% CI, 1.69-2.48]). Older age (5-11 years: OR, 1.25 [95% CI, 1.13-1.38]; 12-17 years: OR, 1.92 [95% CI, 1.73-2.12]; 18-24 years: OR, 3.51 [95% CI, 3.11-3.97]), public payer (OR, 1.43 [95% CI, 1.31-1.57]), outpatient testing (OR, 2.13 [1.86-2.44]), and emergency department testing (OR, 3.16 [95% CI, 2.72-3.67]) were also associated with increased risk of infection. In univariate analyses, nonmalignant chronic disease was associated with lower likelihood of testing, and preexisting respiratory conditions were associated with lower risk of positive test results (standardized ratio [SR], 0.78 [95% CI, 0.73-0.84]). However, several other diagnosis groups were associated with a higher risk of positive test results: malignant disorders (SR, 1.54 [95% CI, 1.19-1.93]), cardiac disorders (SR, 1.18 [95% CI, 1.05-1.32]), endocrinologic disorders (SR, 1.52 [95% CI, 1.31-1.75]), gastrointestinal disorders (SR, 2.00 [95% CI, 1.04-1.38]), genetic disorders (SR, 1.19 [95% CI, 1.00-1.40]), hematologic disorders (SR, 1.26 [95% CI, 1.06-1.47]), musculoskeletal disorders (SR, 1.18 [95% CI, 1.07-1.30]), mental health disorders (SR, 1.20 [95% CI, 1.10-1.30]), and metabolic disorders (SR, 1.42 [95% CI, 1.24-1.61]). Among the 5374 patients with positive test results, 359 (7%) were hospitalized for respiratory, hypotensive, or COVID-19-specific illness. Of these, 99 (28%) required intensive care unit services, and 33 (9%) required mechanical ventilation. The case fatality rate was 0.2% (8 of 5374). The number of patients with a diagnosis of Kawasaki disease in early 2020 was 40% lower (259 vs 433 and 430) than in 2018 or 2019.

CONCLUSIONS AND RELEVANCE

In this large cohort study of US pediatric patients, SARS-CoV-2 infection rates were low, and clinical manifestations were typically mild. Black, Hispanic, and Asian race/ethnicity; adolescence and young adulthood; and nonrespiratory chronic medical conditions were associated with identified infection. Kawasaki disease diagnosis is not an effective proxy for multisystem inflammatory syndrome of childhood.

Big Data for Nutrition Research in Pediatric Oncology: Current State and Framework for Advancement

Recognition and treatment of malnutrition in pediatric oncology patients is crucial because it is associated with increased morbidity and mortality. Nutrition-relevant data collected from cancer clinical trials and nutrition-specific studies are insufficient to drive high-impact nutrition research without augmentation from additional data sources. To date, clinical big data resources are underused for nutrition research in pediatric oncology. Health-care big data can be broadly subclassified into three clinical data categories: administrative, electronic health record (including clinical data research networks and learning health systems), and mobile health. Along with -omics data, each has unique applications and limitations. We summarize the potential use of clinical big data to drive pediatric oncology nutrition research and identify key scientific gaps. A framework for advancement of big data utilization for pediatric oncology nutrition research is presented and focuses on transdisciplinary teams, data interoperability, validated cohort curation, data repurposing, and mobile health applications.