Phenotypic overlap between rare disease patients and variant carriers in a large population cohort informs biological mechanisms.

The biological mechanisms giving rise to the extreme symptoms exhibited by rare disease patients are complex, heterogenous, and difficult to discern. Understanding these mechanisms is critical for developing treatments that address the underlying causes of diseases rather than merely the presenting symptoms. Moreover, the same dysfunctional biological mechanisms implicated in rare recessive diseases may also lead to milder and potentially preventable symptoms in carriers in the general population. Seizures are a common, extreme phenotype that can result from diverse and often elusive biological pathways in patients with ultrarare or undiagnosed disorders. In this pilot study, we present an approach to understand the biological pathways leading to seizures in patients from the Undiagnosed Diseases Network (UDN) by analyzing aggregated genotype and phenotype data from the UK Biobank (UKB). Specifically, we look for enriched phenotypes across UKB participants who harbor rare variants in the same gene known or suspected to be causally implicated in a UDN patient's recessively manifesting disorder. Analyzing these milder but related associated phenotypes in UKB participants can provide insight into the disease-causing molecular mechanisms at play in the rare disease UDN patient. We present six vignettes of undiagnosed patients experiencing seizures as part of their recessive genetic condition, and we discuss the potential mechanisms underlying the spectrum of symptoms associated with UKB participants to the severe presentations exhibited by UDN patients. We find that in our set of rare disease patients, seizures may result from diverse, multi-step pathways that involve multiple body systems. Analyses of large-scale population cohorts such as the UKB can be a critical tool to further our understanding of rare diseases in general.

Emerging therapeutic drug monitoring technologies: considerations and opportunities in precision medicine.

In recent years, the development of sensor and wearable technologies have led to their increased adoption in clinical and health monitoring settings. One area that is in early, but promising, stages of development is the use of biosensors for therapeutic drug monitoring (TDM). Traditionally, TDM could only be performed in certified laboratories and was used in specific scenarios to optimize drug dosage based on measurement of plasma/blood drug concentrations. Although TDM has been typically pursued in settings involving medications that are challenging to manage, the basic approach is useful for characterizing drug activity. TDM is based on the idea that there is likely a clear relationship between plasma/blood drug concentration (or concentration in other matrices) and clinical efficacy. However, these relationships may vary across individuals and may be affected by genetic factors, comorbidities, lifestyle, and diet. TDM technologies will be valuable for enabling precision medicine strategies to determine the clinical efficacy of drugs in individuals, as well as optimizing personalized dosing, especially since therapeutic windows may vary inter-individually. In this mini-review, we discuss emerging TDM technologies and their applications, and factors that influence TDM including drug interactions, polypharmacy, and supplement use. We also discuss how using TDM within single subject (N-of-1) and aggregated N-of-1 clinical trial designs provides opportunities to better capture drug response and activity at the individual level. Individualized TDM solutions have the potential to help optimize treatment selection and dosing regimens so that the right drug and right dose may be matched to the right person and in the right context.

Disease progression strikingly differs in research and real-world Parkinson's populations.

Characterization of Parkinson's disease (PD) progression using real-world evidence could guide clinical trial design and identify subpopulations. Efforts to curate research populations, the increasing availability of real-world data, and advances in natural language processing, particularly large language models, allow for a more granular comparison of populations than previously possible. This study includes two research populations and two real-world data-derived (RWD) populations. The research populations are the Harvard Biomarkers Study (HBS, N = 935), a longitudinal biomarkers cohort study with in-person structured study visits; and Fox Insights (N = 36,660), an online self-survey-based research study of the Michael J. Fox Foundation. Real-world cohorts are the Optum Integrated Claims-electronic health records (N = 157,475), representing wide-scale linked medical and claims data and de-identified data from Mass General Brigham (MGB, N = 22,949), an academic hospital system. Structured, de-identified electronic health records data at MGB are supplemented using a manually validated natural language processing with a large language model to extract measurements of PD progression. Motor and cognitive progression scores change more rapidly in MGB than HBS (median survival until H&Y 3: 5.6 years vs. >10, p < 0.001; mini-mental state exam median decline 0.28 vs. 0.11, p < 0.001; and clinically recognized cognitive decline, p = 0.001). In real-world populations, patients are diagnosed more than eleven years later (RWD mean of 72.2 vs. research mean of 60.4, p < 0.001). After diagnosis, in real-world cohorts, treatment with PD medications has initiated an average of 2.3 years later (95% CI: [2.1-2.4]; p < 0.001). This study provides a detailed characterization of Parkinson's progression in diverse populations. It delineates systemic divergences in the patient populations enrolled in research settings vs. patients in the real-world. These divergences are likely due to a combination of selection bias and real population differences, but exact attribution of the causes is challenging. This study emphasizes a need to utilize multiple data sources and to diligently consider potential biases when planning, choosing data sources, and performing downstream tasks and analyses.

Disease progression strikingly differs in research and real-world Parkinson's populations.

Characterization of Parkinson's disease (PD) progression using real-world evidence could guide clinical trial design and identify subpopulations. Efforts to curate research populations, the increasing availability of real-world data and recent advances in natural language processing, particularly large language models, allow for a more granular comparison of populations and the methods of data collection describing these populations than previously possible. This study includes two research populations and two real-world data derived (RWD) populations. The research populations are the Harvard Biomarkers Study (HBS, N = 935), a longitudinal biomarkers cohort study with in-person structured study visits; and Fox Insights (N = 36,660), an online self-survey-based research study of the Michael J. Fox Foundation. Real-world cohorts are the Optum Integrated Claims-electronic health records (N = 157,475), representing wide-scale linked medical and claims data and de-identified data from Mass General Brigham (MGB, N = 22,949), an academic hospital system. Structured, de-identified electronic health records data at MGB are supplemented using natural language processing with a large language model to extract measurements of PD progression. This extraction process is manually validated for accuracy. Motor and cognitive progression scores change more rapidly in MGB than HBS (median survival until H&Y 3: 5.6 years vs. >10, p<0.001; mini-mental state exam median decline 0.28 vs. 0.11, p<0.001; and clinically recognized cognitive decline, p=0.001). In the real-world populations, patients are diagnosed more than eleven years later (RWD mean of 72.2 vs. research mean of 60.4, p<0.001). After diagnosis, in real-world cohorts, treatment with PD medications is initiated 2.3 years later on average (95% CI: [2.1-2.4]; p<0.001). This study provides a detailed characterization of Parkinson's progression in diverse populations. It delineates systemic divergences in the patient populations enrolled in research settings vs. patients in the real world. These divergences are likely due to a combination of selection bias and real population differences, but exact attribution of the causes is challenging using existing data. This study emphasizes a need to utilize multiple data sources and to diligently consider potential biases when planning, choosing data sources, and performing downstream tasks and analyses.

Zero-shot interpretable phenotyping of postpartum hemorrhage using large language models.

Many areas of medicine would benefit from deeper, more accurate phenotyping, but there are limited approaches for phenotyping using clinical notes without substantial annotated data. Large language models (LLMs) have demonstrated immense potential to adapt to novel tasks with no additional training by specifying task-specific instructions. Here we report the performance of a publicly available LLM, Flan-T5, in phenotyping patients with postpartum hemorrhage (PPH) using discharge notes from electronic health records (n = 271,081). The language model achieves strong performance in extracting 24 granular concepts associated with PPH. Identifying these granular concepts accurately allows the development of interpretable, complex phenotypes and subtypes. The Flan-T5 model achieves high fidelity in phenotyping PPH (positive predictive value of 0.95), identifying 47% more patients with this complication compared to the current standard of using claims codes. This LLM pipeline can be used reliably for subtyping PPH and outperforms a claims-based approach on the three most common PPH subtypes associated with uterine atony, abnormal placentation, and obstetric trauma. The advantage of this approach to subtyping is its interpretability, as each concept contributing to the subtype determination can be evaluated. Moreover, as definitions may change over time due to new guidelines, using granular concepts to create complex phenotypes enables prompt and efficient updating of the algorithm. Using this language modelling approach enables rapid phenotyping without the need for any manually annotated training data across multiple clinical use cases.

Predicting seizure recurrence after an initial seizure-like episode from routine clinical notes using large language models: a retrospective cohort study.

BACKGROUND: The evaluation and management of first-time seizure-like events in children can be difficult because these episodes are not always directly observed and might be epileptic seizures or other conditions (seizure mimics). We aimed to evaluate whether machine learning models using real-world data could predict seizure recurrence after an initial seizure-like event. METHODS: This retrospective cohort study compared models trained and evaluated on two separate datasets between Jan 1, 2010, and Jan 1, 2020: electronic medical records (EMRs) at Boston Children's Hospital and de-identified, patient-level, administrative claims data from the IBM MarketScan research database. The study population comprised patients with an initial diagnosis of either epilepsy or convulsions before the age of 21 years, based on International Classification of Diseases, Clinical Modification (ICD-CM) codes. We compared machine learning-based predictive modelling using structured data (logistic regression and XGBoost) with emerging techniques in natural language processing by use of large language models. FINDINGS: The primary cohort comprised 14 021 patients at Boston Children's Hospital matching inclusion criteria with an initial seizure-like event and the comparison cohort comprised 15 062 patients within the IBM MarketScan research database. Seizure recurrence based on a composite expert-derived definition occurred in 57% of patients at Boston Children's Hospital and 63% of patients within IBM MarketScan. Large language models with additional domain-specific and location-specific pre-training on patients excluded from the study (F1-score 0·826 [95% CI 0·817-0·835], AUC 0·897 [95% CI 0·875-0·913]) performed best. All large language models, including the base model without additional pre-training (F1-score 0·739 [95% CI 0·738-0·741], AUROC 0·846 [95% CI 0·826-0·861]) outperformed models trained with structured data. With structured data only, XGBoost outperformed logistic regression and XGBoost models trained with the Boston Children's Hospital EMR (logistic regression: F1-score 0·650 [95% CI 0·643-0·657], AUC 0·694 [95% CI 0·685-0·705], XGBoost: F1-score 0·679 [0·676-0·683], AUC 0·725 [0·717-0·734]) performed similarly to models trained on the IBM MarketScan database (logistic regression: F1-score 0·596 [0·590-0·601], AUC 0·670 [0·664-0·675], XGBoost: F1-score 0·678 [0·668-0·687], AUC 0·710 [0·703-0·714]). INTERPRETATION: Physician's clinical notes about an initial seizure-like event include substantial signals for prediction of seizure recurrence, and additional domain-specific and location-specific pre-training can significantly improve the performance of clinical large language models, even for specialised cohorts. FUNDING: UCB, National Institute of Neurological Disorders and Stroke (US National Institutes of Health).

Zero-shot Interpretable Phenotyping of Postpartum Hemorrhage Using Large Language Models.

Many areas of medicine would benefit from deeper, more accurate phenotyping, but there are limited approaches for phenotyping using clinical notes without substantial annotated data. Large language models (LLMs) have demonstrated immense potential to adapt to novel tasks with no additional training by specifying task-specific i nstructions. We investigated the per-formance of a publicly available LLM, Flan-T5, in phenotyping patients with postpartum hemorrhage (PPH) using discharge notes from electronic health records ( n =271,081). The language model achieved strong performance in extracting 24 granular concepts associated with PPH. Identifying these granular concepts accurately allowed the development of inter-pretable, complex phenotypes and subtypes. The Flan-T5 model achieved high fidelity in phenotyping PPH (positive predictive value of 0.95), identifying 47% more patients with this complication compared to the current standard of using claims codes. This LLM pipeline can be used reliably for subtyping PPH and outperformed a claims-based approach on the three most common PPH subtypes associated with uterine atony, abnormal placentation, and obstetric trauma. The advantage of this approach to subtyping is its interpretability, as each concept contributing to the subtype determination can be evaluated. Moreover, as definitions may change over time due to new guidelines, using granular concepts to create complex phenotypes enables prompt and efficient updating of the algorithm. Using this lan-guage modelling approach enables rapid phenotyping without the need for any manually annotated training data across multiple clinical use cases.

Generate Analysis-Ready Data for Real-world Evidence: Tutorial for Harnessing Electronic Health Records With Advanced Informatic Technologies.

Although randomized controlled trials (RCTs) are the gold standard for establishing the efficacy and safety of a medical treatment, real-world evidence (RWE) generated from real-world data has been vital in postapproval monitoring and is being promoted for the regulatory process of experimental therapies. An emerging source of real-world data is electronic health records (EHRs), which contain detailed information on patient care in both structured (eg, diagnosis codes) and unstructured (eg, clinical notes and images) forms. Despite the granularity of the data available in EHRs, the critical variables required to reliably assess the relationship between a treatment and clinical outcome are challenging to extract. To address this fundamental challenge and accelerate the reliable use of EHRs for RWE, we introduce an integrated data curation and modeling pipeline consisting of 4 modules that leverage recent advances in natural language processing, computational phenotyping, and causal modeling techniques with noisy data. Module 1 consists of techniques for data harmonization. We use natural language processing to recognize clinical variables from RCT design documents and map the extracted variables to EHR features with description matching and knowledge networks. Module 2 then develops techniques for cohort construction using advanced phenotyping algorithms to both identify patients with diseases of interest and define the treatment arms. Module 3 introduces methods for variable curation, including a list of existing tools to extract baseline variables from different sources (eg, codified, free text, and medical imaging) and end points of various types (eg, death, binary, temporal, and numerical). Finally, module 4 presents validation and robust modeling methods, and we propose a strategy to create gold-standard labels for EHR variables of interest to validate data curation quality and perform subsequent causal modeling for RWE. In addition to the workflow proposed in our pipeline, we also develop a reporting guideline for RWE that covers the necessary information to facilitate transparent reporting and reproducibility of results. Moreover, our pipeline is highly data driven, enhancing study data with a rich variety of publicly available information and knowledge sources. We also showcase our pipeline and provide guidance on the deployment of relevant tools by revisiting the emulation of the Clinical Outcomes of Surgical Therapy Study Group Trial on laparoscopy-assisted colectomy versus open colectomy in patients with early-stage colon cancer. We also draw on existing literature on EHR emulation of RCTs together with our own studies with the Mass General Brigham EHR.

Developing better digital health measures of Parkinson's disease using free living data and a crowdsourced data analysis challenge.

One of the promising opportunities of digital health is its potential to lead to more holistic understandings of diseases by interacting with the daily life of patients and through the collection of large amounts of real-world data. Validating and benchmarking indicators of disease severity in the home setting is difficult, however, given the large number of confounders present in the real world and the challenges in collecting ground truth data in the home. Here we leverage two datasets collected from patients with Parkinson's disease, which couples continuous wrist-worn accelerometer data with frequent symptom reports in the home setting, to develop digital biomarkers of symptom severity. Using these data, we performed a public benchmarking challenge in which participants were asked to build measures of severity across 3 symptoms (on/off medication, dyskinesia, and tremor). 42 teams participated and performance was improved over baseline models for each subchallenge. Additional ensemble modeling across submissions further improved performance, and the top models validated in a subset of patients whose symptoms were observed and rated by trained clinicians.

Multi-center retrospective cohort study applying deep learning to electrocardiograms to identify left heart valvular dysfunction.

BACKGROUND: Aortic Stenosis and Mitral Regurgitation are common valvular conditions representing a hidden burden of disease within the population. The aim of this study was to develop and validate deep learning-based screening and diagnostic tools that can help guide clinical decision making. METHODS: In this multi-center retrospective cohort study, we acquired Transthoracic Echocardiogram reports from five Mount Sinai hospitals within New York City representing a demographically diverse cohort of patients. We developed a Natural Language Processing pipeline to extract ground-truth labels about valvular status and paired these to Electrocardiograms (ECGs). We developed and externally validated deep learning models capable of detecting valvular disease, in addition to considering scenarios of clinical deployment. RESULTS: We use 617,338 ECGs paired to transthoracic echocardiograms from 123,096 patients to develop a deep learning model for detection of Mitral Regurgitation. Area Under Receiver Operating Characteristic curve (AUROC) is 0.88 (95% CI:0.88-0.89) in internal testing, and 0.81 (95% CI:0.80-0.82) in external validation. To develop a model for detection of Aortic Stenosis, we use 617,338 Echo-ECG pairs for 128,628 patients. AUROC is 0.89 (95% CI: 0.88-0.89) in internal testing, going to 0.86 (95% CI: 0.85-0.87) in external validation. The model's performance increases leading up to the time of the diagnostic echo, and it performs well in validation against requirement of Transcatheter Aortic Valve Replacement procedures. CONCLUSIONS: Deep learning based tools can increase the amount of information extracted from ubiquitous investigations such as the ECG. Such tools are inexpensive, can help in earlier disease detection, and potentially improve prognosis.

The valves of the heart have flaps that open and close when the heart beats to maintain the flow of blood in the correct direction. Valvular disease, such as backflow or narrowing, puts additional strain upon heart muscles which can lead to heart failure. Usually, these conditions are diagnosed by doing an echocardiogram, an ultrasound scan of the heart and nearby blood vessels. The electrocardiogram (ECG) records the electrical signal generated by the heart and can be obtained more easily. We used deep learning neural networks, self-learning computer algorithms which excel at finding patterns within complex data. This enabled us to develop computer software able to diagnose valvular disease from ECGs. Earlier detection of such disease can help in improving overall outcome, while also reducing costs related to treatment.

Severity of Epilepsy and Response to Antiseizure Medications in Individuals With Multiple Sclerosis: Analysis of a Real-World Dataset.

Background and Objectives: Epilepsy is an important comorbidity that affects outcomes for people with multiple sclerosis (MS). However, it is unclear whether seizure severity among individuals with coexistence of MS and epilepsy (MS + E) is higher than in those with other focal epilepsies. Our goal was to compare the overall severity of epilepsy in individuals with MS + E vs those with focal epilepsy without MS (E - MS), as defined by seizure-related health care utilization, frequency and duration of status epilepticus, and frequency of antiseizure medication (ASM) regimen changes. Methods: In this hypothesis-generating study, we analyzed a US commercial nationwide deidentified claims data set with >86 million individuals between January 1, 2008, and August 31, 2019. Using validated algorithms, we identified adults with E - MS and those with MS + E. We compared the number and length of seizure-related hospital admissions, the number of claims and unique days with claims for status epilepticus, and the rates of ASM regimen changes between the MS + E and E - MS groups. Results: During the study period, 66,708 individuals with E - MS and 537 with MS + E had ≥2 years of coverage after their initial diagnosis of epilepsy. There was no difference between the MS + E and E - MS groups in the percentage of individuals admitted for seizures and/or status epilepticus. However, MS + E with seizure-related admissions had more admissions and longer hospital stays than those with E - MS. MS + E who experienced status epilepticus had more unique days with status epilepticus claims compared with E - MS. MS + E were more likely to have ASM regimen changes in 2 years after the initial diagnosis of epilepsy and had more ASM changes during 2 years compared with E - MS. Among individuals with MS + E, there were no differences in our measures of seizure severity for those treated with sodium channel blockers/modulators vs other ASM classes. Discussion: This study supports the notion that individuals with MS + E can have more severe epilepsy than those with E - MS. Seizure severity among individuals with MS + E treated with sodium channel blockers/modulators vs other ASM classes shows no significant differences. Classification of Evidence: This study provides Class III evidence that individuals with MS + E can have more severe epilepsy than those with E - MS.

International comparisons of laboratory values from the 4CE collaborative to predict COVID-19 mortality.

Given the growing number of prediction algorithms developed to predict COVID-19 mortality, we evaluated the transportability of a mortality prediction algorithm using a multi-national network of healthcare systems. We predicted COVID-19 mortality using baseline commonly measured laboratory values and standard demographic and clinical covariates across healthcare systems, countries, and continents. Specifically, we trained a Cox regression model with nine measured laboratory test values, standard demographics at admission, and comorbidity burden pre-admission. These models were compared at site, country, and continent level. Of the 39,969 hospitalized patients with COVID-19 (68.6% male), 5717 (14.3%) died. In the Cox model, age, albumin, AST, creatine, CRP, and white blood cell count are most predictive of mortality. The baseline covariates are more predictive of mortality during the early days of COVID-19 hospitalization. Models trained at healthcare systems with larger cohort size largely retain good transportability performance when porting to different sites. The combination of routine laboratory test values at admission along with basic demographic features can predict mortality in patients hospitalized with COVID-19. Importantly, this potentially deployable model differs from prior work by demonstrating not only consistent performance but also reliable transportability across healthcare systems in the US and Europe, highlighting the generalizability of this model and the overall approach.

Temporal Trends in Clinical Evidence of 5-Year Survival Within Electronic Health Records Among Patients With Early-Stage Colon Cancer Managed With Laparoscopy-Assisted Colectomy vs Open Colectomy.

Importance: Temporal shifts in clinical knowledge and practice need to be adjusted for in treatment outcome assessment in clinical evidence. Objective: To use electronic health record (EHR) data to (1) assess the temporal trends in treatment decisions and patient outcomes and (2) emulate a randomized clinical trial (RCT) using EHR data with proper adjustment for temporal trends. Design, Setting, and Participants: The Clinical Outcomes of Surgical Therapy (COST) Study Group Trial assessing overall survival of patients with stages I to III early-stage colon cancer was chosen as the target trial. The RCT was emulated using EHR data of patients from a single health care system cohort who underwent colectomy for early-stage colon cancer from January 1, 2006, to December 31, 2017, and were followed up to January 1, 2020, from Mass General Brigham. Analyses were conducted from December 2, 2019, to January 24, 2022. Exposures: Laparoscopy-assisted colectomy (LAC) vs open colectomy (OC). Main Outcomes and Measures: The primary outcome was 5-year overall survival. To address confounding in the emulation, pretreatment variables were selected and adjusted. The temporal trends were adjusted by stratification of the calendar year when the colectomies were performed with cotraining across strata. Results: A total of 943 patients met key RCT eligibility criteria in the EHR emulation cohort, including 518 undergoing LAC (median age, 63 [range, 20-95] years; 268 [52%] women; 121 [23%] with stage I, 165 [32%] with stage II, and 232 [45%] with stage III cancer; 32 [6%] with colon adhesion; 278 [54%] with right-sided colon cancer; 18 [3%] with left-sided colon cancer; and 222 [43%] with sigmoid colon cancer) and 425 undergoing OC (median age, 65 [range, 28-99] years; 223 [52%] women; 61 [14%] with stage I, 153 [36%] with stage II, and 211 [50%] with stage III cancer; 39 [9%] with colon adhesion; 202 [47%] with right-sided colon cancer; 39 [9%] with left-sided colon cancer; and 201 [47%] with sigmoid colon cancer). Tests for temporal trends in treatment assignment (χ2 = 60.3; P < .001) and overall survival (χ2 = 137.2; P < .001) were significant. The adjusted EHR emulation reached the same conclusion as the RCT: LAC is not inferior to OC in overall survival rate with risk difference at 5 years of -0.007 (95% CI, -0.070 to 0.057). The results were consistent for stratified analysis within each temporal period. Conclusions and Relevance: These findings suggest that confounding bias from temporal trends should be considered when conducting clinical evidence studies with long time spans. Stratification of calendar time and cotraining of models is one solution. With proper adjustment, clinical evidence may supplement RCTs in the assessment of treatment outcome over time.

Does Modulation of an Epigenetic Clock Define a Geroprotector?

There is growing interest in the development of interventions (e.g., drugs, diets, dietary supplements, behavioral therapies, etc.) that can enhance health during the aging process, prevent or delay multiple age-related diseases, and ultimately extend lifespan. However, proving that such 'geroprotectors' do what they are hypothesized to do in relevant clinical trials is not trivial. We briefly discuss some of the more salient issues surrounding the design and interpretation of clinical trials of geroprotectors, including, importantly, how one defines a geroprotector. We also discuss whether emerging surrogate endpoints, such as epigenetic clocks, should be treated as primary or secondary endpoints in such trials. Simply put, geroprotectors should provide overt health and disease prevention benefits but the time-dependent relationships between epigenetic clocks and health-related phenomena are complex and in need of further scrutiny. Therefore, studies that enable understanding of the relationships between epigenetic clocks and disease processes while simultaneously testing the efficacy of a candidate geroprotector are crucial to move the field forward.

Packaging Biocomputing Software to Maximize Distribution and Reuse.

The majority of publications in computational biology and biocomputing develop or apply software approaches to relevant biological problems to some degree. While journals and conferences often prompt authors to make their source code available, these are often only basic requirements. Investigators often wish their software and tools were widely usable to the scientific community, but there are limited resources available to maximize the distribution and provide easy use of developed software. Even when authors adhere to standards of source code availability, the growing problem of system configuration issues, language and library version conflicts, and other implementation issues often impede the broad distribution, availability of software tools, and reproducibility of research. There are a variety of solutions to these implementation issues, but the learning curve for applying these solutions can be steep. This tutorial demonstrates tools and approaches for packaging and distribution of published code, and provides methodological practices for the broad and open sharing of new biocomputing software.

Multinational characterization of neurological phenotypes in patients hospitalized with COVID-19.

Neurological complications worsen outcomes in COVID-19. To define the prevalence of neurological conditions among hospitalized patients with a positive SARS-CoV-2 reverse transcription polymerase chain reaction test in geographically diverse multinational populations during early pandemic, we used electronic health records (EHR) from 338 participating hospitals across 6 countries and 3 continents (January-September 2020) for a cross-sectional analysis. We assessed the frequency of International Classification of Disease code of neurological conditions by countries, healthcare systems, time before and after admission for COVID-19 and COVID-19 severity. Among 35,177 hospitalized patients with SARS-CoV-2 infection, there was an increase in the proportion with disorders of consciousness (5.8%, 95% confidence interval [CI] 3.7-7.8%, pFDR < 0.001) and unspecified disorders of the brain (8.1%, 5.7-10.5%, pFDR < 0.001) when compared to the pre-admission proportion. During hospitalization, the relative risk of disorders of consciousness (22%, 19-25%), cerebrovascular diseases (24%, 13-35%), nontraumatic intracranial hemorrhage (34%, 20-50%), encephalitis and/or myelitis (37%, 17-60%) and myopathy (72%, 67-77%) were higher for patients with severe COVID-19 when compared to those who never experienced severe COVID-19. Leveraging a multinational network to capture standardized EHR data, we highlighted the increased prevalence of central and peripheral neurological phenotypes in patients hospitalized with COVID-19, particularly among those with severe disease.

Illustrating potential effects of alternate control populations on real-world evidence-based statistical analyses.

OBJECTIVE: Case-control study designs are commonly used in retrospective analyses of real-world evidence (RWE). Due to the increasingly wide availability of RWE, it can be difficult to determine whether findings are robust or the result of testing multiple hypotheses. MATERIALS AND METHODS: We investigate the potential effects of modifying cohort definitions in a case-control association study between depression and type 2 diabetes mellitus. We used a large (>75 million individuals) de-identified administrative claims database to observe the effects of minor changes to the requirements of glucose and hemoglobin A1c tests in the control group. RESULTS: We found that small permutations to the criteria used to define the control population result in significant shifts in both the demographic structure of the identified cohort as well as the odds ratio of association. These differences remain present when testing against age- and sex-matched controls. DISCUSSION: Analyses of RWE need to be carefully designed to avoid issues of multiple testing. Minor changes to control cohorts can lead to significantly different results and have the potential to alter even prospective studies through selection bias. CONCLUSION: We believe this work offers strong support for the need for robust guidelines, best practices, and regulations around the use of observational RWE for clinical or regulatory decision-making.

Accelerating diagnosis of Parkinson's disease through risk prediction.

BACKGROUND: Characterization of prediagnostic Parkinson's Disease (PD) and early prediction of subsequent development are critical for preventive interventions, risk stratification and understanding of disease pathology. This study aims to characterize the role of the prediagnostic period in PD and, using selected features from this period as novel interception points, construct a prediction model to accelerate the diagnosis in a real-world setting. METHODS: We constructed two sets of machine learning models: a retrospective approach highlighting exposures up to 5 years prior to PD diagnosis, and an alternative model that prospectively predicted future PD diagnosis from all individuals at their first diagnosis of a gait or tremor disorder, these being features that appeared to represent the initiation of a differential diagnostic window. RESULTS: We found many novel features captured by the retrospective models; however, the high accuracy was primarily driven from surrogate diagnoses for PD, such as gait and tremor disorders, suggesting the presence of a distinctive differential diagnostic period when the clinician already suspected PD. The model utilizing a gait/tremor diagnosis as the interception point, achieved a validation AUC of 0.874 with potential time compression to a future PD diagnosis of more than 300 days. Comparisons of predictive diagnoses between the prospective and prediagnostic cohorts suggest the presence of distinctive trajectories of PD progression based on comorbidity profiles. CONCLUSIONS: Overall, our machine learning approach allows for both guiding clinical decisions such as the initiation of neuroprotective interventions and importantly, the possibility of earlier diagnosis for clinical trials for disease modifying therapies.

Multinational Prevalence of Neurological Phenotypes in Patients Hospitalized with COVID-19.

OBJECTIVE: Neurological complications can worsen outcomes in COVID-19. We defined the prevalence of a wide range of neurological conditions among patients hospitalized with COVID-19 in geographically diverse multinational populations. METHODS: Using electronic health record (EHR) data from 348 participating hospitals across 6 countries and 3 continents between January and September 2020, we performed a cross-sectional study of hospitalized adult and pediatric patients with a positive SARS-CoV-2 reverse transcription polymerase chain reaction test, both with and without severe COVID-19. We assessed the frequency of each disease category and 3-character International Classification of Disease (ICD) code of neurological diseases by countries, sites, time before and after admission for COVID-19, and COVID-19 severity. RESULTS: Among the 35,177 hospitalized patients with SARS-CoV-2 infection, there was increased prevalence of disorders of consciousness (5.8%, 95% confidence interval [CI]: 3.7%-7.8%, p FDR <.001) and unspecified disorders of the brain (8.1%, 95%CI: 5.7%-10.5%, p FDR <.001), compared to pre-admission prevalence. During hospitalization, patients who experienced severe COVID-19 status had 22% (95%CI: 19%-25%) increase in the relative risk (RR) of disorders of consciousness, 24% (95%CI: 13%-35%) increase in other cerebrovascular diseases, 34% (95%CI: 20%-50%) increase in nontraumatic intracranial hemorrhage, 37% (95%CI: 17%-60%) increase in encephalitis and/or myelitis, and 72% (95%CI: 67%-77%) increase in myopathy compared to those who never experienced severe disease. INTERPRETATION: Using an international network and common EHR data elements, we highlight an increase in the prevalence of central and peripheral neurological phenotypes in patients hospitalized with SARS-CoV-2 infection, particularly among those with severe disease.

Machine learning for patient risk stratification: standing on, or looking over, the shoulders of clinicians?

Machine learning can help clinicians to make individualized patient predictions only if researchers demonstrate models that contribute novel insights, rather than learning the most likely next step in a set of actions a clinician will take. We trained deep learning models using only clinician-initiated, administrative data for 42.9 million admissions using three subsets of data: demographic data only, demographic data and information available at admission, and the previous data plus charges recorded during the first day of admission. Models trained on charges during the first day of admission achieve performance close to published full EMR-based benchmarks for inpatient outcomes: inhospital mortality (0.89 AUC), prolonged length of stay (0.82 AUC), and 30-day readmission rate (0.71 AUC). Similar performance between models trained with only clinician-initiated data and those trained with full EMR data purporting to include information about patient state and physiology should raise concern in the deployment of these models. Furthermore, these models exhibited significant declines in performance when evaluated over only myocardial infarction (MI) patients relative to models trained over MI patients alone, highlighting the importance of physician diagnosis in the prognostic performance of these models. These results provide a benchmark for predictive accuracy trained only on prior clinical actions and indicate that models with similar performance may derive their signal by looking over clinician's shoulders-using clinical behavior as the expression of preexisting intuition and suspicion to generate a prediction. For models to guide clinicians in individual decisions, performance exceeding these benchmarks is necessary.