Precision Phenotyping for Curating Research Cohorts of Patients with Post-Acute Sequelae of COVID-19 (PASC) as a Diagnosis of Exclusion

Scalable identification of patients with the post-acute sequelae of COVID-19 (PASC) is challenging due to a lack of reproducible precision phenotyping algorithms and the suboptimal accuracy, demographic biases, and underestimation of the PASC diagnosis code (ICD-10 U09.9). In a retrospective case-control study, we developed a precision phenotyping algorithm for identifying research cohorts of PASC patients, defined as a diagnosis of exclusion. We used longitudinal electronic health records (EHR) data from over 295 thousand patients from 14 hospitals and 20 community health centers in Massachusetts. The algorithm employs an attention mechanism to exclude sequelae that prior conditions can explain. We performed independent chart reviews to tune and validate our precision phenotyping algorithm. Our PASC phenotyping algorithm improves precision and prevalence estimation and reduces bias in identifying Long COVID patients compared to the U09.9 diagnosis code. Our algorithm identified a PASC research cohort of over 24 thousand patients (compared to about 6 thousand when using the U09.9 diagnosis code), with a 79.9 percent precision (compared to 77.8 percent from the U09.9 diagnosis code). Our estimated prevalence of PASC was 22.8 percent, which is close to the national estimates for the region. We also provide an in-depth analysis outlining the clinical attributes, encompassing identified lingering effects by organ, comorbidity profiles, and temporal differences in the risk of PASC. The PASC phenotyping method presented in this study boasts superior precision, accurately gauges the prevalence of PASC without underestimating it, and exhibits less bias in pinpointing Long COVID patients. The PASC cohort derived from our algorithm will serve as a springboard for delving into Long COVID's genetic, metabolomic, and clinical intricacies, surmounting the constraints of recent PASC cohort studies, which were hampered by their limited size and available outcome data.

Association of GLP-1 Receptor Agonists with Chronic Obstructive Pulmonary Disease Exacerbations among Patients with Type 2 Diabetes

Rationale: Patients with chronic obstructive pulmonary disease (COPD) and type 2 diabetes (T2D) have worse clinical outcomes compared with patients without metabolic dysregulation. GLP-1 (glucagon-like peptide 1) receptor agonists (GLP-1RAs) reduce asthma exacerbation risk and improve FVC in patients with COPD. Objectives: To determine whether GLP-1RA use is associated with reduced COPD exacerbation rates, and severe and moderate exacerbation risk, compared with other T2D therapies. Methods: A retrospective, observational, electronic health records-based study was conducted using an active comparator, new-user design of 1,642 patients with COPD in a U.S. health system from 2012 to 2022. The COPD cohort was identified using a previously validated machine learning algorithm that includes a natural language processing tool. Exposures were defined as prescriptions for GLP-1RAs (reference group), DPP-4 (dipeptidyl peptidase 4) inhibitors (DPP-4is), SGLT2 (sodium-glucose cotransporter 2) inhibitors, or sulfonylureas. Measurements and Main Results: Unadjusted COPD exacerbation counts were lower in GLP-1RA users. Adjusted exacerbation rates were significantly higher in DPP-4i (incidence rate ratio, 1.48 [95% confidence interval, 1.08-2.04]; P = 0.02) and sulfonylurea (incidence rate ratio, 2.09 [95% confidence interval, 1.62-2.69]; P < 0.0001) users compared with GLP-1RA users. GLP-1RA use was also associated with significantly reduced risk of severe exacerbations compared with DPP-4i and sulfonylurea use, and of moderate exacerbations compared with sulfonylurea use. After adjustment for clinical covariates, moderate exacerbation risk was also lower in GLP-1RA users compared with DPP-4i users. No statistically significant difference in exacerbation outcomes was seen between GLP-1RA and SGLT2 inhibitor users. Conclusions: Prospective studies of COPD exacerbations in patients with comorbid T2D are warranted. Additional research may elucidate the mechanisms underlying these observed associations with T2D medications.

Characterization of long COVID temporal sub-phenotypes by distributed representation learning from electronic health record data: a cohort study

Background

Characterizing Post-Acute Sequelae of COVID (SARS-CoV-2 Infection), or PASC has been challenging due to the multitude of sub-phenotypes, temporal attributes, and definitions. Scalable characterization of PASC sub-phenotypes can enhance screening capacities, disease management, and treatment planning.

Methods

We conducted a retrospective multi-centre observational cohort study, leveraging longitudinal electronic health record (EHR) data of 30,422 patients from three healthcare systems in the Consortium for the Clinical Characterization of COVID-19 by EHR (4CE). From the total cohort, we applied a deductive approach on 12,424 individuals with follow-up data and developed a distributed representation learning process for providing augmented definitions for PASC sub-phenotypes.

Findings

Our framework characterized seven PASC sub-phenotypes. We estimated that on average 15.7% of the hospitalized COVID-19 patients were likely to suffer from at least one PASC symptom and almost 5.98%, on average, had multiple symptoms. Joint pain and dyspnea had the highest prevalence, with an average prevalence of 5.45% and 4.53%, respectively.

Interpretation

We provided a scalable framework to every participating healthcare system for estimating PASC sub-phenotypes prevalence and temporal attributes, thus developing a unified model that characterizes augmented sub-phenotypes across the different systems.

Funding

Authors are supported by National Institute of Allergy and Infectious Diseases, National Institute on Aging, National Center for Advancing Translational Sciences, National Medical Research Council, National Institute of Neurological Disorders and Stroke, European Union, National Institutes of Health, National Center for Advancing Translational Sciences.

A retrospective cohort analysis leveraging augmented intelligence to characterize long COVID in the electronic health record: A precision medicine framework

Physical and psychological symptoms lasting months following an acute COVID-19 infection are now recognized as post-acute sequelae of COVID-19 (PASC). Accurate tools for identifying such patients could enhance screening capabilities for the recruitment for clinical trials, improve the reliability of disease estimates, and allow for more accurate downstream cohort analysis. In this retrospective cohort study, we analyzed the EHR of hospitalized COVID-19 patients across three healthcare systems to develop a pipeline for better identifying patients with persistent PASC symptoms (dyspnea, fatigue, or joint pain) after their SARS-CoV-2 infection. We implemented distributed representation learning powered by the Machine Learning for modeling Health Outcomes (MLHO) to identify novel EHR features that could suggest PASC symptoms outside of typical diagnosis codes. MLHO applies an entropy-based feature selection and boosting algorithms for representation mining. These improved definitions were then used for estimating PASC among hospitalized patients. 30,422 hospitalized patients were diagnosed with COVID-19 across three healthcare systems between March 13, 2020 and February 28, 2021. The mean age of the population was 62.3 years (SD, 21.0 years) and 15,124 (49.7%) were female. We implemented the distributed representation learning technique to augment PASC definitions. These definitions were found to have positive predictive values of 0.73, 0.74, and 0.91 for dyspnea, fatigue, and joint pain, respectively. We estimated that 25 percent (CI 95%: 6-48), 11 percent (CI 95%: 6-15), and 13 percent (CI 95%: 8-17) of hospitalized COVID-19 patients will have dyspnea, fatigue, and joint pain, respectively, 3 months or longer after a COVID-19 diagnosis. We present a validated framework for screening and identifying patients with PASC in the EHR and then use the tool to estimate its prevalence among hospitalized COVID-19 patients.

Severity of COVID-19-Related Illness in Massachusetts, July 2021 to December 2022

This cohort study uses hospitalization and 30-day mortality risks to create a temporal profile of the severity of COVID-19 in Massachusetts from July 2021 to December 2022.

Informative missingness: What can we learn from patterns in missing laboratory data in the electronic health record?

BACKGROUND

In electronic health records, patterns of missing laboratory test results could capture patients' course of disease as well as ​​reflect clinician's concerns or worries for possible conditions. These patterns are often understudied and overlooked. This study aims to identify informative patterns of missingness among laboratory data collected across 15 healthcare system sites in three countries for COVID-19 inpatients.

METHODS

We collected and analyzed demographic, diagnosis, and laboratory data for 69,939 patients with positive COVID-19 PCR tests across three countries from 1 January 2020 through 30 September 2021. We analyzed missing laboratory measurements across sites, missingness stratification by demographic variables, temporal trends of missingness, correlations between labs based on missingness indicators over time, and clustering of groups of labs based on their missingness/ordering pattern.

RESULTS

With these analyses, we identified mapping issues faced in seven out of 15 sites. We also identified nuances in data collection and variable definition for the various sites. Temporal trend analyses may support the use of laboratory test result missingness patterns in identifying severe COVID-19 patients. Lastly, using missingness patterns, we determined relationships between various labs that reflect clinical behaviors.

CONCLUSION

In this work, we use computational approaches to relate missingness patterns to hospital treatment capacity and highlight the heterogeneity of looking at COVID-19 over time and at multiple sites, where there might be different phases, policies, etc. Changes in missingness could suggest a change in a patient's condition, and patterns of missingness among laboratory measurements could potentially identify clinical outcomes. This allows sites to consider missing data as informative to analyses and help researchers identify which sites are better poised to study particular questions.

Estimates of SARS-CoV-2 Omicron BA.2 Subvariant Severity in New England

IMPORTANCE

The SARS-CoV-2 Omicron subvariant, BA.2, may be less severe than previous variants; however, confounding factors make interpreting the intrinsic severity challenging.

OBJECTIVE

To compare the adjusted risks of mortality, hospitalization, intensive care unit admission, and invasive ventilation between the BA.2 subvariant and the Omicron and Delta variants, after accounting for multiple confounders.

DESIGN, SETTING, AND PARTICIPANTS

This was a retrospective cohort study that applied an entropy balancing approach. Patients in a multicenter inpatient and outpatient system in New England with COVID-19 between March 3, 2020, and June 20, 2022, were identified.

EXPOSURES

Cases were assigned as being exposed to the Delta (B.1.617.2) variant, the Omicron (B.1.1.529) variant, or the Omicron BA.2 lineage subvariants.

MAIN OUTCOMES AND MEASURES

The primary study outcome planned before analysis was risk of 30-day mortality. Secondary outcomes included the risks of hospitalization, invasive ventilation, and intensive care unit admissions.

RESULTS

Of 102 315 confirmed COVID-19 cases (mean [SD] age, 44.2 [21.6] years; 63 482 women [62.0%]), 20 770 were labeled as Delta variants, 52 605 were labeled as the Omicron B.1.1.529 variant, and 28 940 were labeled as Omicron BA.2 subvariants. Patient cases were excluded if they occurred outside the prespecified temporal windows associated with the variants or had minimal longitudinal data in the Mass General Brigham system before COVID-19. Mortality rates were 0.7% for Delta (B.1.617.2), 0.4% for Omicron (B.1.1.529), and 0.3% for Omicron (BA.2). The adjusted odds ratio of mortality from the Delta variant compared with the Omicron BA.2 subvariants was 2.07 (95% CI, 1.04-4.10) and that of the original Omicron variant compared with the Omicron BA.2 subvariant was 2.20 (95% CI, 1.56-3.11). For all outcomes, the Omicron BA.2 subvariants were significantly less severe than that of the Omicron and Delta variants.

CONCLUSIONS AND RELEVANCE

In this cohort study, after having accounted for a variety of confounding factors associated with SARS-CoV-2 outcomes, the Omicron BA.2 subvariant was found to be intrinsically less severe than both the Delta and Omicron variants. With respect to these variants, the severity profile of SARS-CoV-2 appears to be diminishing after taking into account various factors including therapeutics, vaccinations, and prior infections.

International electronic health record-derived post-acute sequelae profiles of COVID-19 patients

The risk profiles of post-acute sequelae of COVID-19 (PASC) have not been well characterized in multi-national settings with appropriate controls. We leveraged electronic health record (EHR) data from 277 international hospitals representing 414,602 patients with COVID-19, 2.3 million control patients without COVID-19 in the inpatient and outpatient settings, and over 221 million diagnosis codes to systematically identify new-onset conditions enriched among patients with COVID-19 during the post-acute period. Compared to inpatient controls, inpatient COVID-19 cases were at significant risk for angina pectoris (RR 1.30, 95% CI 1.09–1.55), heart failure (RR 1.22, 95% CI 1.10–1.35), cognitive dysfunctions (RR 1.18, 95% CI 1.07–1.31), and fatigue (RR 1.18, 95% CI 1.07–1.30). Relative to outpatient controls, outpatient COVID-19 cases were at risk for pulmonary embolism (RR 2.10, 95% CI 1.58–2.76), venous embolism (RR 1.34, 95% CI 1.17–1.54), atrial fibrillation (RR 1.30, 95% CI 1.13–1.50), type 2 diabetes (RR 1.26, 95% CI 1.16–1.36) and vitamin D deficiency (RR 1.19, 95% CI 1.09–1.30). Outpatient COVID-19 cases were also at risk for loss of smell and taste (RR 2.42, 95% CI 1.90–3.06), inflammatory neuropathy (RR 1.66, 95% CI 1.21–2.27), and cognitive dysfunction (RR 1.18, 95% CI 1.04–1.33). The incidence of post-acute cardiovascular and pulmonary conditions decreased across time among inpatient cases while the incidence of cardiovascular, digestive, and metabolic conditions increased among outpatient cases. Our study, based on a federated international network, systematically identified robust conditions associated with PASC compared to control groups, underscoring the multifaceted cardiovascular and neurological phenotype profiles of PASC.

Distinguishing Admissions Specifically for COVID-19 From Incidental SARS-CoV-2 Admissions: National Retrospective Electronic Health Record Study

BACKGROUND

Admissions are generally classified as COVID-19 hospitalizations if the patient has a positive SARS-CoV-2 polymerase chain reaction (PCR) test. However, because 35% of SARS-CoV-2 infections are asymptomatic, patients admitted for unrelated indications with an incidentally positive test could be misclassified as a COVID-19 hospitalization. Electronic health record (EHR)-based studies have been unable to distinguish between a hospitalization specifically for COVID-19 versus an incidental SARS-CoV-2 hospitalization. Although the need to improve classification of COVID-19 versus incidental SARS-CoV-2 is well understood, the magnitude of the problems has only been characterized in small, single-center studies. Furthermore, there have been no peer-reviewed studies evaluating methods for improving classification.

OBJECTIVE

The aims of this study are to, first, quantify the frequency of incidental hospitalizations over the first 15 months of the pandemic in multiple hospital systems in the United States and, second, to apply electronic phenotyping techniques to automatically improve COVID-19 hospitalization classification.

METHODS

From a retrospective EHR-based cohort in 4 US health care systems in Massachusetts, Pennsylvania, and Illinois, a random sample of 1123 SARS-CoV-2 PCR-positive patients hospitalized from March 2020 to August 2021 was manually chart-reviewed and classified as "admitted with COVID-19" (incidental) versus specifically admitted for COVID-19 ("for COVID-19"). EHR-based phenotyping was used to find feature sets to filter out incidental admissions.

RESULTS

EHR-based phenotyped feature sets filtered out incidental admissions, which occurred in an average of 26% of hospitalizations (although this varied widely over time, from 0% to 75%). The top site-specific feature sets had 79%-99% specificity with 62%-75% sensitivity, while the best-performing across-site feature sets had 71%-94% specificity with 69%-81% sensitivity.

CONCLUSIONS

A large proportion of SARS-CoV-2 PCR-positive admissions were incidental. Straightforward EHR-based phenotypes differentiated admissions, which is important to assure accurate public health reporting and research.

An Objective Framework for Evaluating Unrecognized Bias in Medical AI Models Predicting COVID-19 Outcomes

OBJECTIVE

The increasing translation of artificial intelligence (AI)/machine learning (ML) models into clinical practice brings an increased risk of direct harm from modeling bias; however, bias remains incompletely measured in many medical AI applications. This article aims to provide a framework for objective evaluation of medical AI from multiple aspects, focusing on binary classification models.

MATERIALS AND METHODS

Using data from over 56 thousand Mass General Brigham (MGB) patients with confirmed severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), we evaluate unrecognized bias in four AI models developed during the early months of the pandemic in Boston, Massachusetts that predict risks of hospital admission, ICU admission, mechanical ventilation, and death after a SARS-CoV-2 infection purely based on their pre-infection longitudinal medical records. Models were evaluated both retrospectively and prospectively using model-level metrics of discrimination, accuracy, and reliability, and a novel individual-level metric for error.

RESULTS

We found inconsistent instances of model-level bias in the prediction models. From an individual-level aspect, however, we found most all models performing with slightly higher error rates for older patients.

DISCUSSION

While a model can be biased against certain protected groups (i.e., perform worse) in certain tasks, it can be at the same time biased towards another protected group (i.e., perform better). As such, current bias evaluation studies may lack a full depiction of the variable effects of a model on its subpopulations.

CONCLUSION

Only a holistic evaluation, a diligent search for unrecognized bias, can provide enough information for an unbiased judgment of AI bias that can invigorate follow-up investigations on identifying the underlying roots of bias and ultimately make a change.

Distinguishing Admissions Specifically for COVID-19 from Incidental SARS-CoV-2 Admissions: A National EHR Research Consortium Study

Admissions are generally classified as COVID-19 hospitalizations if the patient has a positive SARS-CoV-2 polymerase chain reaction (PCR) test. However, because 35% of SARS-CoV-2 infections are asymptomatic, patients admitted for unrelated indications with an incidentally positive test could be misclassified as a COVID-19 hospitalization. EHR-based studies have been unable to distinguish between a hospitalization specifically for COVID-19 versus an incidental SARS-CoV-2 hospitalization. From a retrospective EHR-based cohort in four US healthcare systems, a random sample of 1,123 SARS-CoV-2 PCR-positive patients hospitalized between 3/2020â€"8/2021 was manually chart-reviewed and classified as admitted-with-COVID-19 (incidental) vs. specifically admitted for COVID-19 (for-COVID-19). EHR-based phenotyped feature sets filtered out incidental admissions, which occurred in 26%. The top site-specific feature sets had 79-99% specificity with 62-75% sensitivity, while the best performing across-site feature set had 71-94% specificity with 69-81% sensitivity. A large proportion of SARS-CoV-2 PCR-positive admissions were incidental. Straightforward EHR-based phenotypes differentiated admissions, which is important to assure accurate public health reporting and research.

Evolving phenotypes of non-hospitalized patients that indicate long COVID

BACKGROUND

For some SARS-CoV-2 survivors, recovery from the acute phase of the infection has been grueling with lingering effects. Many of the symptoms characterized as the post-acute sequelae of COVID-19 (PASC) could have multiple causes or are similarly seen in non-COVID patients. Accurate identification of PASC phenotypes will be important to guide future research and help the healthcare system focus its efforts and resources on adequately controlled age- and gender-specific sequelae of a COVID-19 infection.

METHODS

In this retrospective electronic health record (EHR) cohort study, we applied a computational framework for knowledge discovery from clinical data, MLHO, to identify phenotypes that positively associate with a past positive reverse transcription-polymerase chain reaction (RT-PCR) test for COVID-19. We evaluated the post-test phenotypes in two temporal windows at 3-6 and 6-9 months after the test and by age and gender. Data from longitudinal diagnosis records stored in EHRs from Mass General Brigham in the Boston Metropolitan Area was used for the analyses. Statistical analyses were performed on data from March 2020 to June 2021. Study participants included over 96 thousand patients who had tested positive or negative for COVID-19 and were not hospitalized.

RESULTS

We identified 33 phenotypes among different age/gender cohorts or time windows that were positively associated with past SARS-CoV-2 infection. All identified phenotypes were newly recorded in patients' medical records 2 months or longer after a COVID-19 RT-PCR test in non-hospitalized patients regardless of the test result. Among these phenotypes, a new diagnosis record for anosmia and dysgeusia (OR 2.60, 95% CI [1.94-3.46]), alopecia (OR 3.09, 95% CI [2.53-3.76]), chest pain (OR 1.27, 95% CI [1.09-1.48]), chronic fatigue syndrome (OR 2.60, 95% CI [1.22-2.10]), shortness of breath (OR 1.41, 95% CI [1.22-1.64]), pneumonia (OR 1.66, 95% CI [1.28-2.16]), and type 2 diabetes mellitus (OR 1.41, 95% CI [1.22-1.64]) is one of the most significant indicators of a past COVID-19 infection. Additionally, more new phenotypes were found with increased confidence among the cohorts who were younger than 65.

CONCLUSIONS

The findings of this study confirm many of the post-COVID-19 symptoms and suggest that a variety of new diagnoses, including new diabetes mellitus and neurological disorder diagnoses, are more common among those with a history of COVID-19 than those without the infection. Additionally, more than 63% of PASC phenotypes were observed in patients under 65 years of age, pointing out the importance of vaccination to minimize the risk of debilitating post-acute sequelae of COVID-19 among younger adults.

High-throughput phenotyping with temporal sequences

OBJECTIVE

High-throughput electronic phenotyping algorithms can accelerate translational research using data from electronic health record (EHR) systems. The temporal information buried in EHRs is often underutilized in developing computational phenotypic definitions. This study aims to develop a high-throughput phenotyping method, leveraging temporal sequential patterns from EHRs.

MATERIALS AND METHODS

We develop a representation mining algorithm to extract 5 classes of representations from EHR diagnosis and medication records: the aggregated vector of the records (aggregated vector representation), the standard sequential patterns (sequential pattern mining), the transitive sequential patterns (transitive sequential pattern mining), and 2 hybrid classes. Using EHR data on 10 phenotypes from the Mass General Brigham Biobank, we train and validate phenotyping algorithms.

RESULTS

Phenotyping with temporal sequences resulted in a superior classification performance across all 10 phenotypes compared with the standard representations in electronic phenotyping. The high-throughput algorithm's classification performance was superior or similar to the performance of previously published electronic phenotyping algorithms. We characterize and evaluate the top transitive sequences of diagnosis records paired with the records of risk factors, symptoms, complications, medications, or vaccinations.

DISCUSSION

The proposed high-throughput phenotyping approach enables seamless discovery of sequential record combinations that may be difficult to assume from raw EHR data. Transitive sequences offer more accurate characterization of the phenotype, compared with its individual components, and reflect the actual lived experiences of the patients with that particular disease.

CONCLUSION

Sequential data representations provide a precise mechanism for incorporating raw EHR records into downstream machine learning. Our approach starts with user interpretability and works backward to the technology.

Evolving Phenotypes of non-hospitalized Patients that Indicate Long Covid

For some SARS-CoV-2 survivors, recovery from the acute phase of the infection has been grueling with lingering effects. Many of the symptoms characterized as the post-acute sequelae of COVID-19 (PASC) could have multiple causes or are similarly seen in non-COVID patients. Accurate identification of phenotypes will be important to guide future research and help the healthcare system focus its efforts and resources on adequately controlled age- and gender-specific sequelae of a COVID-19 infection. In this retrospective electronic health records (EHR) cohort study, we applied a computational framework for knowledge discovery from clinical data, MLHO, to identify phenotypes that positively associate with a past positive reverse transcription-polymerase chain reaction (RT-PCR) test for COVID-19. We evaluated the post-test phenotypes in two temporal windows at 3-6 and 6-9 months after the test and by age and gender. Data from longitudinal diagnosis records stored in EHRs from Mass General Brigham in the Boston metropolitan area was used for the analyses. Statistical analyses were performed on data from March 2020 to June 2021. Study participants included over 96 thousand patients who had tested positive or negative for COVID-19 and were not hospitalized. We identified 33 phenotypes among different age/gender cohorts or time windows that were positively associated with past SARS-CoV-2 infection. All identified phenotypes were newly recorded in patients’ medical records two months or longer after a COVID-19 RT-PCR test in non-hospitalized patients regardless of the test result. Among these phenotypes, a new diagnosis record for anosmia and dysgeusia (OR: 2.60, 95% CI [1.94 - 3.46]), alopecia (OR: 3.09, 95% CI [2.53 - 3.76]), chest pain (OR: 1.27, 95% CI [1.09 - 1.48]), chronic fatigue syndrome (OR 2.60, 95% CI [1.22-2.10]), shortness of breath (OR 1.41, 95% CI [1.22 - 1.64]), pneumonia (OR 1.66, 95% CI [1.28 - 2.16]), and type 2 diabetes mellitus (OR 1.41, 95% CI [1.22 - 1.64]) are some of the most significant indicators of a past COVID-19 infection. Additionally, more new phenotypes were found with increased confidence among the cohorts who were younger than 65. Our approach avoids a flood of false positive discoveries while offering a more robust probabilistic approach compared to the standard linear phenome-wide association study (PheWAS). The findings of this study confirm many of the post-COVID symptoms and suggest that a variety of new diagnoses, including new diabetes mellitus and neurological disorder diagnoses, are more common among those with a history of COVID-19 than those without the infection. Additionally, more than 63 percent of PASC phenotypes were observed in patients under 65 years of age, pointing out the importance of vaccination to minimize the risk of debilitating post-acute sequelae of COVID-19 among younger adults.

Individualized prediction of COVID-19 adverse outcomes with MLHO

The COVID-19 pandemic has devastated the world with health and economic wreckage. Precise estimates of adverse outcomes from COVID-19 could have led to better allocation of healthcare resources and more efficient targeted preventive measures, including insight into prioritizing how to best distribute a vaccination. We developed MLHO (pronounced as melo), an end-to-end Machine Learning framework that leverages iterative feature and algorithm selection to predict Health Outcomes. MLHO implements iterative sequential representation mining, and feature and model selection, for predicting patient-level risk of hospitalization, ICU admission, need for mechanical ventilation, and death. It bases this prediction on data from patients' past medical records (before their COVID-19 infection). MLHO's architecture enables a parallel and outcome-oriented model calibration, in which different statistical learning algorithms and vectors of features are simultaneously tested to improve prediction of health outcomes. Using clinical and demographic data from a large cohort of over 13,000 COVID-19-positive patients, we modeled the four adverse outcomes utilizing about 600 features representing patients' pre-COVID health records and demographics. The mean AUC ROC for mortality prediction was 0.91, while the prediction performance ranged between 0.80 and 0.81 for the ICU, hospitalization, and ventilation. We broadly describe the clusters of features that were utilized in modeling and their relative influence for predicting each outcome. Our results demonstrated that while demographic variables (namely age) are important predictors of adverse outcomes after a COVID-19 infection, the incorporation of the past clinical records are vital for a reliable prediction model. As the COVID-19 pandemic unfolds around the world, adaptable and interpretable machine learning frameworks (like MLHO) are crucial to improve our readiness for confronting the potential future waves of COVID-19, as well as other novel infectious diseases that may emerge.

Predicting COVID-19 mortality with electronic medical records

This study aims to predict death after COVID-19 using only the past medical information routinely collected in electronic health records (EHRs) and to understand the differences in risk factors across age groups. Combining computational methods and clinical expertise, we curated clusters that represent 46 clinical conditions as potential risk factors for death after a COVID-19 infection. We trained age-stratified generalized linear models (GLMs) with component-wise gradient boosting to predict the probability of death based on what we know from the patients before they contracted the virus. Despite only relying on previously documented demographics and comorbidities, our models demonstrated similar performance to other prognostic models that require an assortment of symptoms, laboratory values, and images at the time of diagnosis or during the course of the illness. In general, we found age as the most important predictor of mortality in COVID-19 patients. A history of pneumonia, which is rarely asked in typical epidemiology studies, was one of the most important risk factors for predicting COVID-19 mortality. A history of diabetes with complications and cancer (breast and prostate) were notable risk factors for patients between the ages of 45 and 65 years. In patients aged 65–85 years, diseases that affect the pulmonary system, including interstitial lung disease, chronic obstructive pulmonary disease, lung cancer, and a smoking history, were important for predicting mortality. The ability to compute precise individual-level risk scores exclusively based on the EHR is crucial for effectively allocating and distributing resources, such as prioritizing vaccination among the general population.

Transitive Sequencing Medical Records for Mining Predictive and Interpretable Temporal Representations

Electronic health records (EHRs) contain important temporal information about the progression of disease and treatment outcomes. This paper proposes a transitive sequencing approach for constructing temporal representations from EHR observations for downstream machine learning. Using clinical data from a cohort of patients with congestive heart failure, we mined temporal representations by transitive sequencing of EHR medication and diagnosis records for classification and prediction tasks. We compared the classification and prediction performances of the transitive sequential representations (bag-of-sequences approach) with the conventional approach of using aggregated vectors of EHR data (aggregated vector representation) across different classifiers. We found that the transitive sequential representations are better phenotype "differentiators" and predictors than the "atemporal" EHR records. Our results also demonstrated that data representations obtained from transitive sequencing of EHR observations can present novel insights about the progression of the disease that are difficult to discern when clinical data are treated independently of the patient's history.