Claims-Based Algorithms for Identifying Patients With Pulmonary Hypertension: A Comparison of Decision Rules and Machine-Learning Approaches

Validation Study of the Claims-Based Algorithm Using the International Classification of Diseases Codes to Identify Patients With Coronavirus Disease in Japan From 2020 to 2022: The VENUS Study

PURPOSE

We validated claims-based algorithms using the International Classification of Diseases, Tenth Revision (ICD-10) to identify patients with the first-ever coronavirus disease (COVID-19) onset between May 2020 and August 2022.

METHODS

The study cohort was comprised of residents of one municipality enrolled in a public insurance program. This study used data provided by the municipality, including residents' insurer-based medical claims data linked to the Health Center Real-time Information-Sharing System (HER-SYS). The HER-SYS data included positive results from COVID-19 tests and were used as reference standards. Claims-based algorithms #1 and #2 were U07.1, B34.2, with and without suspicious diagnoses, respectively. Claims-based algorithms #3 and #4 were U07.1 with and without suspicious diagnoses, respectively. The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated for each algorithm.

RESULTS

The study cohort included 165 038 residents, including 13 402 residents were the reference standard. For the entire period, the sensitivity, specificity, PPV, and NPV were 55.7% (95% confidence interval: 54.8%-56.5%), 65.4% (65.2%-65.6%), 11.5% (11.3%-11.8%), and 98.9% (98.8%-99.0%) for Algorithm #1, and 67.0% (66.2%-67.8%), 88.1% (87.9%-88.3%), 31.6% (31.1%-32.2%), and 97.8% (97.7%-97.8%) for Algorithm #2, and 52.9% (52.0%-53.7%), 67.1% (66.9%-67.3%), 11.5% (11.2%-11.8%), and 98.3% (98.3%-98.4%) for Algorithm #3, 62.6% (61.8%-63.4%), 88.5% (88.3%-88.7%), 30.9% (30.3%-31.4%), and 97.3% (97.2%-97.4%) for Algorithm #4, respectively.

CONCLUSIONS

Our study showed that the validity of claims-based algorithms consisting of COVID-19-related ICD-10 codes to identify patients with first-onset COVID-19 is limited.

Assessing the precision of machine learning for diagnosing pulmonary arterial hypertension: a systematic review and meta-analysis of diagnostic accuracy studies

Introduction

Pulmonary arterial hypertension (PAH) is a severe cardiovascular condition characterized by pulmonary vascular remodeling, increased resistance to blood flow, and eventual right heart failure. Right heart catheterization (RHC) is the gold standard diagnostic technique, but due to its invasiveness, it poses risks such as vessel and valve injury. In recent years, machine learning (ML) technologies have offered non-invasive alternatives combined with ML for improving the diagnosis of PAH.

Objectives

The study aimed to evaluate the diagnostic performance of various methods, such as electrocardiography (ECG), echocardiography, blood biomarkers, microRNA, chest x-ray, clinical codes, computed tomography (CT) scan, and magnetic resonance imaging (MRI), combined with ML in diagnosing PAH.

Methods

The outcomes of interest included sensitivity, specificity, area under the curve (AUC), positive likelihood ratio (PLR), negative likelihood ratio (NLR), and diagnostic odds ratio (DOR). This study employed the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool for quality appraisal and STATA V.12.0 for the meta-analysis.

Results

A comprehensive search across six databases resulted in 26 articles for examination. Twelve articles were categorized as low-risk, nine as moderate-risk, and five as high-risk. The overall diagnostic performance analysis demonstrated significant findings, with sensitivity at 81% (95% CI = 0.76-0.85, p < 0.001), specificity at 84% (95% CI = 0.77-0.88, p < 0.001), and an AUC of 89% (95% CI = 0.85-0.91). In the subgroup analysis, echocardiography displayed outstanding results, with a sensitivity value of 83% (95% CI = 0.72-0.91), specificity value of 93% (95% CI = 0.89-0.96), PLR value of 12.4 (95% CI = 6.8-22.9), and DOR value of 70 (95% CI = 23-231). ECG demonstrated excellent accuracy performance, with a sensitivity of 82% (95% CI = 0.80-0.84) and a specificity of 82% (95% CI = 0.78-0.84). Moreover, blood biomarkers exhibited the highest NLR value of 0.50 (95% CI = 0.42-0.59).

Conclusion

The implementation of echocardiography and ECG with ML for diagnosing PAH presents a promising alternative to RHC. This approach shows potential, as it achieves excellent diagnostic parameters, offering hope for more accessible and less invasive diagnostic methods.

Systematic Review Registration

PROSPERO (CRD42024496569).

Development of Interoperable Computable Phenotype Algorithms for Adverse Events of Special Interest to Be Used for Biologics Safety Surveillance: Validation Study

BACKGROUND

Adverse events associated with vaccination have been evaluated by epidemiological studies and more recently have gained additional attention with the emergency use authorization of several COVID-19 vaccines. As part of its responsibility to conduct postmarket surveillance, the US Food and Drug Administration continues to monitor several adverse events of special interest (AESIs) to ensure vaccine safety, including for COVID-19.

OBJECTIVE

This study is part of the Biologics Effectiveness and Safety Initiative, which aims to improve the Food and Drug Administration's postmarket surveillance capabilities while minimizing public burden. This study aimed to enhance active surveillance efforts through a rules-based, computable phenotype algorithm to identify 5 AESIs being monitored by the Center for Disease Control and Prevention for COVID-19 or other vaccines: anaphylaxis, Guillain-Barré syndrome, myocarditis/pericarditis, thrombosis with thrombocytopenia syndrome, and febrile seizure. This study examined whether these phenotypes have sufficiently high positive predictive value (PPV) to ensure that the cases selected for surveillance are reasonably likely to be a postbiologic adverse event. This allows patient privacy, and security concerns for the data sharing of patients who had nonadverse events can be properly accounted for when evaluating the cost-benefit aspect of our approach.

METHODS

AESI phenotype algorithms were developed to apply to electronic health record data at health provider organizations across the country by querying for standard and interoperable codes. The codes queried in the rules represent symptoms, diagnoses, or treatments of the AESI sourced from published case definitions and input from clinicians. To validate the performance of the algorithms, we applied them to electronic health record data from a US academic health system and provided a sample of cases for clinicians to evaluate. Performance was assessed using PPV.

RESULTS

With a PPV of 93.3%, our anaphylaxis algorithm performed the best. The PPVs for our febrile seizure, myocarditis/pericarditis, thrombocytopenia syndrome, and Guillain-Barré syndrome algorithms were 89%, 83.5%, 70.2%, and 47.2%, respectively.

CONCLUSIONS

Given our algorithm design and performance, our results support continued research into using interoperable algorithms for widespread AESI postmarket detection.

Using machine learning to improve anaphylaxis case identification in medical claims data

Objectives

Anaphylaxis is a severe life-threatening allergic reaction, and its accurate identification in healthcare databases can harness the potential of "Big Data" for healthcare or public health purposes.

Materials and methods

This study used claims data obtained between October 1, 2015 and February 28, 2019 from the CMS database to examine the utility of machine learning in identifying incident anaphylaxis cases. We created a feature selection pipeline to identify critical features between different datasets. Then a variety of unsupervised and supervised methods were used (eg, Sammon mapping and eXtreme Gradient Boosting) to train models on datasets of differing data quality, which reflects the varying availability and potential rarity of ground truth data in medical databases.

Results

Resulting machine learning model accuracies ranged from 47.7% to 94.4% when tested on ground truth data. Finally, we found new features to help experts enhance existing case-finding algorithms.

Discussion

Developing precise algorithms to detect medical outcomes in claims can be a laborious and expensive process, particularly for conditions presented and coded diversely. We found it beneficial to filter out highly potent codes used for data curation to identify underlying patterns and features. To improve rule-based algorithms where necessary, researchers could use model explainers to determine noteworthy features, which could then be shared with experts and included in the algorithm.

Conclusion

Our work suggests machine learning models can perform at similar levels as a previously published expert case-finding algorithm, while also having the potential to improve performance or streamline algorithm construction processes by identifying new relevant features for algorithm construction.

Development and validation of a code-based algorithm using in-hospital medical records to identify patients with pulmonary arterial hypertension in a French healthcare database

Introduction

Pulmonary arterial hypertension (PAH) is a rare and severe disease for which most of the evidence about prognostic factors, evolution and treatment efficacy comes from cohorts, registries and clinical trials. We therefore aimed to develop and validate a new PAH identification algorithm that can be used in the French healthcare database "Système National des Données de Santé (SNDS)".

Methods

We developed and validated the algorithm using the Grenoble Alpes University Hospital medical charts. We first identified PAH patients following a previously validated algorithm, using in-hospital ICD-10 (10th revision of the International Statistical Classification of Diseases) codes, right heart catheterisation procedure and PAH-specific treatment dispensing. Then, we refined the latter with the exclusion of chronic thromboembolic pulmonary hypertension procedures and treatment, the main misclassification factor. Second, we validated this algorithm using a gold standard review of in-hospital medical charts and calculated sensitivity, specificity, positive and negative predictive value (PPV and NPV) and accuracy. Finally, we applied this algorithm in the French healthcare database and described the characteristics of the identified patients.

Results

In the Grenoble University Hospital, we identified 252 unique patients meeting all the algorithm's criteria between 1 January 2010 and 30 June 2022, and reviewed all medical records. The sensitivity, specificity, PPV, NPV and accuracy were 91.0%, 74.3%, 67.9%, 93.3% and 80.6%, respectively. Application of this algorithm to the SNDS yielded the identification of 9931 patients with consistent characteristics compared to PAH registries.

Conclusion

Overall, we propose a new PAH identification algorithm developed and adapted to the French specificities that can be used in future studies using the French healthcare database.

Resistin predicts disease severity and survival in patients with pulmonary arterial hypertension

BACKGROUND

Abnormal remodeling of distal pulmonary arteries in patients with pulmonary arterial hypertension (PAH) leads to progressively increased pulmonary vascular resistance, followed by right ventricular hypertrophy and failure. Despite considerable advancements in PAH treatment prognosis remains poor. We aim to evaluate the potential for using the cytokine resistin as a genetic and biological marker for disease severity and survival in a large cohort of patients with PAH.

METHODS

Biospecimens, clinical, and genetic data for 1121 adults with PAH, including 808 with idiopathic PAH (IPAH) and 313 with scleroderma-associated PAH (SSc-PAH), were obtained from a national repository. Serum resistin levels were measured by ELISA, and associations between resistin levels, clinical variables, and single nucleotide polymorphism genotypes were examined with multivariable regression models. Machine-learning (ML) algorithms were applied to develop and compare risk models for mortality prediction.

RESULTS

Resistin levels were significantly higher in all PAH samples and PAH subtype (IPAH and SSc-PAH) samples than in controls (P < .0001) and had significant discriminative abilities (AUCs of 0.84, 0.82, and 0.91, respectively; P < .001). High resistin levels (above 4.54 ng/mL) in PAH patients were associated with older age (P = .001), shorter 6-min walk distance (P = .001), and reduced cardiac performance (cardiac index, P = .016). Interestingly, mutant carriers of either rs3219175 or rs3745367 had higher resistin levels (adjusted P = .0001). High resistin levels in PAH patients were also associated with increased risk of death (hazard ratio: 2.6; 95% CI: 1.27-5.33; P < .0087). Comparisons of ML-derived survival models confirmed satisfactory prognostic value of the random forest model (AUC = 0.70, 95% CI: 0.62-0.79) for PAH.

CONCLUSIONS

This work establishes the importance of resistin in the pathobiology of human PAH. In line with its function in rodent models, serum resistin represents a novel biomarker for PAH prognostication and may indicate a new therapeutic avenue. ML-derived survival models highlighted the importance of including resistin levels to improve performance. Future studies are needed to develop multi-marker assays that improve noninvasive risk stratification.

Development and validation of algorithms to predict left ventricular ejection fraction class from healthcare claims data

AIMS

The use of large medical or healthcare claims databases is very useful for population-based studies on the burden of heart failure (HF). Clinical characteristics and management of HF patients differ according to categories of left ventricular ejection fraction (LVEF), but this information is often missing in such databases. We aimed to develop and validate algorithms to identify LVEF in healthcare databases where the information is lacking.

METHODS AND RESULTS

Algorithms were built by machine learning with a random forest approach. Algorithms were trained and reinforced using the French national claims database [Système National des Données de Santé (SNDS)] and a French HF registry. Variables were age, gender, and comorbidities, which could be identified by medico-administrative code-based proxies, Anatomical Therapeutic Chemical codes for drug delivery, International Classification of Diseases (Tenth Revision) coding for hospitalizations, and administrative codes for any other type of reimbursed care. The algorithms were validated by cross-validation and against a subset of the SNDS that includes LVEF information. The areas under the receiver operating characteristic curve were 0.84 for the algorithm identifying LVEF ≤ 40% and 0.79 for the algorithms identifying LVEF < 50% and ≥50%. For LVEF ≤ 40%, the reinforced algorithm identified 50% of patients in the validation dataset with a positive predictive value of 0.88 and a specificity of 0.96. The most important predictive variables were delivery of HF medication, sex, age, hospitalization, and testing for natriuretic peptides with different orders of positive or negative importance according to the LVEF category.

CONCLUSIONS

The algorithms identify reduced or preserved LVEF in HF patients within a nationwide healthcare claims database with high positive predictive value and low rates of false positives.

Pulmonary Hypertension Detection Non-Invasively at Point-of-Care Using a Machine-Learned Algorithm

Artificial intelligence, particularly machine learning, has gained prominence in medical research due to its potential to develop non-invasive diagnostics. Pulmonary hypertension presents a diagnostic challenge due to its heterogeneous nature and similarity in symptoms to other cardiovascular conditions. Here, we describe the development of a supervised machine learning model using non-invasive signals (orthogonal voltage gradient and photoplethysmographic) and a hand-crafted library of 3298 features. The developed model achieved a sensitivity of 87% and a specificity of 83%, with an overall Area Under the Receiver Operator Characteristic Curve (AUC-ROC) of 0.93. Subgroup analysis showed consistent performance across genders, age groups and classes of PH. Feature importance analysis revealed changes in metrics that measure conduction, repolarization and respiration as significant contributors to the model. The model demonstrates promising performance in identifying pulmonary hypertension, offering potential for early detection and intervention when embedded in a point-of-care diagnostic system.

Clinical evaluation of code-based algorithms to identify patients with pulmonary arterial hypertension in healthcare databases

Pulmonary arterial hypertension (PAH) is a rare subgroup of pulmonary hypertension (PH). Claims and administrative databases can be particularly important for research in rare diseases; however, there is a lack of validated algorithms to identify PAH patients using administrative codes. We aimed to measure the accuracy of code-based PAH algorithms against the true clinical diagnosis by right heart catheterization (RHC). This study evaluated algorithms in patients who were recorded in two linkable data assets: the Stanford Healthcare administrative electronic health record database and the Stanford Vera Moulton Wall Center clinical PH database (which records each patient's RHC diagnosis). We assessed the sensitivity and specificity achieved by 16 algorithms (six published). In total, 720 PH patients with linked data available were included and 558 (78%) of these were PAH patients. Algorithms consisting solely of a P(A)H-specific diagnostic code classed all or almost all PH patients as PAH (sensitivity >97%, specificity <12%) while multicomponent algorithms with well-defined temporal sequences of procedure, diagnosis and treatment codes achieved a better balance of sensitivity and specificity. Specificity increased and sensitivity decreased with increasing algorithm complexity. The best-performing algorithms, in terms of fewest misclassified patients, included multiple components (e.g., PH diagnosis, PAH treatment, continuous enrollment for ≥6 months before and ≥12 months following index date) and achieved sensitivities and specificities of around 95% and 38%, respectively. Our findings help researchers tailor their choice and design of code-based PAH algorithms to their research question and demonstrate the importance of including well-defined temporal components in the algorithms.

Using machine learning to improve anaphylaxis case identification in medical claims data

Objective

Anaphylaxis is a severe life-threatening allergic reaction, and its accurate identification in healthcare databases can harness the potential of "Big Data" for healthcare or public health purposes.

Methods

This study used claims data obtained between October 1, 2015 and February 28, 2019 from the CMS database to examine the utility of machine learning in identifying incident anaphylaxis cases. We created a feature selection pipeline to identify critical features between different datasets. Then a variety of unsupervised and supervised methods were used (eg, Sammon mapping and eXtreme Gradient Boosting) to train models on datasets of differing data quality, which reflects the varying availability and potential rarity of ground truth data in medical databases.

Results

Resulting machine learning model accuracies ranged between 47.7% and 94.4% when tested on ground truth data. Finally, we found new features to help experts enhance existing case-finding algorithms.

Discussion

Developing precise algorithms to detect medical outcomes in claims can be a laborious and expensive process, particularly for conditions presented and coded diversely. We found it beneficial to filter out highly potent codes used for data curation to identify underlying patterns and features. To improve rule-based algorithms where necessary, researchers could use model explainers to determine noteworthy features, which could then be shared with experts and included in the algorithm.

Conclusion

Our work suggests machine learning models can perform at similar levels as a previously published expert case-finding algorithm, while also having the potential to improve performance or streamline algorithm construction processes by identifying new relevant features for algorithm construction.

Real-world evidence to advance knowledge in pulmonary hypertension: Status, challenges, and opportunities. A consensus statement from the Pulmonary Vascular Research Institute's Innovative Drug Development Initiative's Real-world Evidence Working Group

This manuscript on real-world evidence (RWE) in pulmonary hypertension (PH) incorporates the broad experience of members of the Pulmonary Vascular Research Institute's Innovative Drug Development Initiative Real-World Evidence Working Group. We aim to strengthen the research community's understanding of RWE in PH to facilitate clinical research advances and ultimately improve patient care. Herein, we review real-world data (RWD) sources, discuss challenges and opportunities when using RWD sources to study PH populations, and identify resources needed to support the generation of meaningful RWE for the global PH community.

Leveraging machine learning to identify acute myeloid leukemia patients and their chemotherapy regimens in an administrative database

BACKGROUND

Administrative datasets are useful for identifying rare disease cohorts such as pediatric acute myeloid leukemia (AML). Previously, cohorts were assembled using labor-intensive, manual reviews of patients' longitudinal chemotherapy data.

METHODS

We utilized a two-step machine learning (ML) method to (i) identify pediatric patients with newly diagnosed AML, and (ii) among the identified AML patients, their chemotherapy courses, in an administrative/billing database. Using 2558 patients previously manually reviewed, multiple ML algorithms were derived from 75% of the study sample, and the selected model was tested in the remaining hold-out sample. The selected model was also applied to assemble a new pediatric AML cohort and further assessed in an external validation, using a standalone cohort established by manual chart abstraction.

RESULTS

For patient identification, the selected Support Vector Machine model yielded a sensitivity of 0.97 and a positive predictive value (PPV) of 0.97 in the hold-out test sample. For course-specific chemotherapy regimen and start date identification, the selected Random Forest model yielded overall PPV greater than or equal to 0.88 and sensitivity greater than or equal to 0.86 across all courses in the test sample. When applied to new cohort assembly, ML identified 3016 AML patients with 10,588 treatment courses. In the external validation subset, PPV was greater than or equal to 0.75 and sensitivity was greater than or equal to 0.82 for patient identification, and PPV was greater than or equal to 0.93 and sensitivity was greater than or equal to 0.94 for regimen identifications.

CONCLUSION

A carefully designed ML model can accurately identify pediatric AML patients and their chemotherapy courses from administrative databases. This approach may be generalizable to other diseases and databases.

Integrating Health Data-Driven Machine Learning Algorithms to Evaluate Risk Factors of Early Stage Hypertension at Different Levels of HDL and LDL Cholesterol

Purpose: Cardiovascular disease (CVD) is a major worldwide health burden. As the risk factors of CVD, hypertension, and hyperlipidemia are most mentioned. Early stage hypertension in the population with dyslipidemia is an important public health hazard. This study was the application of data-driven machine learning (ML), demonstrating complex relationships between risk factors and outcomes and promising predictive performance with vast amounts of medical data, aimed to investigate the association between dyslipidemia and the incidence of early stage hypertension in a large cohort with normal blood pressure at baseline. Methods: This study analyzed annual health screening data for 71,108 people from 2005 to 2017, including data for 27 risk-related indicators, sourced from the MJ Group, a major health screening center in Taiwan. We used five machine learning (ML) methods—stochastic gradient boosting (SGB), multivariate adaptive regression splines (MARS), least absolute shrinkage and selection operator regression (Lasso), ridge regression (Ridge), and gradient boosting with categorical features support (CatBoost)—to develop a multi-stage ML algorithm-based prediction scheme and then evaluate important risk factors at the early stage of hypertension, especially for groups with high-density lipoprotein cholesterol (HDL-C) and low-density lipoprotein cholesterol (LDL-C) levels within or out of the reference range. Results: Age, body mass index, waist circumference, waist-to-hip ratio, fasting plasma glucose, and C-reactive protein (CRP) were associated with hypertension. The hemoglobin level was also a positive contributor to blood pressure elevation and it appeared among the top three important risk factors in all LDL-C/HDL-C groups; therefore, these variables may be important in affecting blood pressure in the early stage of hypertension. A residual contribution to blood pressure elevation was found in groups with increased LDL-C. This suggests that LDL-C levels are associated with CPR levels, and that the LDL-C level may be an important factor for predicting the development of hypertension. Conclusion: The five prediction models provided similar classifications of risk factors. The results of this study show that an increase in LDL-C is more important than the start of a drop in HDL-C in health screening of sub-healthy adults. The findings of this study should be of value to health awareness raising about hypertension and further discussion and follow-up research.

An algorithm to identify cases of pulmonary arterial hypertension from the electronic medical record

BACKGROUND

Study of pulmonary arterial hypertension (PAH) in claims-based (CB) cohorts may facilitate understanding of disease epidemiology, however previous CB algorithms to identify PAH have had limited test characteristics. We hypothesized that machine learning algorithms (MLA) could accurately identify PAH in an CB cohort.

METHODS

ICD-9/10 codes, CPT codes or PAH medications were used to screen an electronic medical record (EMR) for possible PAH. A subset (Development Cohort) was manually reviewed and adjudicated as PAH or "not PAH" and used to train and test MLAs. A second subset (Refinement Cohort) was manually reviewed and combined with the Development Cohort to make The Final Cohort, again divided into training and testing sets, with MLA characteristics defined on test set. The MLA was validated using an independent EMR cohort.

RESULTS

194 PAH and 786 "not PAH" in the Development Cohort trained and tested the initial MLA. In the Final Cohort test set, the final MLA sensitivity was 0.88, specificity was 0.93, positive predictive value was 0.89, and negative predictive value was 0.92. Persistence and strength of PAH medication use and CPT code for right heart catheterization were principal MLA features. Applying the MLA to the EMR cohort using a split cohort internal validation approach, we found 265 additional non-confirmed cases of suspected PAH that exhibited typical PAH demographics, comorbidities, hemodynamics.

CONCLUSIONS

We developed and validated a MLA using only CB features that identified PAH in the EMR with strong test characteristics. When deployed across an entire EMR, the MLA identified cases with known features of PAH.

Harnessing Big Data to Advance Treatment and Understanding of Pulmonary Hypertension

Pulmonary hypertension is a complex disease with multiple causes, corresponding to phenotypic heterogeneity and variable therapeutic responses. Advancing understanding of pulmonary hypertension pathogenesis is likely to hinge on integrated methods that leverage data from health records, imaging, novel molecular -omics profiling, and other modalities. In this review, we summarize key data sets generated thus far in the field and describe analytical methods that hold promise for deciphering the molecular mechanisms that underpin pulmonary vascular remodeling, including machine learning, network medicine, and functional genetics. We also detail how genetic and subphenotyping approaches enable earlier diagnosis, refined prognostication, and optimized treatment prediction. We propose strategies that identify functionally important molecular pathways, bolstered by findings across multi-omics platforms, which are well-positioned to individualize drug therapy selection and advance precision medicine in this highly morbid disease.

An evolutionary machine learning for pulmonary hypertension animal model from arterial blood gas analysis

Pulmonary hypertension (PH) is a rare and fatal condition that leads to right heart failure and death. The pathophysiology of PH and potential therapeutic approaches are yet unknown. PH animal models' development and proper evaluation are critical to PH research. This work presents an effective analysis technology for PH from arterial blood gas analysis utilizing an evolutionary kernel extreme learning machine with multiple strategies integrated slime mould algorithm (MSSMA). In MSSMA, two efficient bee-foraging learning operators are added to the original slime mould algorithm, ensuring a suitable trade-off between intensity and diversity. The proposed MSSMA is evaluated on thirty IEEE benchmarks and the statistical results show that the search performance of the MSSMA is significantly improved. The MSSMA is utilised to develop a kernel extreme learning machine (MSSMA-KELM) on PH from arterial blood gas analysis. Comprehensively, the proposed MSSMA-KELM can be used as an effective analysis technology for PH from arterial Blood gas analysis with an accuracy of 93.31%, Matthews coefficient of 90.13%, Sensitivity of 91.12%, and Specificity of 90.73%. MSSMA-KELM can be treated as an effective approach for evaluating mouse PH models.

Identifying Patients with Group 3 Pulmonary Hypertension Associated with COPD or ILD Using an Administrative Claims Database

BACKGROUND

Group 3 pulmonary hypertension (PH) describes a subpopulation of patients with PH due to chronic lung disease and/or hypoxia, with chronic obstructive pulmonary disease (COPD) and interstitial lung disease (ILD) being two large subgroups. Claims database studies provide insights into the real-world treatment patterns and outcomes among these patients. However, claims data do not provide sufficient detail to assign the clinical subtype of PH required for identifying these patients.

METHODS

A panel of PH clinical experts and researchers was convened to discuss methodologies to identify patients with Group 3 PH associated with COPD or ILD in retrospective claims databases. To inform the discussion, a literature review was conducted to identify claims-based studies of Group 3 PH associated with COPD or ILD published from 2010 through June 2020.

RESULTS

Targeted title and abstract review identified 11 claims-based studies and two conference abstracts (eight based in the United States [US] and five conducted outside the US) that met search criteria. Based on insights from the panel and literature review, the following components were detailed across studies in the identification of Group 3 PH associated with COPD and ILD: (a) COPD or ILD identification, (b) PH identification, (c) defining the sequence between COPD/ILD and PH, and (d) other PH Group and Group 3 PH exclusions.

CONCLUSION

This article provides recommended approaches and considerations for identifying and studying patients with Group 3 PH associated with COPD or ILD using administrative claims data that provide the foundation for future validation studies.

Applying Machine Learning in Distributed Data Networks for Pharmacoepidemiologic and Pharmacovigilance Studies: Opportunities, Challenges, and Considerations

Increasing availability of electronic health databases capturing real-world experiences with medical products has garnered much interest in their use for pharmacoepidemiologic and pharmacovigilance studies. The traditional practice of having numerous groups use single databases to accomplish similar tasks and address common questions about medical products can be made more efficient through well-coordinated multi-database studies, greatly facilitated through distributed data network (DDN) architectures. Access to larger amounts of electronic health data within DDNs has created a growing interest in using data-adaptive machine learning (ML) techniques that can automatically model complex associations in high-dimensional data with minimal human guidance. However, the siloed storage and diverse nature of the databases in DDNs create unique challenges for using ML. In this paper, we discuss opportunities, challenges, and considerations for applying ML in DDNs for pharmacoepidemiologic and pharmacovigilance studies. We first discuss major types of activities performed by DDNs and how ML may be used. Next, we discuss practical data-related factors influencing how DDNs work in practice. We then combine these discussions and jointly consider how opportunities for ML are affected by practical data-related factors for DDNs, leading to several challenges. We present different approaches for addressing these challenges and highlight efforts that real-world DDNs have taken or are currently taking to help mitigate them. Despite these challenges, the time is ripe for the emerging interest to use ML in DDNs, and the utility of these data-adaptive modeling techniques in pharmacoepidemiologic and pharmacovigilance studies will likely continue to increase in the coming years.

What's new in pulmonary hypertension clinical research: lessons from the best abstracts at the 2020 American Thoracic Society International Conference

In this conference paper, we review the 2020 American Thoracic Society International Conference session titled, "What's New in Pulmonary Hypertension Clinical Research: Lessons from the Best Abstracts". This virtual mini-symposium took place on 21 October 2020, in lieu of the annual in-person ATS International Conference which was cancelled due to the COVID-19 pandemic. Seven clinical research abstracts were selected for presentation in the session, which encompassed five major themes: (1) standardizing diagnosis and management of pulmonary hypertension, (2) improving risk assessment in pulmonary arterial hypertension, (3) evaluating biomarkers of disease activity, (4) understanding metabolic dysregulation across the spectrum of pulmonary hypertension, and (5) advancing knowledge in chronic thromboembolic pulmonary hypertension. Focusing on these five thematic contexts, we review the current state of knowledge, summarize presented research abstracts, appraise their significance and limitations, and then discuss relevant future directions in pulmonary hypertension clinical research.

Claims-Based Algorithms for Identifying Patients With Pulmonary Hypertension: A Comparison of Decision Rules and Machine-Learning Approaches

Background

Real‐world healthcare data are an important resource for epidemiologic research. However, accurate identification of patient cohorts—a crucial first step underpinning the validity of research results—remains a challenge. We developed and evaluated claims‐based case ascertainment algorithms for pulmonary hypertension (PH), comparing conventional decision rules with state‐of‐the‐art machine‐learning approaches.

Methods and Results

We analyzed an electronic health record‐Medicare linked database from two large academic tertiary care hospitals (years 2007–2013). Electronic health record charts were reviewed to form a gold standard cohort of patients with (n=386) and without PH (n=164). Using health encounter data captured in Medicare claims (including patients’ demographics, diagnoses, medications, and procedures), we developed and compared 2 approaches for identifying patients with PH: decision rules and machine‐learning algorithms using penalized lasso regression, random forest, and gradient boosting machine. The most optimal rule‐based algorithm—having ≥3 PH‐related healthcare encounters and having undergone right heart catheterization—attained an area under the receiver operating characteristic curve of 0.64 (sensitivity, 0.75; specificity, 0.48). All 3 machine‐learning algorithms outperformed the most optimal rule‐based algorithm (P<0.001). A model derived from the random forest algorithm achieved an area under the receiver operating characteristic curve of 0.88 (sensitivity, 0.87; specificity, 0.70), and gradient boosting machine achieved comparable results (area under the receiver operating characteristic curve, 0.85; sensitivity, 0.87; specificity, 0.70). Penalized lasso regression achieved an area under the receiver operating characteristic curve of 0.73 (sensitivity, 0.70; specificity, 0.68).

Conclusions

Research‐grade case identification algorithms for PH can be derived and rigorously validated using machine‐learning algorithms. Simple decision rules commonly applied in published literature performed poorly; more complex rule‐based algorithms may potentially address the limitation of this approach. PH research using claims data would be considerably strengthened through the use of validated algorithms for cohort ascertainment.