Heterogeneous associations between interleukin-6 receptor variants and phenotypes across ancestries and implications for therapy

The Phenome-Wide Association Study (PheWAS) is increasingly used to broadly screen for potential treatment effects, e.g., IL6R variant as a proxy for IL6R antagonists. This approach offers an opportunity to address the limited power in clinical trials to study differential treatment effects across patient subgroups. However, limited methods exist to efficiently test for differences across subgroups in the thousands of multiple comparisons generated as part of a PheWAS. In this study, we developed an approach that maximizes the power to test for heterogeneous genotype-phenotype associations and applied this approach to an IL6R PheWAS among individuals of African (AFR) and European (EUR) ancestries. We identified 29 traits with differences in IL6R variant-phenotype associations, including a lower risk of type 2 diabetes in AFR (OR 0.96) vs EUR (OR 1.0, p-value for heterogeneity = 8.5 × 10-3), and higher white blood cell count (p-value for heterogeneity = 8.5 × 10-131). These data suggest a more salutary effect of IL6R blockade for T2D among individuals of AFR vs EUR ancestry and provide data to inform ongoing clinical trials targeting IL6 for an expanding number of conditions. Moreover, the method to test for heterogeneity of associations can be applied broadly to other large-scale genotype-phenotype screens in diverse populations.

Neurological diagnoses in hospitalized COVID-19 patients associated with adverse outcomes: A multinational cohort study

Few studies examining the patient outcomes of concurrent neurological manifestations during acute COVID-19 leveraged multinational cohorts of adults and children or distinguished between central and peripheral nervous system (CNS vs. PNS) involvement. Using a federated multinational network in which local clinicians and informatics experts curated the electronic health records data, we evaluated the risk of prolonged hospitalization and mortality in hospitalized COVID-19 patients from 21 healthcare systems across 7 countries. For adults, we used a federated learning approach whereby we ran Cox proportional hazard models locally at each healthcare system and performed a meta-analysis on the aggregated results to estimate the overall risk of adverse outcomes across our geographically diverse populations. For children, we reported descriptive statistics separately due to their low frequency of neurological involvement and poor outcomes. Among the 106,229 hospitalized COVID-19 patients (104,031 patients ≥18 years; 2,198 patients <18 years, January 2020-October 2021), 15,101 (14%) had at least one CNS diagnosis, while 2,788 (3%) had at least one PNS diagnosis. After controlling for demographics and pre-existing conditions, adults with CNS involvement had longer hospital stay (11 versus 6 days) and greater risk of (Hazard Ratio = 1.78) and faster time to death (12 versus 24 days) than patients with no neurological condition (NNC) during acute COVID-19 hospitalization. Adults with PNS involvement also had longer hospital stay but lower risk of mortality than the NNC group. Although children had a low frequency of neurological involvement during COVID-19 hospitalization, a substantially higher proportion of children with CNS involvement died compared to those with NNC (6% vs 1%). Overall, patients with concurrent CNS manifestation during acute COVID-19 hospitalization faced greater risks for adverse clinical outcomes than patients without any neurological diagnosis. Our global informatics framework using a federated approach (versus a centralized data collection approach) has utility for clinical discovery beyond COVID-19.

[Pulmonary artery stenting in chronic thromboembolic pulmonary hypertension: a report of 2 cases]

Chronic thromboembolic pulmonary hypertension (CTEPH) is a pulmonary vascular disease characterized by an insidious onset, progressive deterioration, and poor prognosis. It is distinguished by the thrombotic organization within the pulmonary arteries, leading to vascular stenosis or occlusion. This results in a progressive increase in pulmonary vascular resistance and pulmonary arterial pressure, ultimately leading to right heart failure. In recent years, balloon pulmonary angioplasty (BPA) has emerged as an effective treatment option for patients ineligible for pulmonary endarterectomy (PEA). However, the use of stents in patients with suboptimal balloon dilation remains controversial. This article describes two cases of chronic thromboembolic pulmonary hypertension (CTEPH) in which balloon angioplasty yielded unsatisfactory results, subsequently leading to stent placement. Following stent implantation, there was improved blood flow, significant reduction in pulmonary arterial pressure, and notable alleviation of patient symptoms. One-year follow-up showed no recurrence of stenosis within the stent, suggesting potential guidance for the use of pulmonary artery stenting as a treatment modality for CTEPH. This report provided new insights into the therapeutic approach for CTEPH.

Worldwide forest surveys reveal forty-three new species in Phytophthora major Clade 2 with fundamental implications for the evolution and biogeography of the genus and global plant biosecurity

During 25 surveys of global Phytophthora diversity, conducted between 1998 and 2020, 43 new species were detected in natural ecosystems and, occasionally, in nurseries and outplantings in Europe, Southeast and East Asia and the Americas. Based on a multigene phylogeny of nine nuclear and four mitochondrial gene regions they were assigned to five of the six known subclades, 2a-c, e and f, of Phytophthora major Clade 2 and the new subclade 2g. The evolutionary history of the Clade appears to have involved the pre-Gondwanan divergence of three extant subclades, 2c, 2e and 2f, all having disjunct natural distributions on separate continents and comprising species with a soilborne and aquatic lifestyle and, in addition, a few partially aerial species in Clade 2c; and the post-Gondwanan evolution of subclades 2a and 2g in Southeast/East Asia and 2b in South America, respectively, from their common ancestor. Species in Clade 2g are soilborne whereas Clade 2b comprises both soil-inhabiting and aerial species. Clade 2a has evolved further towards an aerial lifestyle comprising only species which are predominantly or partially airborne. Based on high nuclear heterozygosity levels ca. 38 % of the taxa in Clades 2a and 2b could be some form of hybrid, and the hybridity may be favoured by an A1/A2 breeding system and an aerial life style. Circumstantial evidence suggests the now 93 described species and informally designated taxa in Clade 2 result from both allopatric non-adaptive and sympatric adaptive radiations. They represent most morphological and physiological characters, breeding systems, lifestyles and forms of host specialism found across the Phytophthora clades as a whole, demonstrating the strong biological cohesiveness of the genus. The finding of 43 previously unknown species from a single Phytophthora clade highlight a critical lack of information on the scale of the unknown pathogen threats to forests and natural ecosystems, underlining the risk of basing plant biosecurity protocols mainly on lists of named organisms. More surveys in natural ecosystems of yet unsurveyed regions in Africa, Asia, Central and South America are needed to unveil the full diversity of the clade and the factors driving diversity, speciation and adaptation in Phytophthora. Taxonomic novelties: New species: Phytophthora amamensis T. Jung, K. Kageyama, H. Masuya & S. Uematsu, Phytophthora angustata T. Jung, L. Garcia, B. Mendieta-Araica, & Y. Balci, Phytophthora balkanensis I. Milenković, Ž. Tomić, T. Jung & M. Horta Jung, Phytophthora borneensis T. Jung, A. Durán, M. Tarigan & M. Horta Jung, Phytophthora calidophila T. Jung, Y. Balci, L. Garcia & B. Mendieta-Araica, Phytophthora catenulata T. Jung, T.-T. Chang, N.M. Chi & M. Horta Jung, Phytophthora celeris T. Jung, L. Oliveira, M. Tarigan & I. Milenković, Phytophthora curvata T. Jung, A. Hieno, H. Masuya & M. Horta Jung, Phytophthora distorta T. Jung, A. Durán, E. Sanfuentes von Stowasser & M. Horta Jung, Phytophthora excentrica T. Jung, S. Uematsu, K. Kageyama & C.M. Brasier, Phytophthora falcata T. Jung, K. Kageyama, S. Uematsu & M. Horta Jung, Phytophthora fansipanensis T. Jung, N.M. Chi, T. Corcobado & C.M. Brasier, Phytophthora frigidophila T. Jung, Y. Balci, K. Broders & I. Milenković, Phytophthora furcata T. Jung, N.M. Chi, I. Milenković & M. Horta Jung, Phytophthora inclinata N.M. Chi, T. Jung, M. Horta Jung & I. Milenković, Phytophthora indonesiensis T. Jung, M. Tarigan, L. Oliveira & I. Milenković, Phytophthora japonensis T. Jung, A. Hieno, H. Masuya & J.F. Webber, Phytophthora limosa T. Corcobado, T. Majek, M. Ferreira & T. Jung, Phytophthora macroglobulosa H.-C. Zeng, H.-H. Ho, F.-C. Zheng & T. Jung, Phytophthora montana T. Jung, Y. Balci, K. Broders & M. Horta Jung, Phytophthora multipapillata T. Jung, M. Tarigan, I. Milenković & M. Horta Jung, Phytophthora multiplex T. Jung, Y. Balci, K. Broders & M. Horta Jung, Phytophthora nimia T. Jung, H. Masuya, A. Hieno & C.M. Brasier, Phytophthora oblonga T. Jung, S. Uematsu, K. Kageyama & C.M. Brasier, Phytophthora obovoidea T. Jung, Y. Balci, L. Garcia & B. Mendieta-Araica, Phytophthora obturata T. Jung, N.M. Chi, I. Milenković & M. Horta Jung, Phytophthora penetrans T. Jung, Y. Balci, K. Broders & I. Milenković, Phytophthora platani T. Jung, A. Pérez-Sierra, S.O. Cacciola & M. Horta Jung, Phytophthora proliferata T. Jung, N.M. Chi, I. Milenković & M. Horta Jung, Phytophthora pseudocapensis T. Jung, T.-T. Chang, I. Milenković & M. Horta Jung, Phytophthora pseudocitrophthora T. Jung, S.O. Cacciola, J. Bakonyi & M. Horta Jung, Phytophthora pseudofrigida T. Jung, A. Durán, M. Tarigan & M. Horta Jung, Phytophthora pseudoccultans T. Jung, T.-T. Chang, I. Milenković & M. Horta Jung, Phytophthora pyriformis T. Jung, Y. Balci, K.D. Boders & M. Horta Jung, Phytophthora sumatera T. Jung, M. Tarigan, M. Junaid & A. Durán, Phytophthora transposita T. Jung, K. Kageyama, C.M. Brasier & H. Masuya, Phytophthora vacuola T. Jung, H. Masuya, K. Kageyama & J.F. Webber, Phytophthora valdiviana T. Jung, E. Sanfuentes von Stowasser, A. Durán & M. Horta Jung, Phytophthora variepedicellata T. Jung, Y. Balci, K. Broders & I. Milenković, Phytophthora vietnamensis T. Jung, N.M. Chi, I. Milenković & M. Horta Jung, Phytophthora ×australasiatica T. Jung, N.M. Chi, M. Tarigan & M. Horta Jung, Phytophthora ×lusitanica T. Jung, M. Horta Jung, C. Maia & I. Milenković, Phytophthora ×taiwanensis T. Jung, T.-T. Chang, H.-S. Fu & M. Horta Jung. Citation: Jung T, Milenković I, Balci Y, Janoušek J, Kudláček T, Nagy ZÁ, Baharuddin B, Bakonyi J, Broders KD, Cacciola SO, Chang T-T, Chi NM, Corcobado T, Cravador A, Đorđević B, Durán A, Ferreira M, Fu C-H, Garcia L, Hieno A, Ho H-H, Hong C, Junaid M, Kageyama K, Kuswinanti T, Maia C, Májek T, Masuya H, Magnano di San Lio G, Mendieta-Araica B, Nasri N, Oliveira LSS, Pane A, Pérez-Sierra A, Rosmana A, Sanfuentes von Stowasser E, Scanu B, Singh R, Stanivuković Z, Tarigan M, Thu PQ, Tomić Z, Tomšovský M, Uematsu S, Webber JF, Zeng H-C, Zheng F-C, Brasier CM, Horta Jung M (2024). Worldwide forest surveys reveal forty-three new species in Phytophthora major Clade 2 with fundamental implications for the evolution and biogeography of the genus and global plant biosecurity. Studies in Mycology 107: 251-388. doi: 10.3114/sim.2024.107.04.

Utility of skin tone on pulse oximetry in critically ill patients: a prospective cohort study

Importance

Pulse oximetry, a ubiquitous vital sign in modern medicine, has inequitable accuracy that disproportionately affects Black and Hispanic patients, with associated increases in mortality, organ dysfunction, and oxygen therapy. Although the root cause of these clinical performance discrepancies is believed to be skin tone, previous retrospective studies used self-reported race or ethnicity as a surrogate for skin tone.

Objective

To determine the utility of objectively measured skin tone in explaining pulse oximetry discrepancies.

Design Setting and Participants

Admitted hospital patients at Duke University Hospital were eligible for this prospective cohort study if they had pulse oximetry recorded up to 5 minutes prior to arterial blood gas (ABG) measurements. Skin tone was measured across sixteen body locations using administered visual scales (Fitzpatrick Skin Type, Monk Skin Tone, and Von Luschan), reflectance colorimetry (Delfin SkinColorCatch [L*, individual typology angle {ITA}, Melanin Index {MI}]), and reflectance spectrophotometry (Konica Minolta CM-700D [L*], Variable Spectro 1 [L*]).

Main Outcomes and Measures

Mean directional bias, variability of bias, and accuracy root mean square (ARMS), comparing pulse oximetry and ABG measurements. Linear mixed-effects models were fitted to estimate mean directional bias while accounting for clinical confounders.

Results

128 patients (57 Black, 56 White) with 521 ABG-pulse oximetry pairs were recruited, none with hidden hypoxemia. Skin tone data was prospectively collected using 6 measurement methods, generating 8 measurements. The collected skin tone measurements were shown to yield differences among each other and overlap with self-reported racial groups, suggesting that skin tone could potentially provide information beyond self-reported race. Among the eight skin tone measurements in this study, and compared to self-reported race, the Monk Scale had the best relationship with differences in pulse oximetry bias (point estimate: -2.40%; 95% CI: -4.32%, -0.48%; p=0.01) when comparing patients with lighter and dark skin tones.

Conclusions and relevance

We found clinical performance differences in pulse oximetry, especially in darker skin tones. Additional studies are needed to determine the relative contributions of skin tone measures and other potential factors on pulse oximetry discrepancies.

Semi-supervised ROC analysis for reliable and streamlined evaluation of phenotyping algorithms

OBJECTIVE

High-throughput phenotyping will accelerate the use of electronic health records (EHRs) for translational research. A critical roadblock is the extensive medical supervision required for phenotyping algorithm (PA) estimation and evaluation. To address this challenge, numerous weakly-supervised learning methods have been proposed. However, there is a paucity of methods for reliably evaluating the predictive performance of PAs when a very small proportion of the data is labeled. To fill this gap, we introduce a semi-supervised approach (ssROC) for estimation of the receiver operating characteristic (ROC) parameters of PAs (eg, sensitivity, specificity).

MATERIALS AND METHODS

ssROC uses a small labeled dataset to nonparametrically impute missing labels. The imputations are then used for ROC parameter estimation to yield more precise estimates of PA performance relative to classical supervised ROC analysis (supROC) using only labeled data. We evaluated ssROC with synthetic, semi-synthetic, and EHR data from Mass General Brigham (MGB).

RESULTS

ssROC produced ROC parameter estimates with minimal bias and significantly lower variance than supROC in the simulated and semi-synthetic data. For the 5 PAs from MGB, the estimates from ssROC are 30% to 60% less variable than supROC on average.

DISCUSSION

ssROC enables precise evaluation of PA performance without demanding large volumes of labeled data. ssROC is also easily implementable in open-source R software.

CONCLUSION

When used in conjunction with weakly-supervised PAs, ssROC facilitates the reliable and streamlined phenotyping necessary for EHR-based research.

LATTE: Label-efficient incident phenotyping from longitudinal electronic health records

Electronic health record (EHR) data are increasingly used to support real-world evidence studies but are limited by the lack of precise timings of clinical events. Here, we propose a label-efficient incident phenotyping (LATTE) algorithm to accurately annotate the timing of clinical events from longitudinal EHR data. By leveraging the pre-trained semantic embeddings, LATTE selects predictive features and compresses their information into longitudinal visit embeddings through visit attention learning. LATTE models the sequential dependency between the target event and visit embeddings to derive the timings. To improve label efficiency, LATTE constructs longitudinal silver-standard labels from unlabeled patients to perform semi-supervised training. LATTE is evaluated on the onset of type 2 diabetes, heart failure, and relapses of multiple sclerosis. LATTE consistently achieves substantial improvements over benchmark methods while providing high prediction interpretability. The event timings are shown to help discover risk factors of heart failure among patients with rheumatoid arthritis.

Trans-Balance: Reducing demographic disparity for prediction models in the presence of class imbalance

INTRODUCTION

Risk prediction, including early disease detection, prevention, and intervention, is essential to precision medicine. However, systematic bias in risk estimation caused by heterogeneity across different demographic groups can lead to inappropriate or misinformed treatment decisions. In addition, low incidence (class-imbalance) outcomes negatively impact the classification performance of many standard learning algorithms which further exacerbates the racial disparity issues. Therefore, it is crucial to improve the performance of statistical and machine learning models in underrepresented populations in the presence of heavy class imbalance.

METHOD

To address demographic disparity in the presence of class imbalance, we develop a novel framework, Trans-Balance, by leveraging recent advances in imbalance learning, transfer learning, and federated learning. We consider a practical setting where data from multiple sites are stored locally under privacy constraints.

RESULTS

We show that the proposed Trans-Balance framework improves upon existing approaches by explicitly accounting for heterogeneity across demographic subgroups and cohorts. We demonstrate the feasibility and validity of our methods through numerical experiments and a real application to a multi-cohort study with data from participants of four large, NIH-funded cohorts for stroke risk prediction.

CONCLUSION

Our findings indicate that the Trans-Balance approach significantly improves predictive performance, especially in scenarios marked by severe class imbalance and demographic disparity. Given its versatility and effectiveness, Trans-Balance offers a valuable contribution to enhancing risk prediction in biomedical research and related fields.

Federated and distributed learning applications for electronic health records and structured medical data: a scoping review

OBJECTIVES

Federated learning (FL) has gained popularity in clinical research in recent years to facilitate privacy-preserving collaboration. Structured data, one of the most prevalent forms of clinical data, has experienced significant growth in volume concurrently, notably with the widespread adoption of electronic health records in clinical practice. This review examines FL applications on structured medical data, identifies contemporary limitations, and discusses potential innovations.

MATERIALS AND METHODS

We searched 5 databases, SCOPUS, MEDLINE, Web of Science, Embase, and CINAHL, to identify articles that applied FL to structured medical data and reported results following the PRISMA guidelines. Each selected publication was evaluated from 3 primary perspectives, including data quality, modeling strategies, and FL frameworks.

RESULTS

Out of the 1193 papers screened, 34 met the inclusion criteria, with each article consisting of one or more studies that used FL to handle structured clinical/medical data. Of these, 24 utilized data acquired from electronic health records, with clinical predictions and association studies being the most common clinical research tasks that FL was applied to. Only one article exclusively explored the vertical FL setting, while the remaining 33 explored the horizontal FL setting, with only 14 discussing comparisons between single-site (local) and FL (global) analysis.

CONCLUSIONS

The existing FL applications on structured medical data lack sufficient evaluations of clinically meaningful benefits, particularly when compared to single-site analyses. Therefore, it is crucial for future FL applications to prioritize clinical motivations and develop designs and methodologies that can effectively support and aid clinical practice and research.

Associations between home environmental factors and childhood eczema and related symptoms in different cities in China

Previous studies have shown significant associations between home environmental factors and childhood eczema. However, few studies have compared how associations differ in different regions. This study investigated associations between home environmental factors and childhood eczema ever, and related symptoms including itchy rash (IR) and being awakened by itchy rash at night (awake by IR) in 4 cities located in different regions of China, based on cross-sectional investigations during 2010-2012. We used two-step analysis to explore the associations between influencing factors and eczema/related symptoms: first, group Least Absolute Shrinkage and Selection Operator (LASSO) was conducted to identify important factors among a list of candidates; then, the associations in total study population and in each city were estimated using logistic regression. We found these home environmental factors to be risk factors for eczema or related symptoms: large residence size, shared room, air cleaner at home, abnormal smell, perceived dry air, visible mold or damp stains, cooking with coal or wood, painted wall, incense, mice, new furniture during pregnancy, abnormal smell at birth, window condensation at birth and environmental tobacco smoke at birth. Environmental protective factors were rural house location and window ventilation. Associations of factors with eczema/related symptoms differed across cities. For example, air conditioning was protective for eczema in Beijing and awakening by IR in Shanghai with ORs of 0.70 (95%CI: 0.52, 0.95) and 0.33 (95%CI: 0.14, 0.81) respectively, but not significant in other cities. Our results have implications for improving home environments to reduce the risk of childhood eczema/related symptoms in different regions of China.

Facilitating Harmonization of Variables in Framingham, MESA, ARIC, and REGARDS Studies Through a Metadata Repository

BACKGROUND

High-quality research in cardiovascular prevention, as in other fields, requires inclusion of a broad range of data sets from different sources. Integrating and harmonizing different data sources are essential to increase generalizability, sample size, and representation of understudied populations-strengthening the evidence for the scientific questions being addressed.

METHODS

Here, we describe an effort to build an open-access repository and interactive online portal for researchers to access the metadata and code harmonizing data from 4 well-known cohort studies-the REGARDS (Reasons for Geographic and Racial Differences in Stroke) study, FHS (Framingham Heart Study), MESA (Multi-Ethnic Study of Atherosclerosis), and ARIC (Atherosclerosis Risk in Communities) study. We introduce a methodology and a framework used for preprocessing and harmonizing variables from multiple studies.

RESULTS

We provide a real-case study and step-by-step guidance to demonstrate the practical utility of our repository and interactive web page. In addition to our successful development of such an open-access repository and interactive web page, this exercise in harmonizing data from multiple cohort studies has revealed several key themes. These themes include the importance of careful preprocessing and harmonization of variables, the value of creating an open-access repository to facilitate collaboration and reproducibility, and the potential for using harmonized data to address important scientific questions and disparities in cardiovascular disease research.

CONCLUSIONS

By integrating and harmonizing these large-scale cohort studies, such a repository may improve the statistical power and representation of understudied cohorts, enabling development and validation of risk prediction models, identification and investigation of risk factors, and creating a platform for racial disparities research.

REGISTRATION

URL: https://precision.heart.org/duke-ninds.

[A case of metastatic breast cancer complicated by pulmonary tumor thrombotic microangiopathy]

Pulmonary tumor thrombotic microangiopathy is a malignancy-related complication with rapid progression and high mortality. To improve the understanding of the disease, early diagnosis and treatment are key to successful treatment. A 39-year-old patient with pulmonary hypertension transferred from another hospital was admitted to the First Affiliated Hospital of Guangzhou Medical University on September 26, 2021. The patient developed shortness of breath and progressive exacerbation over the past month. No pulmonary artery embolism was seen on computed tomography pulmonary angiography (CTPA) at the outside hospital where the breast cancer was diagnosed. Pulmonary tumor thrombotic microangiopathy was immediately considered on admission and oncological endocrine therapy was started. After treatment, the patient's dyspnoea improved, PET-CT showed significant tumor regression, and cardiac ultrasound showed a significant decrease in pulmonary artery pressure. The successful treatment experience of this case was summarized for reference.

Knowledge-Driven Online Multimodal Automated Phenotyping System

Though electronic health record (EHR) systems are a rich repository of clinical information with large potential, the use of EHR-based phenotyping algorithms is often hindered by inaccurate diagnostic records, the presence of many irrelevant features, and the requirement for a human-labeled training set. In this paper, we describe a knowledge-driven online multimodal automated phenotyping (KOMAP) system that i) generates a list of informative features by an online narrative and codified feature search engine (ONCE) and ii) enables the training of a multimodal phenotyping algorithm based on summary data. Powered by composite knowledge from multiple EHR sources, online article corpora, and a large language model, features selected by ONCE show high concordance with the state-of-the-art AI models (GPT4 and ChatGPT) and encourage large-scale phenotyping by providing a smaller but highly relevant feature set. Validation of the KOMAP system across four healthcare centers suggests that it can generate efficient phenotyping algorithms with robust performance. Compared to other methods requiring patient-level inputs and gold-standard labels, the fully online KOMAP provides a significant opportunity to enable multi-center collaboration.

FedScore: A privacy-preserving framework for federated scoring system development

OBJECTIVE

We propose FedScore, a privacy-preserving federated learning framework for scoring system generation across multiple sites to facilitate cross-institutional collaborations.

MATERIALS AND METHODS

The FedScore framework includes five modules: federated variable ranking, federated variable transformation, federated score derivation, federated model selection and federated model evaluation. To illustrate usage and assess FedScore's performance, we built a hypothetical global scoring system for mortality prediction within 30 days after a visit to an emergency department using 10 simulated sites divided from a tertiary hospital in Singapore. We employed a pre-existing score generator to construct 10 local scoring systems independently at each site and we also developed a scoring system using centralized data for comparison.

RESULTS

We compared the acquired FedScore model's performance with that of other scoring models using the receiver operating characteristic (ROC) analysis. The FedScore model achieved an average area under the curve (AUC) value of 0.763 across all sites, with a standard deviation (SD) of 0.020. We also calculated the average AUC values and SDs for each local model, and the FedScore model showed promising accuracy and stability with a high average AUC value which was closest to the one of the pooled model and SD which was lower than that of most local models.

CONCLUSION

This study demonstrates that FedScore is a privacy-preserving scoring system generator with potentially good generalizability.

Semi-supervised calibration of noisy event risk (SCANER) with electronic health records

OBJECTIVE

Electronic health records (EHR), containing detailed longitudinal clinical information on a large number of patients and covering broad patient populations, open opportunities for comprehensive predictive modeling of disease progression and treatment response. However, since EHRs were originally constructed for administrative purposes not for research, in the EHR-linked studies, it is often not feasible to capture reliable information for analytical variables, especially in the survival setting, when both accurate event status and event times are needed for model building. For example, progression-free survival (PFS), a commonly used survival outcome for cancer patients, often involves complex information embedded in free-text clinical notes and cannot be extracted reliably. Proxies of PFS time such as time to the first mention of progression in the notes are at best good approximations to the true event time. This leads to difficulty in efficiently estimating event rates for an EHR patient cohort. Estimating survival rates based on error-prone outcome definitions can lead to biased results and hamper the power in the downstream analysis. On the other hand, extracting accurate event time information via manual annotation is time and resource intensive. The objective of this study is to develop a calibrated survival rate estimator using noisy outcomes from EHR data.

MATERIALS AND METHODS

In this paper, we propose a two-stage semi-supervised calibration of noisy event rate (SCANER) estimator that can effectively overcome censoring induced dependency and attains more robust performance (i.e., not sensitive to misspecification of the imputation model) by fully utilizing both a small-labeled set of gold-standard survival outcomes annotated via manual chart review and a set of proxy features automatically captured via EHR in the unlabeled set. We validate the SCANER estimator by estimating the PFS rates for a virtual cohort of lung cancer patients from one large tertiary care center and the ICU-free survival rates for COVID patients from two large tertiary care centers.

RESULTS

In terms of survival rate estimates, the SCANER had very similar point estimates compared to the complete-case Kaplan Meier estimator. On the other hand, other benchmark methods for comparison, which fail to account for the induced dependency between event time and the censoring time conditioning on surrogate outcomes, produced biased results across all three case studies. In terms of standard errors, the SCANER estimator was more efficient than the KM estimator, with up to 50% efficiency gain.

CONCLUSION

The SCANER estimator achieves more efficient, robust, and accurate survival rate estimates compared to existing approaches. This promising new approach can also improve the resolution (i.e., granularity of event time) by using labels conditioning on multiple surrogates, particularly among less common or poorly coded conditions.

Identifying shared genetic architecture between rheumatoid arthritis and other conditions: a phenome-wide association study with genetic risk scores

BACKGROUND

Rheumatoid arthritis (RA) shares genetic variants with other autoimmune conditions, but existing studies test the association between RA variants with a pre-defined set of phenotypes. The objective of this study was to perform a large-scale, systemic screen to determine phenotypes that share genetic architecture with RA to inform our understanding of shared pathways.

METHODS

In the UK Biobank (UKB), we constructed RA genetic risk scores (GRS) incorporating human leukocyte antigen (HLA) and non-HLA risk alleles. Phenotypes were defined using groupings of International Classification of Diseases (ICD) codes. Patients with an RA code were excluded to mitigate the possibility of associations being driven by the diagnosis or management of RA. We performed a phenome-wide association study, testing the association between the RA GRS with phenotypes using multivariate generalized estimating equations that adjusted for age, sex, and first five principal components. Statistical significance was defined using Bonferroni correction. Results were replicated in an independent cohort and replicated phenotypes were validated using medical record review of patients.

FINDINGS

We studied n = 316,166 subjects from UKB without evidence of RA and screened for association between the RA GRS and n = 1317 phenotypes. In the UKB, 20 phenotypes were significantly associated with the RA GRS, of which 13 (65%) were immune mediated conditions including polymyalgia rheumatica, granulomatosis with polyangiitis (GPA), type 1 diabetes, and multiple sclerosis. We further identified a novel association in Celiac disease where the HLA and non-HLA alleles had strong associations in opposite directions. Strikingly, we observed that the non-HLA GRS was exclusively associated with greater risk of the validated conditions, suggesting shared underlying pathways outside the HLA region.

INTERPRETATION

This study replicated and identified novel autoimmune phenotypes verified by medical record review that share immune pathways with RA and may inform opportunities for shared treatment targets, as well as risk assessment for conditions with a paucity of genomic data, such as GPA.

FUNDING

This research was funded by the US National Institutes of Health (P30AR072577, R21AR078339, R35GM142879, T32AR007530) and the Harold and DuVal Bowen Fund.

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.

ARCH: Large-scale Knowledge Graph via Aggregated Narrative Codified Health Records Analysis

Objective

Electronic health record (EHR) systems contain a wealth of clinical data stored as both codified data and free-text narrative notes, covering hundreds of thousands of clinical concepts available for research and clinical care. The complex, massive, heterogeneous, and noisy nature of EHR data imposes significant challenges for feature representation, information extraction, and uncertainty quantification. To address these challenges, we proposed an efficient Aggregated naRrative Codified Health (ARCH) records analysis to generate a large-scale knowledge graph (KG) for a comprehensive set of EHR codified and narrative features.

Methods

The ARCH algorithm first derives embedding vectors from a co-occurrence matrix of all EHR concepts and then generates cosine similarities along with associated p -values to measure the strength of relatedness between clinical features with statistical certainty quantification. In the final step, ARCH performs a sparse embedding regression to remove indirect linkage between entity pairs. We validated the clinical utility of the ARCH knowledge graph, generated from 12.5 million patients in the Veterans Affairs (VA) healthcare system, through downstream tasks including detecting known relationships between entity pairs, predicting drug side effects, disease phenotyping, as well as sub-typing Alzheimer's disease patients.

Results

ARCH produces high-quality clinical embeddings and KG for over 60,000 EHR concepts, as visualized in the R-shiny powered web-API (https://celehs.hms.harvard.edu/ARCH/). The ARCH embeddings attained an average area under the ROC curve (AUC) of 0.926 and 0.861 for detecting pairs of similar EHR concepts when the concepts are mapped to codified data and to NLP data; and 0.810 (codified) and 0.843 (NLP) for detecting related pairs. Based on the p -values computed by ARCH, the sensitivity of detecting similar and related entity pairs are 0.906 and 0.888 under false discovery rate (FDR) control of 5%. For detecting drug side effects, the cosine similarity based on the ARCH semantic representations achieved an AUC of 0.723 while the AUC improved to 0.826 after few-shot training via minimizing the loss function on the training data set. Incorporating NLP data substantially improved the ability to detect side effects in the EHR. For example, based on unsupervised ARCH embeddings, the power of detecting drug-side effects pairs when using codified data only was 0.15, much lower than the power of 0.51 when using both codified and NLP concepts. Compared to existing large-scale representation learning methods including PubmedBERT, BioBERT and SAPBERT, ARCH attains the most robust performance and substantially higher accuracy in detecting these relationships. Incorporating ARCH selected features in weakly supervised phenotyping algorithms can improve the robustness of algorithm performance, especially for diseases that benefit from NLP features as supporting evidence. For example, the phenotyping algorithm for depression attained an AUC of 0.927 when using ARCH selected features but only 0.857 when using codified features selected via the KESER network[1]. In addition, embeddings and knowledge graphs generated from the ARCH network were able to cluster AD patients into two subgroups, where the fast progression subgroup had a much higher mortality rate.

Conclusions

The proposed ARCH algorithm generates large-scale high-quality semantic representations and knowledge graph for both codified and NLP EHR features, useful for a wide range of predictive modeling tasks.

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.

Multimodal representation learning for predicting molecule-disease relations

MOTIVATION

Predicting molecule-disease indications and side effects is important for drug development and pharmacovigilance. Comprehensively mining molecule-molecule, molecule-disease and disease-disease semantic dependencies can potentially improve prediction performance.

METHODS

We introduce a Multi-Modal REpresentation Mapping Approach to Predicting molecular-disease relations (M2REMAP) by incorporating clinical semantics learned from electronic health records (EHR) of 12.6 million patients. Specifically, M2REMAP first learns a multimodal molecule representation that synthesizes chemical property and clinical semantic information by mapping molecule chemicals via a deep neural network onto the clinical semantic embedding space shared by drugs, diseases and other common clinical concepts. To infer molecule-disease relations, M2REMAP combines multimodal molecule representation and disease semantic embedding to jointly infer indications and side effects.

RESULTS

We extensively evaluate M2REMAP on molecule indications, side effects and interactions. Results show that incorporating EHR embeddings improves performance significantly, for example, attaining an improvement over the baseline models by 23.6% in PRC-AUC on indications and 23.9% on side effects. Further, M2REMAP overcomes the limitation of existing methods and effectively predicts drugs for novel diseases and emerging pathogens.

AVAILABILITY AND IMPLEMENTATION

The code is available at https://github.com/celehs/M2REMAP, and prediction results are provided at https://shiny.parse-health.org/drugs-diseases-dev/.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Radiomics signature based on CECT for non-invasive prediction of response to anti-PD-1 therapy in patients with hepatocellular carcinoma

PURPOSE

This study aimed to develop a radiomics signature (RS) based on contrast-enhanced computed tomography (CECT) and evaluate its potential predictive value in hepatocellular carcinoma (HCC) patients receiving anti-PD-1 therapy.

METHOD

CECT scans of 76 HCC patients who received anti-PD-1 therapy were obtained in this study (training group = 53 and validation group = 23). The least absolute shrinkage and selection operator (LASSO) regression was applied to select radiomics features of primary and metastatic lesions and establish a RS to predict lesion-level response. Then, a nomogram combined the mean RS (MRS) and clinical variables with patient-level response as the end point.

RESULTS

In the lesion-level analysis, the area under the curves (AUCs) of RS in the training and validation groups were 0.751 (95% CI, 0.668-0.835) and 0.734 (95% CI, 0.604-0.864), respectively. In the patient-level analysis, the AUCs of the nomogram in the training and validation groups were 0.897 (95% CI, 0.798-0.996) and 0.889 (95% CI, 0.748-1.000), respectively. The nomogram stratified patients into low- and high-risk groups, which showed a significant difference in progression-free survival (PFS) (p<0.05).

CONCLUSIONS

The RS is a noninvasive biomarker for predicting anti-PD-1 therapy response in patients with HCC. The nomogram may be of clinical use for identifying high-risk patients and formulating individualised treatments.

Real-world outcomes of Selexipag for treatment of pulmonary hypertension in an Asian population

Funding Acknowledgements

Type of funding sources: None.

Introduction

Selexipag is an oral selective prostacyclin IP receptor agonist indicated for treatment of pulmonary arterial hypertension (PAH). Data on its real-world safety and efficacy in Asians is lacking.

Purpose

We sought to evaluate the clinical characteristics, treatment regimens and outcomes of patients initiated on selexipag in a tertiary cardiac centre in Asia.

Methods

This was a retrospective study on all patients initiated on selexipag from January 2017 to December 2020. Baseline and follow up characteristics including demographics, functional status and clinical data were collected. Clinical outcomes evaluated included hospitalisation for PH related complications and all-cause mortality. Patients were risk stratified using the COMPERA 2.0 risk scores.

Results

A total of 36 PAH patients were treated with selexipag. At baseline, most patients were WHO functional class II or III (36.4% and 51.5% respectively), with a NT-proBNP of 1335 pg/ml (557 – 2918) and 6 minute walk test (6MWT) duration of 327.5 ±126.4 meters. Selexipag was initiated at 200mcg twice daily dosage for all except one patient (started at 200mcg once daily) and the maximum tolerated dose ranged from 200mcg twice daily to 1400mcg twice daily, with majority tolerating up to a dose of 600mcg twice daily (58.3%). Side effects were reported in 23 patients (63.9%), of which headache (27.8%), diarrhea (30.6%) or musculoskeletal symptoms (27.8%) were predominant. After a median follow up duration of 25.9 ± 23.1 months, selexipag was stopped in 20 patients (55.6%), of which eight patients were due to PAH progression requiring alternative therapy, and 12 patients due to side effects from selexipag. At baseline, patients were classified into low (8.3%), intermediate-low (30.6%), intermediate-high (33.3%) and high risk (27.8%) respectively. Patients who continued on selexipag at follow up showed no change (46.2%), improvement (15.4%) and deterioration (38.5%) in risk score. In the overall cohort of 36 patients, majority (75%) had at least one hospitalisation for PAH related complications and 15 patients (41.7%) demised.

Conclusion

In this real-world study, while selexipag was associated with a stable or improved PAH risk scores in majority of patients, there was a subset of patients with disease progression or intolerance to the medication. Further studies are warranted to identify patients who will benefit most from this therapy.

Predictive Accuracy of Stroke Risk Prediction Models Across Black and White Race, Sex, and Age Groups

Importance

Stroke is the fifth-highest cause of death in the US and a leading cause of serious long-term disability with particularly high risk in Black individuals. Quality risk prediction algorithms, free of bias, are key for comprehensive prevention strategies.

Objective

To compare the performance of stroke-specific algorithms with pooled cohort equations developed for atherosclerotic cardiovascular disease for the prediction of new-onset stroke across different subgroups (race, sex, and age) and to determine the added value of novel machine learning techniques.

Design, Setting, and Participants

Retrospective cohort study on combined and harmonized data from Black and White participants of the Framingham Offspring, Atherosclerosis Risk in Communities (ARIC), Multi-Ethnic Study for Atherosclerosis (MESA), and Reasons for Geographical and Racial Differences in Stroke (REGARDS) studies (1983-2019) conducted in the US. The 62 482 participants included at baseline were at least 45 years of age and free of stroke or transient ischemic attack.

Exposures

Published stroke-specific algorithms from Framingham and REGARDS (based on self-reported risk factors) as well as pooled cohort equations for atherosclerotic cardiovascular disease plus 2 newly developed machine learning algorithms.

Main Outcomes and Measures

Models were designed to estimate the 10-year risk of new-onset stroke (ischemic or hemorrhagic). Discrimination concordance index (C index) and calibration ratios of expected vs observed event rates were assessed at 10 years. Analyses were conducted by race, sex, and age groups.

Results

The combined study sample included 62 482 participants (median age, 61 years, 54% women, and 29% Black individuals). Discrimination C indexes were not significantly different for the 2 stroke-specific models (Framingham stroke, 0.72; 95% CI, 0.72-073; REGARDS self-report, 0.73; 95% CI, 0.72-0.74) vs the pooled cohort equations (0.72; 95% CI, 0.71-0.73): differences 0.01 or less (P values >.05) in the combined sample. Significant differences in discrimination were observed by race: the C indexes were 0.76 for all 3 models in White vs 0.69 in Black women (all P values <.001) and between 0.71 and 0.72 in White men and between 0.64 and 0.66 in Black men (all P values ≤.001). When stratified by age, model discrimination was better for younger (<60 years) vs older (≥60 years) adults for both Black and White individuals. The ratios of observed to expected 10-year stroke rates were closest to 1 for the REGARDS self-report model (1.05; 95% CI, 1.00-1.09) and indicated risk overestimation for Framingham stroke (0.86; 95% CI, 0.82-0.89) and pooled cohort equations (0.74; 95% CI, 0.71-0.77). Performance did not significantly improve when novel machine learning algorithms were applied.

Conclusions and Relevance

In this analysis of Black and White individuals without stroke or transient ischemic attack among 4 US cohorts, existing stroke-specific risk prediction models and novel machine learning techniques did not significantly improve discriminative accuracy for new-onset stroke compared with the pooled cohort equations, and the REGARDS self-report model had the best calibration. All algorithms exhibited worse discrimination in Black individuals than in White individuals, indicating the need to expand the pool of risk factors and improve modeling techniques to address observed racial disparities and improve model performance.

Acute respiratory distress syndrome after SARS-CoV-2 infection on young adult population: International observational federated study based on electronic health records through the 4CE consortium

PURPOSE

In young adults (18 to 49 years old), investigation of the acute respiratory distress syndrome (ARDS) after severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection has been limited. We evaluated the risk factors and outcomes of ARDS following infection with SARS-CoV-2 in a young adult population.

METHODS

A retrospective cohort study was conducted between January 1st, 2020 and February 28th, 2021 using patient-level electronic health records (EHR), across 241 United States hospitals and 43 European hospitals participating in the Consortium for Clinical Characterization of COVID-19 by EHR (4CE). To identify the risk factors associated with ARDS, we compared young patients with and without ARDS through a federated analysis. We further compared the outcomes between young and old patients with ARDS.

RESULTS

Among the 75,377 hospitalized patients with positive SARS-CoV-2 PCR, 1001 young adults presented with ARDS (7.8% of young hospitalized adults). Their mortality rate at 90 days was 16.2% and they presented with a similar complication rate for infection than older adults with ARDS. Peptic ulcer disease, paralysis, obesity, congestive heart failure, valvular disease, diabetes, chronic pulmonary disease and liver disease were associated with a higher risk of ARDS. We described a high prevalence of obesity (53%), hypertension (38%- although not significantly associated with ARDS), and diabetes (32%).

CONCLUSION

Trough an innovative method, a large international cohort study of young adults developing ARDS after SARS-CoV-2 infection has been gather. It demonstrated the poor outcomes of this population and associated risk factor.

Long-term kidney function recovery and mortality after COVID-19-associated acute kidney injury: An international multi-centre observational cohort study

Background

While acute kidney injury (AKI) is a common complication in COVID-19, data on post-AKI kidney function recovery and the clinical factors associated with poor kidney function recovery is lacking.

Methods

A retrospective multi-centre observational cohort study comprising 12,891 hospitalized patients aged 18 years or older with a diagnosis of SARS-CoV-2 infection confirmed by polymerase chain reaction from 1 January 2020 to 10 September 2020, and with at least one serum creatinine value 1-365 days prior to admission. Mortality and serum creatinine values were obtained up to 10 September 2021.

Findings

Advanced age (HR 2.77, 95%CI 2.53-3.04, p < 0.0001), severe COVID-19 (HR 2.91, 95%CI 2.03-4.17, p < 0.0001), severe AKI (KDIGO stage 3: HR 4.22, 95%CI 3.55-5.00, p < 0.0001), and ischemic heart disease (HR 1.26, 95%CI 1.14-1.39, p < 0.0001) were associated with worse mortality outcomes. AKI severity (KDIGO stage 3: HR 0.41, 95%CI 0.37-0.46, p < 0.0001) was associated with worse kidney function recovery, whereas remdesivir use (HR 1.34, 95%CI 1.17-1.54, p < 0.0001) was associated with better kidney function recovery. In a subset of patients without chronic kidney disease, advanced age (HR 1.38, 95%CI 1.20-1.58, p < 0.0001), male sex (HR 1.67, 95%CI 1.45-1.93, p < 0.0001), severe AKI (KDIGO stage 3: HR 11.68, 95%CI 9.80-13.91, p < 0.0001), and hypertension (HR 1.22, 95%CI 1.10-1.36, p = 0.0002) were associated with post-AKI kidney function impairment. Furthermore, patients with COVID-19-associated AKI had significant and persistent elevations of baseline serum creatinine 125% or more at 180 days (RR 1.49, 95%CI 1.32-1.67) and 365 days (RR 1.54, 95%CI 1.21-1.96) compared to COVID-19 patients with no AKI.

Interpretation

COVID-19-associated AKI was associated with higher mortality, and severe COVID-19-associated AKI was associated with worse long-term post-AKI kidney function recovery.

Funding

Authors are supported by various funders, with full details stated in the acknowledgement section.

Distribution and accumulation of mercury in pot-grown African rice cultivars (Oryza glaberrima Steud. and Oryza sativa L.) determined via LA-ICP-MS

There is limited information concerning the distribution of mercury in rice, particularly in African rice. The objective was to compare the distribution of total mercury (THg) and methylmercury (MeHg) in African rice (Oryza glaberrima Steud.) and Asian rice (O. sativa L.). It is hypothesized that increased mineral accumulation and greater stress tolerance in O. glaberrima will affect the uptake and distribution of THg and MeHg, compared to O. sativa. Rice varieties from the Republic of Mali, including O. glaberrima (n =1) and O. sativa (n = 2), were cultivated in a greenhouse, in mercury-spiked soil (50 mg/kg) (n =3 replicates/variety). THg and MeHg concentrations were analyzed in the grain (brown rice), and the THg distribution was analyzed using laser ablation inductively coupled-plasma mass spectrometry (LA-ICP-MS). THg and MeHg concentrations did not differ between O. glaberrima and O. sativa grain. However, in both O. sativa varieties, THg was highly concentrated in the scutellum, which surrounds the embryo and is removed during polishing. Conversely, in O. glaberrima grain, THg was widely distributed throughout the endosperm, the edible portion of the grain. Differences in the THg distribution in O. glaberrima grain, compared to O. sativa, may elevate the risk of mercury exposure through ingestion of polished rice. The novelty of this study includes the investigation of a less-studied rice species (O. glaberrima), the use of a highly sensitive elemental imaging technique (LA-ICP-MS), and its finding of a different grain THg distribution in O. glaberrima than has been observed in O. sativa.

A semi-supervised adaptive Markov Gaussian embedding process (SAMGEP) for prediction of phenotype event times using the electronic health record

While there exist numerous methods to identify binary phenotypes (i.e. COPD) using electronic health record (EHR) data, few exist to ascertain the timings of phenotype events (i.e. COPD onset or exacerbations). Estimating event times could enable more powerful use of EHR data for longitudinal risk modeling, including survival analysis. Here we introduce Semi-supervised Adaptive Markov Gaussian Embedding Process (SAMGEP), a semi-supervised machine learning algorithm to estimate phenotype event times using EHR data with limited observed labels, which require resource-intensive chart review to obtain. SAMGEP models latent phenotype states as a binary Markov process, and it employs an adaptive weighting strategy to map timestamped EHR features to an embedding function that it models as a state-dependent Gaussian process. SAMGEP's feature weighting achieves meaningful feature selection, and its predictions significantly improve AUCs and F1 scores over existing approaches in diverse simulations and real-world settings. It is particularly adept at predicting cumulative risk and event counting process functions, and is robust to diverse generative model parameters. Moreover, it achieves high accuracy with few (50-100) labels, efficiently leveraging unlabeled EHR data to maximize information gain from costly-to-obtain event time labels. SAMGEP can be used to estimate accurate phenotype state functions for risk modeling research.

Application of machine learning to identify top determinants of fibrofatty plaque burden by CCTA in humans with psoriasis

Introduction

Fibrofatty plaque burden (FFB) is a high-risk, vulnerable plaque feature comprised of an atheromatous core and fibrous cap with increased risk of coronary artery disease (CAD) [1]. Psoriasis (PSO) is a chronic inflammatory disease linked with atherosclerotic risk and premature cardiovascular disease, driven in part by vulnerable plaque rupture [2,3]. Machine learning (ML) previously showed the prognostic value of FFB in predicting 5-year risk of cardiac-related mortality in patients with CAD [4]. Whether ML can predict FFB in psoriasis is understudied.

Purpose

To use ML to identify top determinants of FFB by CCTA in PSO.

Methods

320 consecutive participants with psoriasis were recruited as part of an ongoing cohort study, of whom 307 had FFB analyzed with coronary computed tomography angiography (CCTA) and quantified by QAngio CT (Medis, The Netherlands). 140 out of 182 potential determinants were subjected to ML algorithms analyzed by random forest and validated by 5-fold cross validation to select the top determinants based on R-square criteria. Lipid concentration and size were measured by nuclear magnetic resonance (NMR) and sdLDL-C was calculated by Sampson's formula.

Results

The top 21 determinants of FFB at baseline were grouped into 3 categories: cardiometabolic risk factors (BMI, sex, DBP, mean arterial pressure, exercise, heart rate, glucose, anxiety, psoriasis disease duration), clinical measurements (basophils, platelets, hemoglobin, RBC, alkaline phosphatase, ALT, creatinine, neutrophil-to-lymphocyte ratio), and lipoproteins (LDL particle size, apolipoprotein A1, apolipoprotein B-to-A1 ratio, calculated sdLDL-C).

Conclusion

ML confirmed that FFB strongly correlates with cardiometabolic risk factors, clinical measurements, and lipoproteins. Further investigations into these top determinants of FFB over time may provide insight into potential therapeutic interventions that decrease cardiovascular risk in patients with chronic inflammatory diseases and should be validated in larger studies.

Funding Acknowledgement

Type of funding sources: Public Institution(s). Main funding source(s): This study was supported by the National Heart, Lung and Blood Institute (NHLBI) IntramuralResearch Program (ZIA-HL-06193). This research was made possible through the NIH MedicalResearch Scholars Program, a public-private partnership supported jointly by the NIH andcontributions to the Foundation for the NIH from the Doris Duke Charitable Foundation,Genentech, the American Association for Dental Research, the Colgate-Palmolive Company, andother private donors.

Estimated Clinical Trial Capacity of Sites Participating in the COVID-19 Convalescent Plasma Expanded Access Program

This cross-sectional study estimates the trial capacity of sites participating in the COVID-19 convalescent plasma expanded access program.

Weakly Semi-supervised phenotyping using Electronic Health records

OBJECTIVE

Electronic Health Record (EHR) based phenotyping is a crucial yet challenging problem in the biomedical field. Though clinicians typically determine patient-level diagnoses via manual chart review, the sheer volume and heterogeneity of EHR data renders such tasks challenging, time-consuming, and prohibitively expensive, thus leading to a scarcity of clinical annotations in EHRs. Weakly supervised learning algorithms have been successfully applied to various EHR phenotyping problems, due to their ability to leverage information from large quantities of unlabeled samples to better inform predictions based on a far smaller number of patients. However, most weakly supervised methods are subject to the challenge to choose the right cutoff value to generate an optimal classifier. Furthermore, since they only utilize the most informative features (i.e., main ICD and NLP counts) they may fail for episodic phenotypes that cannot be consistently detected via ICD and NLP data. In this paper, we propose a label-efficient, weakly semi-supervised deep learning algorithm for EHR phenotyping (WSS-DL), which overcomes the limitations above.

MATERIALS AND METHODS

WSS-DL classifies patient-level disease status through a series of learning stages: 1) generating silver standard labels, 2) deriving enhanced-silver-standard labels by fitting a weakly supervised deep learning model to data with silver standard labels as outcomes and high dimensional EHR features as input, and 3) obtaining the final prediction score and classifier by fitting a supervised learning model to data with a minimal number of gold standard labels as the outcome, and the enhanced-silver-standard labels and a minimal set of most informative EHR features as input. To assess the generalizability of WSS-DL across different phenotypes and medical institutions, we apply WSS-DL to classify a total of 17 diseases, including both acute and chronic conditions, using EHR data from three healthcare systems. Additionally, we determine the minimum quantity of training labels required by WSS-DL to outperform existing supervised and semi-supervised phenotyping methods.

RESULTS

The proposed method, in combining the strengths of deep learning and weakly semi-supervised learning, successfully leverages the crucial phenotyping information contained in EHR features from unlabeled samples. Indeed, the deep learning model's ability to handle high-dimensional EHR features allows it to generate strong phenotype status predictions from silver standard labels. These predictions, in turn, provide highly effective features in the final logistic regression stage, leading to high phenotyping accuracy in notably small subsets of labeled data (e.g. n = 40 labeled samples).

CONCLUSION

Our method's high performance in EHR datasets with very small numbers of labels indicates its potential value in aiding doctors to diagnose rare diseases as well as conditions susceptible to misdiagnosis.

SurvMaximin: Robust federated approach to transporting survival risk prediction models

OBJECTIVE

For multi-center heterogeneous Real-World Data (RWD) with time-to-event outcomes and high-dimensional features, we propose the SurvMaximin algorithm to estimate Cox model feature coefficients for a target population by borrowing summary information from a set of health care centers without sharing patient-level information.

MATERIALS AND METHODS

For each of the centers from which we want to borrow information to improve the prediction performance for the target population, a penalized Cox model is fitted to estimate feature coefficients for the center. Using estimated feature coefficients and the covariance matrix of the target population, we then obtain a SurvMaximin estimated set of feature coefficients for the target population. The target population can be an entire cohort comprised of all centers, corresponding to federated learning, or a single center, corresponding to transfer learning.

RESULTS

Simulation studies and a real-world international electronic health records application study, with 15 participating health care centers across three countries (France, Germany, and the U.S.), show that the proposed SurvMaximin algorithm achieves comparable or higher accuracy compared with the estimator using only the information of the target site and other existing methods. The SurvMaximin estimator is robust to variations in sample sizes and estimated feature coefficients between centers, which amounts to significantly improved estimates for target sites with fewer observations.

CONCLUSIONS

The SurvMaximin method is well suited for both federated and transfer learning in the high-dimensional survival analysis setting. SurvMaximin only requires a one-time summary information exchange from participating centers. Estimated regression vectors can be very heterogeneous. SurvMaximin provides robust Cox feature coefficient estimates without outcome information in the target population and is privacy-preserving.

The efficacy of parecoxib in improving pain after total knee or total hip arthroplasty: Systematic review and meta-analysis

BACKGROUND

The cyclooxygenase-2 (COX-2) selective inhibitor parecoxib is widely used in the treatment of pain and inflammation. Parecoxib has been adopted for use for postoperative analgesia following a range of surgical procedures (orthopedic, general, gynecological, and dental surgery). Total knee or total hip arthroplasty (THA) surgery is mostly done in older patients, so postoperative analgesics need to be used more carefully, and the safety and efficacy of parecoxib in this type of surgery need to be further verified. The aim of this study was to investigate the effects of parecoxib on patient safety, cumulative morphine consumption and was at 24 and 48 hours in the analgesic treatment of total knee or THA for meta-analysis and systematic review, with few studies in this area so far.

METHODS

We searched the Online Database Cochrane Library, PubMed, Web of Science, EMBASE, and CBM (SinoMed), CNKI, VIP, WANFANG up to January 2021. According to the value of I2, the random-effect model or fixed-effect model was supposed to combine data from studies, respectively. Publication bias was assessed through funneling plot and Beggs test. Review Manager 5.3 and Stata 16.0 software were applied to perform the statistical analyses.

RESULTS

Eleven RCTs which involved 1690 participants were included in this study. The meta-analysis indicated parecoxib sodium could not significantly reduce the incidence of adverse events after total knee or THA compared with placebo. There was no statistical significance in incidence of nausea and vomiting. 24 hours resting VAS score was statistically significant between the group. The 48-hour resting VAS scores did not indicate a significant difference between the groups.

CONCLUSION

Parecoxib can reduce the incidence of adverse events after total knee or total hip surgery to some extent but cannot reduce the incidence of nausea and vomiting. Twenty-four hour postoperative analgesia is better than placebo, but 48 hours after operation analgesia is the same as placebo.

Aldehyde dehydrogenase 2 rs671 polymorphism and multiple diseases: protocol for a quantitative umbrella review of meta-analyses

BACKGROUND

The mutant allele (*2) of aldehyde dehydrogenase type 2 (ALDH2) caused by a single nucleotide variant (rs671) inhibits enzymatic activity and is associated with multiple diseases. In recent years, an explosive number of original studies and meta-analyses have been conducted to examine the associations of ALDH2 rs671 polymorphism with diseases. Due to conflicting results, the overall associations of ALDH2 rs671 polymorphism and multiple diseases remain unclear.

METHODS

A quantitative umbrella review will be conducted on meta-analyses of genetic association studies to examine the pleiotropic effects of ALDH2 rs671, mainly including cardio-cerebral vascular disease, diabetes mellitus, cancer, neurodegenerative disease, and alcohol-induced medical disease. A search of relevant literature according to comprehensive search strategies will be performed on studies published before July 1st, 2022 in PubMed, MEDLINE Ovid, Embase, Cochrane Database of Systematic Reviews, and Web of Science. Study selection, data extraction, methodology quality assessment, and strength of evidence assessment will be conducted by two reviewers independently and in duplicate. Included meta-analyses will be grouped by outcomes. Data conflicts and overlap between meta-analyses will be managed through updated standardized and customized methods including the calculation of CCA for study selection reference, application of Doi plots to assess small-study effects and others. Evidence from included meta-analyses will be quantitatively synthesized by overlap-corrected analyses and meta-analysis using primary studies.

DISCUSSION

This umbrella review is expected to generate systematic evidence on the association between ALDH2 rs671 and diseases. Specific approaches were developed to address key challenges in conducting an umbrella review, including assessment tools of methodology and evidence quality of meta-analyses, methods to manage overlap between meta-analyses, a "stop-light" plot to summarize key findings. These approaches provide applicable methods for future umbrella reviews of meta-analyses on genetic association studies.

TRIAL REGISTRATION

CRD42021223812.

Scalable relevance ranking algorithm via semantic similarity assessment improves efficiency of medical chart review

OBJECTIVE

Accurately assigning phenotype information to individual patients via computational phenotyping using Electronic Health Records (EHRs) has been seen as the first step towards enabling EHRs for precision medicine research. Chart review labels annotated by clinical experts, also known as "gold standard" labels, are essential for the development and validation of computational phenotyping algorithms. However, given the complexity of EHR systems, the process of chart review is both labor intensive and time consuming. We propose a fully automated algorithm, referred to as pGUESS, to rank EHR notes according to their relevance to a given phenotype. By identifying the most relevant notes, pGUESS can greatly improve the efficiency and accuracy of chart reviews.

METHOD

pGUESS uses prior guided semantic similarity to measure the informativeness of a clinical note to a given phenotype. We first select candidate clinical concepts from a pool of comprehensive medical concepts using public knowledge sources and then derive the semantic embedding vector (SEV) for a reference article (SEV_ref) and each note (SEV_note). The algorithm scores the relevance of a note as the cosine similarity between SEV_note and SEV_ref.

RESULTS

The algorithm was validated against four sets of 200 notes that were manually annotated by clinical experts to assess their informativeness to one of three disease phenotypes. pGUESS algorithm substantially outperforms existing unsupervised approaches for classifying the relevance status with respect to both accuracy and scalability across phenotypes. Averaging over the three phenotypes, the rank correlation between the algorithm ranking and gold standard label was 0.64 for pGUESS, but only 0.47 and 0.35 for the next two best performing algorithms. pGUESS is also much more computationally scalable compared to existing algorithms.

CONCLUSION

pGUESS algorithm can substantially reduce the burden of chart review and holds potential in improving the efficiency and accuracy of human annotation.

Multiview Incomplete Knowledge Graph Integration with application to cross-institutional EHR data harmonization

OBJECTIVE

The growing availability of electronic health records (EHR) data opens opportunities for integrative analysis of multi-institutional EHR to produce generalizable knowledge. A key barrier to such integrative analyses is the lack of semantic interoperability across different institutions due to coding differences. We propose a Multiview Incomplete Knowledge Graph Integration (MIKGI) algorithm to integrate information from multiple sources with partially overlapping EHR concept codes to enable translations between healthcare systems.

METHODS

The MIKGI algorithm combines knowledge graph information from (i) embeddings trained from the co-occurrence patterns of medical codes within each EHR system and (ii) semantic embeddings of the textual strings of all medical codes obtained from the Self-Aligning Pretrained BERT (SAPBERT) algorithm. Due to the heterogeneity in the coding across healthcare systems, each EHR source provides partial coverage of the available codes. MIKGI synthesizes the incomplete knowledge graphs derived from these multi-source embeddings by minimizing a spherical loss function that combines the pairwise directional similarities of embeddings computed from all available sources. MIKGI outputs harmonized semantic embedding vectors for all EHR codes, which improves the quality of the embeddings and enables direct assessment of both similarity and relatedness between any pair of codes from multiple healthcare systems.

RESULTS

With EHR co-occurrence data from Veteran Affairs (VA) healthcare and Mass General Brigham (MGB), MIKGI algorithm produces high quality embeddings for a variety of downstream tasks including detecting known similar or related entity pairs and mapping VA local codes to the relevant EHR codes used at MGB. Based on the cosine similarity of the MIKGI trained embeddings, the AUC was 0.918 for detecting similar entity pairs and 0.809 for detecting related pairs. For cross-institutional medical code mapping, the top 1 and top 5 accuracy were 91.0% and 97.5% when mapping medication codes at VA to RxNorm medication codes at MGB; 59.1% and 75.8% when mapping VA local laboratory codes to LOINC hierarchy. When trained with 500 labels, the lab code mapping attained top 1 and 5 accuracy at 77.7% and 87.9%. MIKGI also attained best performance in selecting VA local lab codes for desired laboratory tests and COVID-19 related features for COVID EHR studies. Compared to existing methods, MIKGI attained the most robust performance with accuracy the highest or near the highest across all tasks.

CONCLUSIONS

The proposed MIKGI algorithm can effectively integrate incomplete summary data from biomedical text and EHR data to generate harmonized embeddings for EHR codes for knowledge graph modeling and cross-institutional translation of EHR codes.

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.

Changes in laboratory value improvement and mortality rates over the course of the pandemic: an international retrospective cohort study of hospitalised patients infected with SARS-CoV-2

OBJECTIVE

To assess changes in international mortality rates and laboratory recovery rates during hospitalisation for patients hospitalised with SARS-CoV-2 between the first wave (1 March to 30 June 2020) and the second wave (1 July 2020 to 31 January 2021) of the COVID-19 pandemic.

DESIGN, SETTING AND PARTICIPANTS

This is a retrospective cohort study of 83 178 hospitalised patients admitted between 7 days before or 14 days after PCR-confirmed SARS-CoV-2 infection within the Consortium for Clinical Characterization of COVID-19 by Electronic Health Record, an international multihealthcare system collaborative of 288 hospitals in the USA and Europe. The laboratory recovery rates and mortality rates over time were compared between the two waves of the pandemic.

PRIMARY AND SECONDARY OUTCOME MEASURES

The primary outcome was all-cause mortality rate within 28 days after hospitalisation stratified by predicted low, medium and high mortality risk at baseline. The secondary outcome was the average rate of change in laboratory values during the first week of hospitalisation.

RESULTS

Baseline Charlson Comorbidity Index and laboratory values at admission were not significantly different between the first and second waves. The improvement in laboratory values over time was faster in the second wave compared with the first. The average C reactive protein rate of change was -4.72 mg/dL vs -4.14 mg/dL per day (p=0.05). The mortality rates within each risk category significantly decreased over time, with the most substantial decrease in the high-risk group (42.3% in March-April 2020 vs 30.8% in November 2020 to January 2021, p<0.001) and a moderate decrease in the intermediate-risk group (21.5% in March-April 2020 vs 14.3% in November 2020 to January 2021, p<0.001).

CONCLUSIONS

Admission profiles of patients hospitalised with SARS-CoV-2 infection did not differ greatly between the first and second waves of the pandemic, but there were notable differences in laboratory improvement rates during hospitalisation. Mortality risks among patients with similar risk profiles decreased over the course of the pandemic. The improvement in laboratory values and mortality risk was consistent across multiple countries.

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.

AB0932 Patient and learner experience in a new set up of a rheum-derm combined care model for psoriatic arthritis

Background

Psoriasis (PsO) and musculoskeletal manifestations are common among patients with psoriatic arthritis (PsA). A shared-care model between rheumatologists and dermatologists has been advocated to promote early diagnosis and improve management care. Data from Asia is scanty. Patients’ and learners’ experience of shared-care models are seldom explored.

Objectives

We described the set-up of a new shared-cared PsA-PsO clinic incorporating service, education and research between rheumatologist and dermatologist for PsA. We describe the patients’ and learners’ experience of this shared-care model.

Methods

A combined care clinic was newly set up in 2019. Referrals were internal through either specialty. Each patient was first seen by a trainee, followed by both a dermatologist and rheumatologist simultaneously in the same consultation room. We collected patients’ and learners’ experience through self-administered survey.

Results

From May 2019 to January 2020, data from 44 visits (55% new referrals, 45% follow-up) from 28 patients were captured in the PsA-PsO clinic. 50% of cases were referred from either specialty. 34% were referred for diagnostic doubts, 66% were for therapeutic issues. 61% of patients continued follow-up in the PsA-PsO clinic, and 39% discharged back to respective care. From patients’ experience rated on scale from 0-10, median (interquartile range, IQR) rating of the care was 8 (7, 8). 69.2% and 96% of patients would recommend the care to others. Free text comments included enhanced convenience, time saving, and having both specialties input on management. From 20 learners (3 medial students, 12 residents, 4 senior residents and one scientist), 95% reported extremely or very beneficial to training, 77.8% reported improved confidence in care for PsA and/or PsO patients. The PsA-PsO clinic was temporally suspended during the Covid-19 viral pandemic since February 2020 due to lack of manpower and not fulfilling the spacing out requirement for infectious control. The service was resumed gradually from May 2021.

Conclusion

Despite challenges, we report the setup of a new care model between dermatologists and rheumatologists for care of patients with psoriatic disease. The care model was well received by patients. Learners from various levels reported benefit from the learning experience.

Disclosure of Interests

Cassandra Hong: None declared, Liwen Fang: None declared, Yi-Wei Yeo: None declared, Haur Yueh Lee: None declared, Andrea Low: None declared, Ying Ying Leung Speakers bureau: Received honorarium from Abbvie, DKSH, Janssen, Novartis and Pfizer.

AB1328 A FEASIBILITY STUDY ON A NOVEL COMBINED THERMAL IMAGING AND CLINICAL JOINT ASSESSMENT APPROACH USING ULTRASOUND DETECTED JOINT INFLAMMATION OUTCOMES IN RHEUMATOID ARTHRITIS

Background

Thermal imaging (TI) is a portable, low cost imaging tool with high feasibility for use. Clinical joint assessment.

Is routinely performed in rheumatoid arthritis (RA) patient care.

Objectives

To assess a combined TI and clinical joint assessment (CTCA) approach in comparison with TI alone using ultrasound (US) detected joint inflammation outcomes as a gold standard.

Methods

Bilateral (BL) hand and wrist (22 joint sites) were assessed in this cross-sectional study. For TI (performed in a draft free room with a controlled temperature of around 22°C), the adjusted maximum (Tmax), minimum (Tmin) and average (Tavg) temperatures were derived by subtracting a control temperature (lowest Tmin at the joints per subject) from the Tmax, Tmin and Tavg per joint. US power Doppler (PD) and greyscale (GS) joint inflammation were graded semi-quantitatively (0-3) using validated scoring methods. Joint swelling and tenderness were graded as yes = 1 or no = 0. To increase the relative weightage of CTCA-MAX, CTCA-MIN and CTCA-AVG on the CTCA scores, if the joint was swollen and/or tender, the adjusted Tmax, Tmin and Tavg at each joint were multiplied by a factor of 2; otherwise, they remained unchanged. Receiver operating characteristic (ROC) analysis assessed the performance of TI and CTCA in identifying joints with US PD score > 1 and GS score > 1. A parameter was selected as a univariate predictor if statistically significant (P < 0.05) with area under the ROC curve (AUC) ≥ 0.70.

Results

This study included 814 joints from 37 RA patients (mean disease duration, 30.9 months; mean DAS28, 4.43). For both TI and CTCA, out of the 22 joints sites, 3 joint sites were evaluated for PD score > 1 and 14 joint sites for GS score > 1; the remaining joint sites had AUC results unavailable due to small number of outcomes. For TI (Table 1), 3 joint sites had ≥ 1 predictive parameter for either PD score > 1 and/or GS score > 1 as follows: left (L) wrist and right (R) MCPJ 1, AUCs (0.813 to 0.897) for PD score > 1; L wrist and R MCPJs 1 and 3, AUCs (0.808 to 0.947) for GS score > 1. For CTCA (Table 1), 6 joint sites had ≥ 1 predictive parameter for either PD score > 1 and/or GS score > 1 as follows: BL wrists, AUCs (0.726 to 0.899) for PD score > 1; BL wrists, MCPJs 2 and 3, AUCs (0.739 to 0.931) for GS score > 1.

Table 1.

Identifying joints with ultrasound PD score >1 & GS score >1

Thermal Imaging aloneCTCAJointUScriterionParameter (AUC ≥ 0.7& P <0.05)AUC(95% CI)Cut-offJointUScriterionParameter (AUC ≥ 0.7& P <0.05)AUC (95% CI)Cut-offLRLRLPD score >1Adjusted Tmax**0.841 (0.691, 0.992)4.7L & RPD score >1CTCA-MAX**0.899 (0.797, 1)**0.776 (0.578, .973)9.47.3WristAdjusted Tmin**0.813 (0.669, 0.958)2.85WristCTCA-MIN**0.861 (0.735, 0.987)*0.7265.74.45(0.526, 0.926)Adjusted Tavg**0.849 (0.714, 0.985)3.9CTCA-AVG**0.889 (0.781, 0.997)*0.7617.35.95(0.563, 0.959)GS score >1Adjusted Tmax**0.827 (0.687, 0.966)4.7GS score >1CTCA-MAX**0.918 (0.833, 1)**0.81387.3(0.632, 0.994)Adjusted Tmin**0.808 (0.67, 0.947)2.85CTCA-MIN**0.873 (0.761, 0.986)**0.7664.44.45(0.581, 0.951)Adjusted Tavg**0.837 (0.707, 0.967)3.9CTCA-AVG**0.913**0.8025.55.95(0.824, 1)(0.62, 0.985)RPD score >1Adjusted Tmax*0.897 (0.726, 1)5.7L & RGS score >1CTCA-MAX-*0.758-9.8(0.494, 1)MCPJ 1MCPJ 2GS score >1Adjusted Tmax*0.936 (0.813, 1)7.2CTCA-MIN*0.902*0.7392.753.9(0.775, 1)(0.443, 1)Adjusted Tmin*0.932 (0.793, 1)3.95CTCA-AVG*0.931**0.7634.75.5(0.835, 1)(0.474, 1)Adjusted Tavg*0.947 (0.868, 1)4.9L & RGS score >1CTCA-MAX*0.914*0.8736.3512.2(0.735, 1)(0.617, 1)RGS score >1Adjusted Tmax*0.922 (0.76, 1)4.6MCPJ 3CTCA-MIN-*0.902-3.15(0.75, 1)MCPJ 3CTCA-AVG-*0.902-4.1(0.728, 1)

Corresponding P-value: statistically significance at *P <0.05, **P<0.01.

Conclusion

A novel CTCA approach helps discriminate the severity of US detected joint inflammation in RA at more joint sites when compared to TI alone; this includes the commonly affected BL wrists, MCPJs 2 and 3. Further validation work in a larger RA cohort will be required.

Disclosure of Interests

None declared

[Impact of nonsteroidal anti-inflammatory drugs on efficacy of anti-PD-1 therapy for primary liver cancer]

OBJECTIVE

To assess the impact of nonsteroidal anti-inflammatory drugs (NSAIDs) on clinical outcomes of patients receiving anti-PD-1 immunotherapy for hepatocellular carcinoma.

METHODS

We conducted a retrospective study among 215 patients with primary liver cancer receiving immunotherapy between June, 2018 and October, 2020. The patients with balanced baseline characteristics were selected based on propensity matching scores, and among them 33 patients who used NSAIDs were matched at the ratio of 1∶3 with 78 patients who did not use NSAIDs. We compared the overall survival (OS), progression-free survival (PFS), and disease control rate (DCR) between the two groups.

RESULTS

There was no significant difference in OS between the patients using NSAIDs (29.7%) and those who did not use NSAIDs (70.2%). Univariate and multivariate analyses did not show an a correlation of NSAIDs use with DCR (univariate analysis: OR=0.602, 95% CI: 0.299-1.213, P=0.156; multivariate analysis: OR=0.693, 95% CI: 0.330-1.458, P=0.334), PFS (univariate analysis: HR=1.230, 95% CI: 0.789-1.916, P=0.361; multivariate analysis: HR=1.151, 95% CI: 0.732-1.810, P=9.544), or OS (univariate analysis: HR=0.552, 95% CI: 0.208-1.463, P=0.232; multivariate analysis: HR=1.085, 95% CI: 0.685-1.717, P=0.729).

CONCLUSION

Our results show no favorable effect of NSAIDs on the efficacy of immunotherapy in patients with advanced primary liver cancer, but this finding still needs to be verified by future prospective studies of large cohorts.

Binary acronym disambiguation in clinical notes from electronic health records with an application in computational phenotyping

OBJECTIVE

The use of electronic health records (EHR) systems has grown over the past decade, and with it, the need to extract information from unstructured clinical narratives. Clinical notes, however, frequently contain acronyms with several potential senses (meanings) and traditional natural language processing (NLP) techniques cannot differentiate between these senses. In this study we introduce a semi-supervised method for binary acronym disambiguation, the task of classifying a target sense for acronyms in the clinical EHR notes.

METHODS

We developed a semi-supervised ensemble machine learning (CASEml) algorithm to automatically identify when an acronym means a target sense by leveraging semantic embeddings, visit-level text and billing information. The algorithm was validated using note data from the Veterans Affairs hospital system to classify the meaning of three acronyms: RA, MS, and MI. We compared the performance of CASEml against another standard semi-supervised method and a baseline metric selecting the most frequent acronym sense. Along with evaluating the performance of these methods for specific instances of acronyms, we evaluated the impact of acronym disambiguation on NLP-driven phenotyping of rheumatoid arthritis.

RESULTS

CASEml achieved accuracies of 0.947, 0.911, and 0.706 for RA, MS, and MI, respectively, higher than a standard baseline metric and (on average) higher than a state-of-the-art semi-supervised method. As well, we demonstrated that applying CASEml to medical notes improves the AUC of a phenotype algorithm for rheumatoid arthritis.

CONCLUSION

CASEml is a novel method that accurately disambiguates acronyms in clinical notes and has advantages over commonly used supervised and semi-supervised machine learning approaches. In addition, CASEml improves the performance of NLP tasks that rely on ambiguous acronyms, such as phenotyping.