Pierre Elias

Pierre Elias

Auto-generated profile, based on publicly available information

Pierre Elias

Seymour, Paul, and Gloria Milstein Division of Cardiology, Department of Medicine, Columbia University Irving Medical Center, New York, USA

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 August 2023 in npj Digital Medicine
Verified
Journal Article
Open access
PDF file
LTLiyan Tang
Liyan Tang
ZSZhaoyi Sun
Zhaoyi Sun
BIBetina Idnay
Betina Idnay
JNJordan G. Nestor
Jordan G. Nestor
ASAli Soroush
Ali Soroush
YPYifan Peng
Yifan Peng
Recent advances in large language models (LLMs) have demonstrated remarkable successes in zero- and few-shot performance on various downstream tasks, paving the way for applications in high-stakes domains. In this study, we systematically examine the capabilities and limitations of LLMs, specifically GPT-3.5 and ChatGPT, in performing zero-shot medical evidence summarization across six clinical domains. We conduct both automatic and human evaluations, covering several dimensions of summary quality. Our study demonstrates that automatic metrics often do not strongly correlate with the quality of summaries. Furthermore, informed by our human evaluations, we define a terminology of error types for medical evidence summarization. Our findings reveal that LLMs could be susceptible to generating factually inconsistent summaries and making overly convincing or uncertain statements, leading to potential harm due to misinformation. Moreover, we find that models struggle to identify the salient information and are more error-prone when summarizing over longer textual contexts.

26 February 2021 in Nature Communications
Verified
Journal Article
Open access
PDF file
AGAakriti Gupta
Aakriti Gupta
MMMahesh V. Madhavan
Mahesh V. Madhavan
TPTimothy J. Poterucha
Timothy J. Poterucha
EDErsilia M. DeFilippis
Ersilia M. DeFilippis
JHJessica A. Hennessey
Jessica A. Hennessey
SPSahil A. Parikh
Sahil A. Parikh
The coronavirus disease 2019 (COVID-19) can result in a hyperinflammatory state, leading to acute respiratory distress syndrome (ARDS), myocardial injury, and thrombotic complications, among other sequelae. Statins, which are known to have anti-inflammatory and antithrombotic properties, have been studied in the setting of other viral infections, but their benefit has not been assessed in COVID-19. This is a retrospective analysis of patients admitted with COVID-19 from February 1st through May 12th, 2020 with study period ending on June 11th, 2020. Antecedent statin use was assessed using medication information available in the electronic medical record. We constructed a multivariable logistic regression model to predict the propensity of receiving statins, adjusting for baseline sociodemographic and clinical characteristics, and outpatient medications. The primary endpoint includes in-hospital mortality within 30 days. A total of 2626 patients were admitted during the study period, of whom 951 (36.2%) were antecedent statin users. Among 1296 patients (648 statin users, 648 non-statin users) identified with 1:1 propensity-score matching, statin use is significantly associated with lower odds of the primary endpoint in the propensity-matched cohort (OR 0.47, 95% CI 0.36–0.62, p < 0.001). We conclude that antecedent statin use in patients hospitalized with COVID-19 is associated with lower inpatient mortality.

16 July 2025 in Nature
Verified
Journal Article
Open access
PDF file
TPTimothy J. Poterucha
Timothy J. Poterucha
LJLinyuan Jing
Linyuan Jing
RRRamon Pimentel Ricart
Ramon Pimentel Ricart
MAMichael Adjei-Mosi
Michael Adjei-Mosi
JFJoshua Finer
Joshua Finer
PEPierre Elias
Pierre Elias
Early detection of structural heart disease is critical to improving outcomes, but widespread screening remains limited by the cost and accessibility of imaging tools such as echocardiography1,2. Recent advances in machine learning applied to heart rhythm recordings have shown promise in identifying disease3,4, although previous work has been limited by development in narrow populations or targeting only select heart conditions5. Here we introduce a deep learning model, EchoNext, trained on more than 1 million heart rhythm and imaging records across a large and diverse health system to detect many forms of structural heart disease. The model demonstrated high diagnostic accuracy in internal and external validation, outperforming cardiologists in a controlled evaluation and showing consistent performance across different care settings and racial and/or ethnic groups. The models were prospectively evaluated in a clinical trial of patients without previous cardiac imaging, successfully identifying previously undiagnosed heart disease. These findings support the potential of artificial intelligence to expand access to heart disease screening at scale. To enable further development and transparency, we have publicly released model weights and a large, annotated dataset linking heart rhythm data to imaging-based diagnoses.

12 September 2023 in npj Digital Medicine
Verified
Journal Article
Open access
PDF file
JHJ. Weston Hughes
J. Weston Hughes
JTJames Tooley
James Tooley
JSJessica Torres Soto
Jessica Torres Soto
AOAnna Ostropolets
Anna Ostropolets
TPTim Poterucha
Tim Poterucha
MPMarco V. Perez
Marco V. Perez
The electrocardiogram (ECG) is the most frequently performed cardiovascular diagnostic test, but it is unclear how much information resting ECGs contain about long term cardiovascular risk. Here we report that a deep convolutional neural network can accurately predict the long-term risk of cardiovascular mortality and disease based on a resting ECG alone. Using a large dataset of resting 12-lead ECGs collected at Stanford University Medical Center, we developed SEER, the Stanford Estimator of Electrocardiogram Risk. SEER predicts 5-year cardiovascular mortality with an area under the receiver operator characteristic curve (AUC) of 0.83 in a held-out test set at Stanford, and with AUCs of 0.78 and 0.83 respectively when independently evaluated at Cedars-Sinai Medical Center and Columbia University Irving Medical Center. SEER predicts 5-year atherosclerotic disease (ASCVD) with an AUC of 0.67, similar to the Pooled Cohort Equations for ASCVD Risk, while being only modestly correlated. When used in conjunction with the Pooled Cohort Equations, SEER accurately reclassified 16% of patients from low to moderate risk, uncovering a group with an actual average 9.9% 10-year ASCVD risk who would not have otherwise been indicated for statin therapy. SEER can also predict several other cardiovascular conditions such as heart failure and atrial fibrillation. Using only lead I of the ECG it predicts 5-year cardiovascular mortality with an AUC of 0.80. SEER, used alongside the Pooled Cohort Equations and other risk tools, can substantially improve cardiovascular risk stratification and aid in medical decision making.

17 September 2024 in Circulation
Verified
Journal Article
Open access
ALAaron Long
Aaron Long
CHChristopher M. Haggerty
Christopher M. Haggerty
JFJoshua Finer
Joshua Finer
DHDustin Hartzel
Dustin Hartzel
LJLinyuan Jing
Linyuan Jing
TPTimothy J. Poterucha
Timothy J. Poterucha
BACKGROUND: Artificial intelligence, particularly deep learning (DL), has immense potential to improve the interpretation of transthoracic echocardiography (TTE). Mitral regurgitation (MR) is the most common valvular heart disease and presents unique challenges for DL, including the integration of multiple video-level assessments into a final study-level classification. METHODS: A novel DL system was developed to intake complete TTEs, identify color MR Doppler videos, and determine MR severity on a 4-step ordinal scale (none/trace, mild, moderate, and severe) using the reading cardiologist as a reference standard. This DL system was tested in internal and external test sets with performance assessed by agreement with the reading cardiologist, weighted κ, and area under the receiver-operating characteristic curve for binary classification of both moderate or greater and severe MR. In addition to the primary 4-step model, a 6-step MR assessment model was studied with the addition of the intermediate MR classes of mild-moderate and moderate-severe with performance assessed by both exact agreement and ±1 step agreement with the clinical MR interpretation. RESULTS: A total of 61 689 TTEs were split into train (n=43 811), validation (n=8891), and internal test (n=8987) sets with an additional external test set of 8208 TTEs. The model had high performance in MR classification in internal (exact accuracy, 82%; κ=0.84; area under the receiver-operating characteristic curve, 0.98 for moderate or greater MR) and external test sets (exact accuracy, 79%; κ=0.80; area under the receiver-operating characteristic curve, 0.98 for moderate or greater MR). Most (63% internal and 66% external) misclassification disagreements were between none/trace and mild MR. MR classification accuracy was slightly higher using multiple TTE views (accuracy, 82%) than with only apical 4-chamber views (accuracy, 80%). In subset analyses, the model was accurate in the classification of both primary and secondary MR with slightly lower performance in cases of eccentric MR. In the analysis of the 6-step classification system, the exact accuracy was 80% and 76% with a ±1 step agreement of 99% and 98% in the internal and external test set, respectively. CONCLUSIONS: This end-to-end DL system can intake entire echocardiogram studies to accurately classify MR severity and may be useful in helping clinicians refine MR assessments.

7 February 2021 in Circulation: Arrhythmia and Electrophysiology
Verified
Journal Article
Closed access
PDF file
AOAnna Ostropolets
Anna Ostropolets
PEPierre A. Elias
Pierre A. Elias
MRMichael V. Reyes
Michael V. Reyes
EWElaine Y. Wan
Elaine Y. Wan
UPUtpal B. Pajvani
Utpal B. Pajvani
John MorrowJohn Morrow
John Morrow
Background - Type 2 diabetes (DM2) is one of the most common chronic disorders worldwide and is an important cause of cardiovascular disease. Studies investigating the risk of atrial and ventricular arrhythmias in diabetic patients taking different oral diabetes medications are sparse. Methods - We used IBM MarketScan® Medicare Supplemental Database to examine the risk of arrhythmias for patients on different oral diabetes medications by propensity score matching. Results - We found that patients on metformin monotherapy had significantly reduced risk of atrial arrhythmias, including atrial fibrillation, compared to monotherapy with DPP4 or TZD medications. Patients on metformin monotherapy had significantly reduced risk of atrial arrhythmias, ventricular arrhythmias, and bradycardia compared to monotherapy with sulfonylureas. Combination therapy with sulfonylureas and metformin had an increased risk of atrial arrhythmias compared to some other combinations. Conclusions - Different oral diabetes medications have significantly different long-term risk of arrhythmia. Specifically, metformin is associated with reduced risk of atrial fibrillation and ventricular arrhythmias compared to sulfonylureas.