What is the clinical evidence from this study?

Study design: Cross-Sectional. Population: Heart Failure (n=10100). Intervention: Artificial Intelligence (AI) algorithm for chest X-ray interpretation vs. Patients not flagged by AI (negative for increased CTR and pleural effusion). Primary outcome: Diagnosis of heart failure.

What does this research mean for the field?

AI interpretation of chest X-rays yields a 77% positive predictive value and 91% negative predictive value for diagnosing heart failure, with a majority of newly identified cases being heart failure with preserved ejection fraction (HFpEF). Novelty: ClaimNovelty.INCREMENTAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

August 31, 2023Open Access

The diagnostic value of chest X‐ray scanning by the help of Artificial Intelligence in Heart Failure (ART‐IN‐HF)

Key Result

AI interpretation of chest X-rays yielded a 77% positive predictive value and 91% negative predictive value for diagnosing heart failure, with 54.9% of new cases being HFpEF.

Study Design

Type

Cross-Sectional (n=10,100)

Structured PICO

Does Artificial Intelligence (AI) interpretation of chest X-rays improve the early diagnosis of heart failure in outpatients older than 45 years?

Population

10,100 outpatients older than 45 years undergoing chest X-rays

Intervention

Artificial Intelligence (AI) algorithm interpretation of chest X-rays to detect increased cardiothoracic ratio (CTR > 0.5) and pleural effusion

Comparator

Standard diagnostic investigations according to current guidelines

Outcome

Diagnosis of heart failure (Positive predictive value and negative predictive value of the AI algorithm)

AI-assisted interpretation of routine chest X-rays demonstrates high diagnostic accuracy for the early detection of heart failure, particularly HFpEF, in an outpatient setting.

Main Result

Absolute Event Rate: 77% vs 8%

Abstract

BACKGROUND: Typical signs of heart failure (HF), like increased cardiothoracic ratio (CTR) and pleural effusion, can be seen on X-ray. Artificial Intelligence (AI) can help in the early and quicker diagnosis of HF. OBJECTIVES: The study's goal was to demonstrate that the AI interpretation of chest X-rays can assist the clinician in diagnosing HF. METHODS: Patients older than 45 years were included in the study. The study analyzed 10 100 deidentified outpatient chest X-rays by AI algorithm. The AI-generated report was later verified by an independent radiologist. Patients with CTR > 0.5 and pleural effusion were marked as potential HF. Flagged patients underwent confirmatory tests, and those labeled as negative also underwent further investigations to rule out HF. RESULTS: Out of 10 100, the AI algorithm detected 183 (1.8%) patients with increased CTR and pleural effusion on chest X-rays. One hundred and six out of 183 underwent diagnostic tests. Eighty-two (77%) out of 106 were diagnosed with HF according to current guidelines. From the remaining 9917 patients, 106 patients were randomly selected. Nine (8%) out of them were diagnosed with HF. The positive predictive value of AI for diagnosing HF is 77%, and the negative predictive value is 91%. More than half (54.9%) of newly diagnosed patients had HF with preserved ejection fraction. CONCLUSION: HF is a risky condition with nonspecific symptoms that are difficult to diagnose, especially in the early stages. Using AI assistance for X-ray interpretation can be helpful for early diagnosis of HF especially HF with preserved ejection fraction.