AI Article Synopsis

  • The study explores an AI-based system for autonomously following up with patients suffering from neovascular age-related macular degeneration (AMD).
  • The research involved training a temporal deep learning model on a large dataset of scans to better detect disease activity, outperforming a previous non-temporal model.
  • Results indicated that the AI system made autonomous decisions in 73% of the cases, aligning closely with expert opinions and suggesting it could help relieve pressure on ophthalmology services dealing with more AMD patients in the future.

Article Abstract

Purpose: In this study, we investigate the potential of a novel artificial intelligence-based system for autonomous follow-up of patients treated for neovascular age-related macular degeneration (AMD).

Methods: A temporal deep learning model was trained on a data set of 84 489 optical coherence tomography scans from AMD patients to recognize disease activity, and its performance was compared with a published non-temporal model trained on the same data (Acta Ophthalmol, 2021). An autonomous follow-up system was created by augmenting the AI model with deterministic logic to suggest treatment according to the observe-and-plan regimen. To validate the AI-based system, a data set comprising clinical decisions and imaging data from 200 follow-up consultations was collected prospectively. In each case, both the autonomous AI decision and original clinical decision were compared with an expert panel consensus.

Results: The temporal AI model proved superior at detecting disease activity compared with the model without temporal input (area under the curve 0.900 (95% CI 0.894-0.906) and 0.857 (95% CI 0.846-0.867) respectively). The AI-based follow-up system could make an autonomous decision in 73% of the cases, 91.8% of which were in agreement with expert consensus. This was on par with the 87.7% agreement rate between decisions made in the clinic and expert consensus (p = 0.33).

Conclusions: The proposed autonomous follow-up system was shown to be safe and compliant with expert consensus on par with clinical practice. The system could in the future ease the pressure on public ophthalmology services from an increasing number of AMD patients.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9790353PMC
http://dx.doi.org/10.1111/aos.15133DOI Listing

Publication Analysis

Top Keywords

autonomous follow-up
12
follow-up system
12
expert consensus
12
artificial intelligence-based
8
intelligence-based system
8
follow-up patients
8
age-related macular
8
macular degeneration
8
system autonomous
8
model trained
8

Similar Publications

Risk prediction of new-onset thrombocytopenia in patients with systemic lupus erythematosus: a multicenter prospective cohort study based on Chinese SLE treatment and research group (CSTAR) registry.

Arthritis Res Ther

December 2024

Department of Rheumatology and Clinical Immunology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences, Peking Union Medical College, National Clinical Research Center for Dermatologic and Immunologic Diseases (NCRC-DID), Ministry of Science & Technology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Key Laboratory of Rheumatology and Clinical Immunology, Ministry of Education, Beijing, China.

Background: Thrombocytopenia (TP) is a hematological manifestation of systemic lupus erythematosus (SLE) and is associated with unfavorable prognostic outcomes. This study aimed to develop a risk prediction model for new-onset TP in SLE patients.

Methods: Based on the multicenter prospective Chinese SLE Treatment and Research Group (CSTAR) registry, newly diagnosed SLE patients without TP at registration were enrolled.

View Article and Find Full Text PDF

Value of ultrasound-assessed dactylitis in the early diagnosis of psoriatic arthritis.

Semin Arthritis Rheum

December 2024

Department of Rheumatology and Joint and Bone Research Unit. Fundación Jiménez Díaz University Hospital and Health Research Institute Fundación Jiménez Díaz (IIS-FJD, UAM), Autonomous University of Madrid, Madrid, Spain. Electronic address:

Purpose: The primary objective of this prospective, longitudinal, observational, single-centre study was to evaluate the association between ultrasound-assessed lesions of dactylitis and the diagnosis of psoriatic arthritis (PsA) in patients with psoriasis (PsO) and hand arthralgia.

Methods: We included adult patients diagnosed with PsO with hand arthralgia, with or without other musculoskeletal complaints. They were clinically assessed at baseline, 6 and 12 months by a rheumatologist blinded to the ultrasound findings.

View Article and Find Full Text PDF

Objective: To investigate the prevalence and incidence of dementia in patients with non-overtly functional adrenal tumours (NOFATs).

Design: A national retrospective register-based study was conducted on patients diagnosed with NOFAT and controls diagnosed between 2005 and 2019, in Sweden. Individuals diagnosed with overt adrenal hormone excess or previous malignancies were excluded.

View Article and Find Full Text PDF

Objective: To describe the prevalence and epidemic trends of several chronic multimorbidy among adult residents in 10 provinces(autonomous regions)of China over the past 14 years, and to analyze their multimorbidity patterns.

Methods: According to the fasting blood physiological and biochemical tests, physical measurements and questionnaires of 17 000 adult residents aged 18 years and above who were surveyed in 4 rounds of follow-up surveys in 2009, 2015, 2018 and 2023, the relevant indicators and disease history information of obesity, hypertension, diabetes mellitus, dyslipidemia, hyperuricemia, and various chronic diseases were obtained. Descriptive analysis was carried out to identify and compare several common combinations of multimorbidity in the population with 2 or more chronic disease conditions and the changing trends of 4 rounds of surveys.

View Article and Find Full Text PDF

Association of constipation with all-cause mortality among individuals with type 2 diabetes: A retrospective cohort study.

J Diabetes Investig

December 2024

Center for Endocrine Metabolism and Immune Diseases, Beijing Lu He Hospital, Capital Medical University, Beijing, China.

Background: Constipation is a common complication in type 2 diabetes mellitus (T2DM), yet its impact on mortality remains unclear. This study aimed to investigate the association between constipation and all-cause mortality in patients with T2DM.

Methods: We conducted a retrospective cohort study using data from the National Health and Nutrition Examination Survey (NHANES) 2005-2010.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!