Dataset Information

Universal artificial intelligence platform for collaborative management of cataracts.

ABSTRACT: PURPOSE:To establish and validate a universal artificial intelligence (AI) platform for collaborative management of cataracts involving multilevel clinical scenarios and explored an AI-based medical referral pattern to improve collaborative efficiency and resource coverage. METHODS:The training and validation datasets were derived from the Chinese Medical Alliance for Artificial Intelligence, covering multilevel healthcare facilities and capture modes. The datasets were labelled using a three-step strategy: (1) capture mode recognition; (2) cataract diagnosis as a normal lens, cataract or a postoperative eye and (3) detection of referable cataracts with respect to aetiology and severity. Moreover, we integrated the cataract AI agent with a real-world multilevel referral pattern involving self-monitoring at home, primary healthcare and specialised hospital services. RESULTS:The universal AI platform and multilevel collaborative pattern showed robust diagnostic performance in three-step tasks: (1) capture mode recognition (area under the curve (AUC) 99.28%-99.71%), (2) cataract diagnosis (normal lens, cataract or postoperative eye with AUCs of 99.82%, 99.96% and 99.93% for mydriatic-slit lamp mode and AUCs >99% for other capture modes) and (3) detection of referable cataracts (AUCs >91% in all tests). In the real-world tertiary referral pattern, the agent suggested 30.3% of people be 'referred', substantially increasing the ophthalmologist-to-population service ratio by 10.2-fold compared with the traditional pattern. CONCLUSIONS:The universal AI platform and multilevel collaborative pattern showed robust diagnostic performance and effective service for cataracts. The context of our AI-based medical referral pattern will be extended to other common disease conditions and resource-intensive situations.

SUBMITTER: Wu X

PROVIDER: S-EPMC6855787 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundShorter, more effective treatments for tuberculosis (TB) are urgently needed. While many TB drugs are available, identification of the best regimens is challenging because of the large number of possible drug-dose combinations. We have found consistently that responses of cells or whole animals to drug-dose stimulations fit a parabolic response surface (PRS), allowing us to identify and optimize the best drug combinations by testing only a small fraction of the total search space. Previously, we used PRS methodology to identify three regimens (PRS Regimens I-III) that in murine models are much more effective than the standard regimen used to treat TB. However, PRS Regimens I and II are unsuitable for treating drug-resistant TB and PRS Regimen III includes an experimental drug. Here, we use PRS methodology to identify from an expanded pool of drugs new highly effective near-universal drug regimens comprising only approved drugs.Methods and findingsWe evaluated combinations of 15 different drugs in a human macrophage TB model and identified the most promising 4-drug combinations. We then tested 14 of these combinations in Mycobacterium tuberculosis-infected BALB/c mice and chose for PRS dose optimization and further study the two most potent regimens, designated PRS Regimens IV and V, consisting of clofazimine (CFZ), bedaquiline (BDQ), pyrazinamide (PZA), and either amoxicillin/clavulanate (AC) or delamanid (DLM), respectively. We then evaluated the efficacy in mice of optimized PRS Regimens IV and V, as well as a 3-drug regimen, PRS Regimen VI (CFZ, BDQ, and PZA), and compared their efficacy to PRS Regimen III (CFZ, BDQ, PZA, and SQ109), previously shown to reduce the time to achieve relapse-free cure in mice by 80% compared with the Standard Regimen (isoniazid, rifampicin, PZA, and ethambutol). Efficacy measurements included early bactericidal activity, time to lung sterilization, and time to relapse-free cure. PRS Regimens III-VI all rapidly sterilized the lungs and achieved relapse-free cure in 3 weeks (PRS Regimens III, V, and VI) or 5 weeks (PRS Regimen IV). In contrast, mice treated with the Standard Regimen still had high numbers of bacteria in their lungs after 6-weeks treatment and none achieved relapse-free cure in this time-period.ConclusionsWe have identified three new regimens that rapidly sterilize the lungs of mice and dramatically shorten the time required to achieve relapse-free cure. All mouse drug doses in these regimens extrapolate to doses that are readily achievable in humans. Because PRS Regimens IV and V contain only one first line drug (PZA) and exclude fluoroquinolones and aminoglycosides, they should be effective against most TB cases that are multidrug resistant (MDR-TB) and many that are extensively drug-resistant (XDR-TB). Hence, these regimens have potential to shorten dramatically the time required for treatment of both drug-sensitive and drug-resistant TB. If clinical trials confirm that these regimens dramatically shorten the time required to achieve relapse-free cure in humans, then this radically shortened treatment has the potential to improve treatment compliance, decrease the emergence of drug resistance, and decrease the healthcare burden of treating both drug-sensitive and drug-resistant TB.

Project description:BackgroundCC-Cruiser is an artificial intelligence (AI) platform developed for diagnosing childhood cataracts and providing risk stratification and treatment recommendations. The high accuracy of CC-Cruiser was previously validated using specific datasets. The objective of this study was to compare the diagnostic efficacy and treatment decision-making capacity between CC-Cruiser and ophthalmologists in real-world clinical settings.MethodsThis multicentre randomized controlled trial was performed in five ophthalmic clinics in different areas across China. Pediatric patients (aged ≤ 14 years) without a definitive diagnosis of cataracts or history of previous eye surgery were randomized (1:1) to receive a diagnosis and treatment recommendation from either CC-Cruiser or senior consultants (with over 5 years of clinical experience in pediatric ophthalmology). The experts who provided a gold standard diagnosis, and the investigators who performed slit-lamp photography and data analysis were blinded to the group assignments. The primary outcome was the diagnostic performance for childhood cataracts with reference to cataract experts' standards. The secondary outcomes included the evaluation of disease severity and treatment determination, the time required for the diagnosis, and patient satisfaction, which was determined by the mean rating. This trial is registered with ClinicalTrials.gov (NCT03240848).FindingsBetween August 9, 2017 and May 25, 2018, 350 participants (700 eyes) were randomly assigned for diagnosis by CC-Cruiser (350 eyes) or senior consultants (350 eyes). The accuracies of cataract diagnosis and treatment determination were 87.4% and 70.8%, respectively, for CC-Cruiser, which were significantly lower than 99.1% and 96.7%, respectively, for senior consultants (p < 0.001, OR = 0.06 [95% CI 0.02 to 0.19]; and p < 0.001, OR = 0.08 [95% CI 0.03 to 0.25], respectively). The mean time for receiving a diagnosis from CC-Cruiser was 2.79 min, which was significantly less than 8.53 min for senior consultants (p < 0.001, mean difference 5.74 [95% CI 5.43 to 6.05]). The patients were satisfied with the overall medical service quality provided by CC-Cruiser, typically with its time-saving feature in cataract diagnosis.InterpretationCC-Cruiser exhibited less accurate performance comparing to senior consultants in diagnosing childhood cataracts and making treatment decisions. However, the medical service provided by CC-Cruiser was less time-consuming and achieved a high level of patient satisfaction. CC-Cruiser has the capacity to assist human doctors in clinical practice in its current state.FundingNational Key R&D Program of China (2018YFC0116500) and the Key Research Plan for the National Natural Science Foundation of China in Cultivation Project (91846109).

Project description:PurposeTo assess the accuracy of e-Paarvai, an artificial intelligence-based smartphone application (app) that detects and grades cataracts using images taken with a smartphone by comparing with slit lamp-based diagnoses by trained ophthalmologists.MethodsIn this prospective diagnostic study conducted between January and April 2022 at a large tertiary-care eye hospital in South India, two screeners were trained to use the app. Patients aged >40 years and with a best-corrected visual acuity <20/40 were recruited for the study. The app is intended to determine whether the eye has immature cataract, mature cataract, posterior chamber intra-ocular lens, or no cataract. The diagnosis of the app was compared with that of trained ophthalmologists based on slit-lamp examinations, the gold standard, and a receiver operating characteristic (ROC) curve was estimated. The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were computed.ResultsThe two screeners used the app to screen 2,619 eyes of 1,407 patients. In detecting cataracts, the app showed high sensitivity (96%) but low specificity (25%), an overall accuracy of 88%, a PPV of 92.3%, and an NPV of 57.8%. In terms of cataract grading, the accuracy of the app was high in detecting immature cataracts (1,875 eyes, 94.2%), but its accuracy was poor in detecting mature cataracts (73 eyes, 22%), posterior chamber intra-ocular lenses (55 eyes, 29.3%), and clear lenses (2 eyes, 2%). We found that the area under the curve in predicting ophthalmologists' cataract diagnosis could potentially be improved beyond the app's diagnosis based on using images only by incorporating information about patient sex and age (P < 0.0001) and best-corrected visual acuity (P < 0.0001).ConclusionsAlthough there is room for improvement, e-Paarvai app is a promising approach for diagnosing cataracts in difficult-to-reach populations. Integrating this with existing outreach programs can enhance the case detection rate.

Project description:ImportanceThe transformative potential of artificial intelligence (AI), particularly via large language models, is increasingly being manifested in healthcare. Dietary interventions are foundational to weight management efforts, but whether AI techniques are presently capable of generating clinically applicable diet plans has not been evaluated.ObjectiveOur study sought to evaluate the potential of personalized AI-generated weight-loss diet plans for clinical applications by employing a survey-based assessment conducted by experts in the fields of obesity medicine and clinical nutrition.Design setting and participantsWe utilized ChatGPT (4.0) to create weight-loss diet plans and selected two control diet plans from tertiary medical centers for comparison. Dietitians, physicians, and nurse practitioners specializing in obesity medicine or nutrition were invited to provide feedback on the AI-generated plans. Each plan was assessed blindly based on its effectiveness, balanced-ness, comprehensiveness, flexibility, and applicability. Personalized plans for hypothetical patients with specific health conditions were also evaluated.Main outcomes and measuresThe primary outcomes measured included the indistinguishability of the AI diet plan from human-created plans, and the potential of personalized AI-generated diet plans for real-world clinical applications.ResultsOf 95 participants, 67 completed the survey and were included in the final analysis. No significant differences were found among the three weight-loss diet plans in any evaluation category. Among the 14 experts who believed that they could identify the AI plan, only five did so correctly. In an evaluation involving 57 experts, the AI-generated personalized weight-loss diet plan was assessed, with scores above neutral for all evaluation variables. Several limitations, of the AI-generated plans were highlighted, including conflicting dietary considerations, lack of affordability, and insufficient specificity in recommendations, such as exact portion sizes. These limitations suggest that refining inputs could enhance the quality and applicability of AI-generated diet plans.ConclusionDespite certain limitations, our study highlights the potential of AI-generated diet plans for clinical applications. AI-generated dietary plans were frequently indistinguishable from diet plans widely used at major tertiary medical centers. Although further refinement and prospective studies are needed, these findings illustrate the potential of AI in advancing personalized weight-centric care.

Dataset Information

Universal artificial intelligence platform for collaborative management of cataracts.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets