RESUMEN
Primary diabetes care and diabetic retinopathy (DR) screening persist as major public health challenges due to a shortage of trained primary care physicians (PCPs), particularly in low-resource settings. Here, to bridge the gaps, we developed an integrated image-language system (DeepDR-LLM), combining a large language model (LLM module) and image-based deep learning (DeepDR-Transformer), to provide individualized diabetes management recommendations to PCPs. In a retrospective evaluation, the LLM module demonstrated comparable performance to PCPs and endocrinology residents when tested in English and outperformed PCPs and had comparable performance to endocrinology residents in Chinese. For identifying referable DR, the average PCP's accuracy was 81.0% unassisted and 92.3% assisted by DeepDR-Transformer. Furthermore, we performed a single-center real-world prospective study, deploying DeepDR-LLM. We compared diabetes management adherence of patients under the unassisted PCP arm (n = 397) with those under the PCP+DeepDR-LLM arm (n = 372). Patients with newly diagnosed diabetes in the PCP+DeepDR-LLM arm showed better self-management behaviors throughout follow-up (P < 0.05). For patients with referral DR, those in the PCP+DeepDR-LLM arm were more likely to adhere to DR referrals (P < 0.01). Additionally, DeepDR-LLM deployment improved the quality and empathy level of management recommendations. Given its multifaceted performance, DeepDR-LLM holds promise as a digital solution for enhancing primary diabetes care and DR screening.
RESUMEN
BACKGROUND: Diabetic macular edema (DME) is the leading cause of vision loss in people with diabetes. Application of artificial intelligence (AI) in interpreting fundus photography (FP) and optical coherence tomography (OCT) images allows prompt detection and intervention. PURPOSE: To evaluate the performance of AI in detecting DME from FP or OCT images and identify potential factors affecting model performances. DATA SOURCES: We searched seven electronic libraries up to 12 February 2023. STUDY SELECTION: We included studies using AI to detect DME from FP or OCT images. DATA EXTRACTION: We extracted study characteristics and performance parameters. DATA SYNTHESIS: Fifty-three studies were included in the meta-analysis. FP-based algorithms of 25 studies yielded pooled area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity of 0.964, 92.6%, and 91.1%, respectively. OCT-based algorithms of 28 studies yielded pooled AUROC, sensitivity, and specificity of 0.985, 95.9%, and 97.9%, respectively. Potential factors improving model performance included deep learning techniques, larger size, and more diversity in training data sets. Models demonstrated better performance when validated internally than externally, and those trained with multiple data sets showed better results upon external validation. LIMITATIONS: Analyses were limited by unstandardized algorithm outcomes and insufficient data in patient demographics, OCT volumetric scans, and external validation. CONCLUSIONS: This meta-analysis demonstrates satisfactory performance of AI in detecting DME from FP or OCT images. External validation is warranted for future studies to evaluate model generalizability. Further investigations may estimate optimal sample size, effect of class balance, patient demographics, and additional benefits of OCT volumetric scans.
Asunto(s)
Diabetes Mellitus , Retinopatía Diabética , Edema Macular , Humanos , Retinopatía Diabética/diagnóstico por imagen , Retinopatía Diabética/complicaciones , Edema Macular/diagnóstico por imagen , Edema Macular/etiología , Inteligencia Artificial , Tomografía de Coherencia Óptica/métodos , Fotograbar/métodosRESUMEN
INTRODUCTION: Generative pretrained transformer-4 (GPT-4) has gained widespread attention from society, and its potential has been extensively evaluated in many areas. However, investigation of GPT-4's use in medicine, especially in the ophthalmology field, is still limited. This study aims to evaluate GPT-4's capability to identify rare ophthalmic diseases in three simulated scenarios for different end-users, including patients, family physicians, and junior ophthalmologists. METHODS: We selected ten treatable rare ophthalmic disease cases from the publicly available EyeRounds service. We gradually increased the amount of information fed into GPT-4 to simulate the scenarios of patient, family physician, and junior ophthalmologist using GPT-4. GPT-4's responses were evaluated from two aspects: suitability (appropriate or inappropriate) and accuracy (right or wrong) by senior ophthalmologists (> 10 years' experiences). RESULTS: Among the 30 responses, 83.3% were considered "appropriate" by senior ophthalmologists. In the scenarios of simulated patient, family physician, and junior ophthalmologist, seven (70%), ten (100%), and eight (80%) responses were graded as "appropriate" by senior ophthalmologists. However, compared to the ground truth, GPT-4 could only output several possible diseases generally without "right" responses in the simulated patient scenarios. In contrast, in the simulated family physician scenario, 50% of GPT-4's responses were "right," and in the simulated junior ophthalmologist scenario, the model achieved a higher "right" rate of 90%. CONCLUSION: To our knowledge, this is the first proof-of-concept study that evaluates GPT-4's capacity to identify rare eye diseases in simulated scenarios involving patients, family physicians, and junior ophthalmologists. The results indicate that GPT-4 has the potential to serve as a consultation assisting tool for patients and family physicians to receive referral suggestions and an assisting tool for junior ophthalmologists to diagnose rare eye diseases. However, it is important to approach GPT-4 with caution and acknowledge the need for verification and careful referrals in clinical settings.
RESUMEN
Importance: The presence of diabetic macular ischemia (DMI) on optical coherence tomography angiography (OCTA) images predicts diabetic retinal disease progression and visual acuity (VA) deterioration, suggesting an OCTA-based DMI evaluation can further enhance diabetic retinopathy (DR) management. Objective: To investigate whether an automated binary DMI algorithm using OCTA images provides prognostic value on DR progression, diabetic macular edema (DME) development, and VA deterioration in a cohort of patients with diabetes. Design, Setting, and Participants: In this cohort study, DMI assessment of superficial capillary plexus and deep capillary plexus OCTA images was performed by a previously developed deep learning algorithm. The presence of DMI was defined as images exhibiting disruption of fovea avascular zone with or without additional areas of capillary loss, while absence of DMI was defined as images presented with intact fovea avascular zone outline and normal distribution of vasculature. Patients with diabetes were recruited starting in July 2015 and were followed up for at least 4 years. Cox proportional hazards models were used to evaluate the association of the presence of DMI with DR progression, DME development, and VA deterioration. Analysis took place between June and December 2022. Main Outcomes and Measures: DR progression, DME development, and VA deterioration. Results: A total of 321 eyes from 178 patients were included for analysis (85 [47.75%] female; mean [SD] age, 63.39 [11.04] years). Over a median (IQR) follow-up of 50.41 (48.16-56.48) months, 105 eyes (32.71%) had DR progression, 33 eyes (10.28%) developed DME, and 68 eyes (21.18%) had VA deterioration. Presence of superficial capillary plexus-DMI (hazard ratio [HR], 2.69; 95% CI, 1.64-4.43; P < .001) and deep capillary plexus-DMI (HR, 3.21; 95% CI, 1.94-5.30; P < .001) at baseline were significantly associated with DR progression, whereas presence of deep capillary plexus-DMI was also associated with DME development (HR, 4.60; 95% CI, 1.15-8.20; P = .003) and VA deterioration (HR, 2.12; 95% CI, 1.01-5.22; P = .04) after adjusting for age, duration of diabetes, fasting glucose, glycated hemoglobin, mean arterial blood pressure, DR severity, ganglion cell-inner plexiform layer thickness, axial length, and smoking at baseline. Conclusions and Relevance: In this study, the presence of DMI on OCTA images demonstrates prognostic value for DR progression, DME development, and VA deterioration.
Asunto(s)
Diabetes Mellitus , Retinopatía Diabética , Edema Macular , Humanos , Femenino , Persona de Mediana Edad , Masculino , Retinopatía Diabética/fisiopatología , Edema Macular/fisiopatología , Angiografía con Fluoresceína/métodos , Tomografía de Coherencia Óptica/métodos , Estudios de Cohortes , Inteligencia Artificial , Capilares/fisiopatología , Estudios Retrospectivos , Agudeza Visual , Progresión de la Enfermedad , Isquemia/diagnósticoRESUMEN
Optical coherence tomography angiography (OCT-A) provides depth-resolved visualization of the retinal microvasculature without intravenous dye injection. It facilitates investigations of various retinal vascular diseases and glaucoma by assessment of qualitative and quantitative microvascular changes in the different retinal layers and radial peripapillary layer non-invasively, individually, and efficiently. Deep learning (DL), a subset of artificial intelligence (AI) based on deep neural networks, has been applied in OCT-A image analysis in recent years and achieved good performance for different tasks, such as image quality control, segmentation, and classification. DL technologies have further facilitated the potential implementation of OCT-A in eye clinics in an automated and efficient manner and enhanced its clinical values for detecting and evaluating various vascular retinopathies. Nevertheless, the deployment of this combination in real-world clinics is still in the "proof-of-concept" stage due to several limitations, such as small training sample size, lack of standardized data preprocessing, insufficient testing in external datasets, and absence of standardized results interpretation. In this review, we introduce the existing applications of DL in OCT-A, summarize the potential challenges of the clinical deployment, and discuss future research directions.
RESUMEN
Advances in artificial intelligence deep learning (DL) have made tremendous impacts on the field of ocular imaging over the last few years. Specifically, DL has been utilised to detect and classify various ocular diseases on retinal photographs, optical coherence tomography (OCT) images, and OCT-angiography images. In order to achieve good robustness and generalisability of model performance, DL training strategies traditionally require extensive and diverse training datasets from various sites to be transferred and pooled into a "centralised location". However, such a data transferring process could raise practical concerns related to data security and patient privacy. Federated learning (FL) is a distributed collaborative learning paradigm which enables the coordination of multiple collaborators without the need for sharing confidential data. This distributed training approach has great potential to ensure data privacy among different institutions and reduce the potential risk of data leakage from data pooling or centralisation. This review article aims to introduce the concept of FL, provide current evidence of FL in ocular imaging, and discuss potential challenges as well as future applications.
RESUMEN
Photooxidation kinetics of phenol, 1-naphthol, 2-naphthol, tyrosine (TyrOH) and N-acetyl-tyrosine (AcTyrOH), tryptophan (TrpH) by ruthenium(II) polypyridyl complexes: [Ru(bpy)3]Cl2 (1), [Ru(phen)3]Cl2 (2), [Ru(bpy)(phen)(bpg)]Cl2 (3), and [Ru(dpq)2(bxbg)]Cl2 (4) where bpy is 2,2'-bipyridine, phen - 1,10-phenanthroline, bpg - bipyridine-glycoluril, dpq - dipyrido[3,2-d:2',3'-f]quinoxaline, and bxbg - bis(o-xylene)bipyridine-glycoluril are investigated. Rate constants have been measured by steady-state luminescence and phase-modulation fluorometry in aqueous solutions at different pH's. The rates for the oxidation of the phenols and phenolic aromatic amino acids spreads over a wide range from 4.2×106 to 6.8×109M-1s-1, depending on pH and the nature of solutes. At pH>pKa of the quenchers, the presence of reactive species (PhO-) in the alkaline solutions is accounted for the rapid ET rates. In the pH range between 4 and 10 (pHAsunto(s)
Fenoles/química
, Compuestos de Rutenio/química
, Espectrometría de Fluorescencia/métodos
, Triptófano/química
, Tirosina/análogos & derivados
, Tirosina/química
, Transporte de Electrón
, Cinética
, Soluciones
, Agua/química
RESUMEN
The photo-oxidation of the nucleobase, thymine (Thy), and nucleoside, thymidine (dThy), by dipyridyl (DP) has been investigated in aqueous solution using time-resolved laser flash photolysis. The pH dependence of the oxidation rate constants is measured within a large pH scale. As a consequence, the chemical reactivity of the reactants existing in solution at a certain range of pH is predicted. Bimolecular rate constants of the quenching reactions between triplet dipyridyl and thymine and thymidine are, respectively, kq = 2.4 × 10(7) M(-1) s(-1) (pH < 5.8) and kq = 1.0 × 10(7) M(-1) s(-1) (5.8 < pH < 9.8). Cyclic voltammetry was used to measure the potentials of thymine oxidation and dipyridyl reduction in water at pH < 7. Both results give hints for a proton coupled electron-transfer (PCET) reaction from thymine to triplet dipyridyl.
Asunto(s)
2,2'-Dipiridil/química , Timidina/química , Timina/química , Concentración de Iones de Hidrógeno , Cinética , Oxidación-Reducción , Soluciones , Agua/químicaRESUMEN
The kinetics of triplet state quenching of 3,3',4,4'-benzophenone tetracarboxylic acid (BPTC) by DNA bases adenine, adenosine, thymine, and thymidine has been investigated in aqueous solution using time-resolved laser flash photolysis. The observation of the BPTC ketyl radical anion at λ(max) = 630 nm indicates that one electron transfer is involved in the quenching reactions. The pH-dependence of the quenching rate constants is measured in detail. As a result, the chemical reactivity of the reactants is assigned. The bimolecular rate constants of the quenching reactions between triplet BPTC and adenine, adenosine, thymine, and thymidine are k(q) = 2.3 × 10(9) (4.7 < pH < 9.9), k(q) = 4.0 × 10(9) (3.5 < pH < 4.7), k(q) = 1.0 × 10(9) (4.7 < pH < 9.9), and k(q) = 4.0 × 10(8) M(-1) s(-1) (4.7 < pH < 9.8), respectively. Moreover, it reveals that in strong basic medium (pH = 12.0) a keto-enol tautomerism of thymine inhibits its reaction with triplet BPTC. Such a behavior is not possible for thymidine because of its deoxyribose group. In addition, the pH-dependence of the apparent electrochemical standard potential of thymine in aqueous solution was investigated by cyclic voltammetry. The ΔE/ΔpH ≈ -59 mV/pH result is characteristic of proton-coupled electron transfer. This behavior, together with the kinetic analysis, leads to the conclusion that the quenching reactions between triplet BPTC and thymine involve one proton-coupled electron transfer.