RESUMO
BACKGROUND: Discharge letters are a critical component in the continuity of care between specialists and primary care providers. However, these letters are time-consuming to write, underprioritized in comparison to direct clinical care, and are often tasked to junior doctors. Prior studies assessing the quality of discharge summaries written for inpatient hospital admissions show inadequacies in many domains. Large language models such as GPT have the ability to summarize large volumes of unstructured free text such as electronic medical records and have the potential to automate such tasks, providing time savings and consistency in quality. OBJECTIVE: The aim of this study was to assess the performance of GPT-4 in generating discharge letters written from urology specialist outpatient clinics to primary care providers and to compare their quality against letters written by junior clinicians. METHODS: Fictional electronic records were written by physicians simulating 5 common urology outpatient cases with long-term follow-up. Records comprised simulated consultation notes, referral letters and replies, and relevant discharge summaries from inpatient admissions. GPT-4 was tasked to write discharge letters for these cases with a specified target audience of primary care providers who would be continuing the patient's care. Prompts were written for safety, content, and style. Concurrently, junior clinicians were provided with the same case records and instructional prompts. GPT-4 output was assessed for instances of hallucination. A blinded panel of primary care physicians then evaluated the letters using a standardized questionnaire tool. RESULTS: GPT-4 outperformed human counterparts in information provision (mean 4.32, SD 0.95 vs 3.70, SD 1.27; P=.03) and had no instances of hallucination. There were no statistically significant differences in the mean clarity (4.16, SD 0.95 vs 3.68, SD 1.24; P=.12), collegiality (4.36, SD 1.00 vs 3.84, SD 1.22; P=.05), conciseness (3.60, SD 1.12 vs 3.64, SD 1.27; P=.71), follow-up recommendations (4.16, SD 1.03 vs 3.72, SD 1.13; P=.08), and overall satisfaction (3.96, SD 1.14 vs 3.62, SD 1.34; P=.36) between the letters generated by GPT-4 and humans, respectively. CONCLUSIONS: Discharge letters written by GPT-4 had equivalent quality to those written by junior clinicians, without any hallucinations. This study provides a proof of concept that large language models can be useful and safe tools in clinical documentation.
Assuntos
Alta do Paciente , Humanos , Alta do Paciente/normas , Registros Eletrônicos de Saúde/normas , Método Simples-Cego , IdiomaRESUMO
BACKGROUND: Diabetic retinopathy (DR) and diabetic macular edema (DME) are major causes of visual impairment that challenge global vision health. New strategies are needed to tackle these growing global health problems, and the integration of artificial intelligence (AI) into ophthalmology has the potential to revolutionize DR and DME management to meet these challenges. MAIN TEXT: This review discusses the latest AI-driven methodologies in the context of DR and DME in terms of disease identification, patient-specific disease profiling, and short-term and long-term management. This includes current screening and diagnostic systems and their real-world implementation, lesion detection and analysis, disease progression prediction, and treatment response models. It also highlights the technical advancements that have been made in these areas. Despite these advancements, there are obstacles to the widespread adoption of these technologies in clinical settings, including regulatory and privacy concerns, the need for extensive validation, and integration with existing healthcare systems. We also explore the disparity between the potential of AI models and their actual effectiveness in real-world applications. CONCLUSION: AI has the potential to revolutionize the management of DR and DME, offering more efficient and precise tools for healthcare professionals. However, overcoming challenges in deployment, regulatory compliance, and patient privacy is essential for these technologies to realize their full potential. Future research should aim to bridge the gap between technological innovation and clinical application, ensuring AI tools integrate seamlessly into healthcare workflows to enhance patient outcomes.
RESUMO
Introduction: Automated machine learning (autoML) removes technical and technological barriers to building artificial intelligence models. We aimed to summarise the clinical applications of autoML, assess the capabilities of utilised platforms, evaluate the quality of the evidence trialling autoML, and gauge the performance of autoML platforms relative to conventionally developed models, as well as each other. Method: This review adhered to a prospectively registered protocol (PROSPERO identifier CRD42022344427). The Cochrane Library, Embase, MEDLINE and Scopus were searched from inception to 11 July 2022. Two researchers screened abstracts and full texts, extracted data and conducted quality assessment. Disagreement was resolved through discussion and if required, arbitration by a third researcher. Results: There were 26 distinct autoML platforms featured in 82 studies. Brain and lung disease were the most common fields of study of 22 specialties. AutoML exhibited variable performance: area under the receiver operator characteristic curve (AUCROC) 0.35-1.00, F1-score 0.16-0.99, area under the precision-recall curve (AUPRC) 0.51-1.00. AutoML exhibited the highest AUCROC in 75.6% trials; the highest F1-score in 42.3% trials; and the highest AUPRC in 83.3% trials. In autoML platform comparisons, AutoPrognosis and Amazon Rekognition performed strongest with unstructured and structured data, respectively. Quality of reporting was poor, with a median DECIDE-AI score of 14 of 27. Conclusion: A myriad of autoML platforms have been applied in a variety of clinical contexts. The performance of autoML compares well to bespoke computational and clinical benchmarks. Further work is required to improve the quality of validation studies. AutoML may facilitate a transition to data-centric development, and integration with large language models may enable AI to build itself to fulfil user-defined goals.
Assuntos
Aprendizado de Máquina , Humanos , Pneumopatias/diagnóstico , Curva ROC , Encefalopatias/diagnóstico , Área Sob a CurvaRESUMO
The objective of this study is to define structure-function relationships of pathological lesions related to age-related macular degeneration (AMD) using microperimetry and multimodal retinal imaging. We conducted a cross-sectional study of 87 patients with AMD (30 eyes with early and intermediate AMD and 110 eyes with advanced AMD), compared to 33 normal controls (66 eyes) recruited from a single tertiary center. All participants had enface and cross-sectional optical coherence tomography (Heidelberg HRA-2), OCT angiography, color and infra-red (IR) fundus and microperimetry (MP) (Nidek MP-3) performed. Multimodal images were graded for specific AMD pathological lesions. A custom marking tool was used to demarcate lesion boundaries on corresponding enface IR images, and subsequently superimposed onto MP color fundus photographs with retinal sensitivity points (RSP). The resulting overlay was used to correlate pathological structural changes to zonal functional changes. Mean age of patients with early/intermediate AMD, advanced AMD and controls were 73(SD = 8.2), 70.8(SD = 8), and 65.4(SD = 7.7) years respectively. Mean retinal sensitivity (MRS) of both early/intermediate (23.1 dB; SD = 5.5) and advanced AMD (18.1 dB; SD = 7.8) eyes were significantly worse than controls (27.8 dB, SD = 4.3) (p < 0.01). Advanced AMD eyes had significantly more unstable fixation (70%; SD = 63.6), larger mean fixation area (3.9 mm2; SD = 3.0), and focal fixation point further away from the fovea (0.7 mm; SD = 0.8), than controls (29%; SD = 43.9; 2.6 mm2; SD = 1.9; 0.4 mm; SD = 0.3) (p ≤ 0.01). Notably, 22 fellow eyes of AMD eyes (25.7 dB; SD = 3.0), with no AMD lesions, still had lower MRS than controls (p = 0.04). For specific AMD-related lesions, end-stage changes such as fibrosis (5.5 dB, SD = 5.4 dB) and atrophy (6.2 dB, SD = 7.0 dB) had the lowest MRS; while drusen and pigment epithelial detachment (17.7 dB, SD = 8.0 dB) had the highest MRS. Peri-lesional areas (20.2 dB, SD = 7.6 dB) and surrounding structurally normal areas (22.2 dB, SD = 6.9 dB) of the retina with no AMD lesions still had lower MRS compared to controls (27.8 dB, SD = 4.3 dB) (p < 0.01). Our detailed topographic structure-function correlation identified specific AMD pathological changes associated with a poorer visual function. This can provide an added value to the assessment of visual function to optimize treatment outcomes to existing and potentially future novel therapies.
Assuntos
Degeneração Macular , Humanos , Estudos Transversais , Estudos Prospectivos , Degeneração Macular/diagnóstico por imagem , Tomografia de Coerência Óptica , Angiofluoresceinografia , Relação Estrutura-AtividadeRESUMO
Large language models (LLMs) underlie remarkable recent advanced in natural language processing, and they are beginning to be applied in clinical contexts. We aimed to evaluate the clinical potential of state-of-the-art LLMs in ophthalmology using a more robust benchmark than raw examination scores. We trialled GPT-3.5 and GPT-4 on 347 ophthalmology questions before GPT-3.5, GPT-4, PaLM 2, LLaMA, expert ophthalmologists, and doctors in training were trialled on a mock examination of 87 questions. Performance was analysed with respect to question subject and type (first order recall and higher order reasoning). Masked ophthalmologists graded the accuracy, relevance, and overall preference of GPT-3.5 and GPT-4 responses to the same questions. The performance of GPT-4 (69%) was superior to GPT-3.5 (48%), LLaMA (32%), and PaLM 2 (56%). GPT-4 compared favourably with expert ophthalmologists (median 76%, range 64-90%), ophthalmology trainees (median 59%, range 57-63%), and unspecialised junior doctors (median 43%, range 41-44%). Low agreement between LLMs and doctors reflected idiosyncratic differences in knowledge and reasoning with overall consistency across subjects and types (p>0.05). All ophthalmologists preferred GPT-4 responses over GPT-3.5 and rated the accuracy and relevance of GPT-4 as higher (p<0.05). LLMs are approaching expert-level knowledge and reasoning skills in ophthalmology. In view of the comparable or superior performance to trainee-grade ophthalmologists and unspecialised junior doctors, state-of-the-art LLMs such as GPT-4 may provide useful medical advice and assistance where access to expert ophthalmologists is limited. Clinical benchmarks provide useful assays of LLM capabilities in healthcare before clinical trials can be designed and conducted.
RESUMO
Federated learning (FL) is a distributed machine learning framework that is gaining traction in view of increasing health data privacy protection needs. By conducting a systematic review of FL applications in healthcare, we identify relevant articles in scientific, engineering, and medical journals in English up to August 31st, 2023. Out of a total of 22,693 articles under review, 612 articles are included in the final analysis. The majority of articles are proof-of-concepts studies, and only 5.2% are studies with real-life application of FL. Radiology and internal medicine are the most common specialties involved in FL. FL is robust to a variety of machine learning models and data types, with neural networks and medical imaging being the most common, respectively. We highlight the need to address the barriers to clinical translation and to assess its real-world impact in this new digital data-driven healthcare scene.
Assuntos
Atenção à Saúde , Aprendizado de Máquina , Humanos , Redes Neurais de ComputaçãoRESUMO
PURPOSE: To evaluate the relationship between specific monocular and binocular visual function (VF) assessments with binocularly performed activities of daily living task tests (ADLTTs) in patients with age-related macular degeneration (AMD) and healthy controls. DESIGN: Prospective case-control cohort study. SUBJECTS: Thirty-six AMD patients and 36 controls. METHOD: Visual field assessments included monocular and binocular best-corrected visual acuity (BCVA), contrast sensitivity (CS), and monocular microperimetry testing for mean macula sensitivity, mean retina sensitivity (MRS), fixation area, and fixation distance from fovea (FDF). Age-related macular degeneration lesion area and sensitivity were measured on OCT and microperimetry, respectively. Participants performed 4 validated ADLTTs with binocular BCVA: (1) reading; (2) item-search; (3) money-counting; and (4) multi-step drink-making tasks. MAIN OUTCOME MEASURES: Spearman correlations and multivariate regression analysis, adjusted for age, sex, and potential correlation between the 2 eyes, were used to assess the relationship between monocular and binocular VF assessments, and ADLTT performance in both groups. RESULTS: Age-related macular degeneration patients had poorer VF (BCVA, CS, mean macula sensitivity, and MRS) compared with healthy controls. Monocular BCVA in both better- and worse-vision eyes was moderately correlated with the binocular reading speed and money-counting tasks in participants with AMD. In AMD, monocular worse eye CS, MRS, AMD lesion area on OCT, and lesion sensitivity on microperimetry showed moderate correlations to various ADLTTs, such as reading, money-counting, and drink-making. Similar findings were found in our AMD cohort on multivariate regression analysis. Fewer significant correlations were observed for the better-vision eye, whereas no correlations were observed for healthy controls between VF parameters and ADLTTs. In contrast, significant associations were observed between binocular BCVA and CS with binocular ADLTTs (reading and item-search tasks) but not in AMD patients. CONCLUSION: Although monocular BCVA remains the most common measure of VF, CS and microperimetry testing also show significant correlations with ADLTTs performance in AMD patients, and should be considered as complimentary VF-outcome measures in both clinical and research settings. Unlike healthy subjects, AMD patients do not rely on binocular VF for ADLTT function, with the worse-vision eye impacting binocular ADLTT function more than the better-vision eye. Therefore, the worse-vision eye should not be neglected during the management of AMD. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
Assuntos
Atividades Cotidianas , Degeneração Macular , Humanos , Acuidade Visual , Estudos de Casos e Controles , Visão Binocular , Degeneração Macular/diagnósticoRESUMO
The Metaverse has gained wide attention for being the application interface for the next generation of Internet. The potential of the Metaverse is growing, as Web 3·0 development and adoption continues to advance medicine and healthcare. We define the next generation of interoperable healthcare ecosystem in the Metaverse. We examine the existing literature regarding the Metaverse, explain the technology framework to deliver an immersive experience, along with a technical comparison of legacy and novel Metaverse platforms that are publicly released and in active use. The potential applications of different features of the Metaverse, including avatar-based meetings, immersive simulations, and social interactions are examined with different roles from patients to healthcare providers and healthcare organizations. Present challenges in the development of the Metaverse healthcare ecosystem are discussed, along with potential solutions including capabilities requiring technological innovation, use cases requiring regulatory supervision, and sound governance. This proposed concept and framework of the Metaverse could potentially redefine the traditional healthcare system and enhance digital transformation in healthcare. Similar to AI technology at the beginning of this decade, real-world development and implementation of these capabilities are relatively nascent. Further pragmatic research is needed for the development of an interoperable healthcare ecosystem in the Metaverse.
RESUMO
The rapid progress of large language models (LLMs) driving generative artificial intelligence applications heralds the potential of opportunities in health care. We conducted a review up to April 2023 on Google Scholar, Embase, MEDLINE, and Scopus using the following terms: "large language models," "generative artificial intelligence," "ophthalmology," "ChatGPT," and "eye," based on relevance to this review. From a clinical viewpoint specific to ophthalmologists, we explore from the different stakeholders' perspectives-including patients, physicians, and policymakers-the potential LLM applications in education, research, and clinical domains specific to ophthalmology. We also highlight the foreseeable challenges of LLM implementation into clinical practice, including the concerns of accuracy, interpretability, perpetuating bias, and data security. As LLMs continue to mature, it is essential for stakeholders to jointly establish standards for best practices to safeguard patient safety. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
RESUMO
Current and future healthcare professionals are generally not trained to cope with the proliferation of artificial intelligence (AI) technology in healthcare. To design a curriculum that caters to variable baseline knowledge and skills, clinicians may be conceptualized as "consumers", "translators", or "developers". The changes required of medical education because of AI innovation are linked to those brought about by evidence-based medicine (EBM). We outline a core curriculum for AI education of future consumers, translators, and developers, emphasizing the links between AI and EBM, with suggestions for how teaching may be integrated into existing curricula. We consider the key barriers to implementation of AI in the medical curriculum: time, resources, variable interest, and knowledge retention. By improving AI literacy rates and fostering a translator- and developer-enriched workforce, innovation may be accelerated for the benefit of patients and practitioners.
Assuntos
Inteligência Artificial , Educação Médica , Humanos , Currículo , Medicina Baseada em Evidências/educaçãoRESUMO
In this issue of Cell Reports Medicine, Zhao and colleagues1 report a multi-tasking artificial intelligence system that can assist the whole process of fundus fluorescein angiography (FFA) imaging and reduce the reliance on retinal specialists in FFA examination.
Assuntos
Aprendizado Profundo , Terapia a Laser , Doenças Retinianas , Humanos , Vasos Retinianos , Inteligência Artificial , Medicina de Precisão , Fundo de Olho , Doenças Retinianas/diagnóstico por imagem , Doenças Retinianas/terapiaRESUMO
Artificial intelligence (AI) has demonstrated the ability to extract insights from data, but the fairness of such data-driven insights remains a concern in high-stakes fields. Despite extensive developments, issues of AI fairness in clinical contexts have not been adequately addressed. A fair model is normally expected to perform equally across subgroups defined by sensitive variables (e.g., age, gender/sex, race/ethnicity, socio-economic status, etc.). Various fairness measurements have been developed to detect differences between subgroups as evidence of bias, and bias mitigation methods are designed to reduce the differences detected. This perspective of fairness, however, is misaligned with some key considerations in clinical contexts. The set of sensitive variables used in healthcare applications must be carefully examined for relevance and justified by clear clinical motivations. In addition, clinical AI fairness should closely investigate the ethical implications of fairness measurements (e.g., potential conflicts between group- and individual-level fairness) to select suitable and objective metrics. Generally defining AI fairness as "equality" is not necessarily reasonable in clinical settings, as differences may have clinical justifications and do not indicate biases. Instead, "equity" would be an appropriate objective of clinical AI fairness. Moreover, clinical feedback is essential to developing fair and well-performing AI models, and efforts should be made to actively involve clinicians in the process. The adaptation of AI fairness towards healthcare is not self-evident due to misalignments between technical developments and clinical considerations. Multidisciplinary collaboration between AI researchers, clinicians, and ethicists is necessary to bridge the gap and translate AI fairness into real-life benefits.
RESUMO
Background: The implementation of deep learning models for medical image classification poses significant challenges, including gradual performance degradation and limited adaptability to new diseases. However, frequent retraining of models is unfeasible and raises concerns about healthcare privacy due to the retention of prior patient data. To address these issues, this study investigated privacy-preserving continual learning methods as an alternative solution. Methods: We evaluated twelve privacy-preserving non-storage continual learning algorithms based deep learning models for classifying retinal diseases from public optical coherence tomography (OCT) images, in a class-incremental learning scenario. The OCT dataset comprises 108,309 OCT images. Its classes include normal (47.21%), drusen (7.96%), choroidal neovascularization (CNV) (34.35%), and diabetic macular edema (DME) (10.48%). Each class consisted of 250 testing images. For continuous training, the first task involved CNV and normal classes, the second task focused on DME class, and the third task included drusen class. All selected algorithms were further experimented with different training sequence combinations. The final model's average class accuracy was measured. The performance of the joint model obtained through retraining and the original finetune model without continual learning algorithms were compared. Additionally, a publicly available medical dataset for colon cancer detection based on histology slides was selected as a proof of concept, while the CIFAR10 dataset was included as the continual learning benchmark. Results: Among the continual learning algorithms, Brain-inspired-replay (BIR) outperformed the others in the continual learning-based classification of retinal diseases from OCT images, achieving an accuracy of 62.00% (95% confidence interval: 59.36-64.64%), with consistent top performance observed in different training sequences. For colon cancer histology classification, Efficient Feature Transformations (EFT) attained the highest accuracy of 66.82% (95% confidence interval: 64.23-69.42%). In comparison, the joint model achieved accuracies of 90.76% and 89.28%, respectively. The finetune model demonstrated catastrophic forgetting in both datasets. Conclusion: Although the joint retraining model exhibited superior performance, continual learning holds promise in mitigating catastrophic forgetting and facilitating continual model updates while preserving privacy in healthcare deep learning models. Thus, it presents a highly promising solution for the long-term clinical deployment of such models.
RESUMO
PURPOSE OF REVIEW: Despite the growing scope of artificial intelligence (AI) and deep learning (DL) applications in the field of ophthalmology, most have yet to reach clinical adoption. Beyond model performance metrics, there has been an increasing emphasis on the need for explainability of proposed DL models. RECENT FINDINGS: Several explainable AI (XAI) methods have been proposed, and increasingly applied in ophthalmological DL applications, predominantly in medical imaging analysis tasks. SUMMARY: We summarize an overview of the key concepts, and categorize some examples of commonly employed XAI methods. Specific to ophthalmology, we explore XAI from a clinical perspective, in enhancing end-user trust, assisting clinical management, and uncovering new insights. We finally discuss its limitations and future directions to strengthen XAI for application to clinical practice.
RESUMO
Global eye health is defined as the degree to which vision, ocular health, and function are maximised worldwide, thereby optimising overall wellbeing and quality of life. Improving eye health is a global priority as a key to unlocking human potential by reducing the morbidity burden of disease, increasing productivity, and supporting access to education. Although extraordinary progress fuelled by global eye health initiatives has been made over the last decade, there remain substantial challenges impeding further progress. The accelerated development of digital health and artificial intelligence (AI) applications provides an opportunity to transform eye health, from facilitating and increasing access to eye care to supporting clinical decision making with an objective, data-driven approach. Here, we explore the opportunities and challenges presented by digital health and AI in global eye health and describe how these technologies could be leveraged to improve global eye health. AI, telehealth, and emerging technologies have great potential, but require specific work to overcome barriers to implementation. We suggest that a global digital eye health task force could facilitate coordination of funding, infrastructural development, and democratisation of AI and digital health to drive progress forwards in this domain.
Assuntos
Inteligência Artificial , Qualidade de Vida , Humanos , Comitês Consultivos , Tomada de Decisão Clínica , EscolaridadeRESUMO
Colour vision deficiency is an impairment in discriminating colours. Beyond occupational opportunities, colour vision-based restrictions may limit driving, which is a daily task for many people. This review aims to compare existing colour vision requirements for obtaining a driving license in southeast Asian countries to the rest of the world. Subsequently, to review existing published literature and provide evidence-based recommendations for future guidelines for colour-deficient drivers. Color vision requirements for obtaining a driving license vary widely amongst countries. While colour-deficient drivers may face mild challenges in driving, increased awareness and developing effective compensatory strategies could enable them to drive safely. The current evidence does not support a strict exclusion of all colour-deficient individuals from driving. Instead, emphasis is needed on screening to increase awareness and insight into their disability. Future studies should consider compensatory adaptive strategies that are specific for high-risk situations such as challenging driving conditions.
RESUMO
Large language models (LLMs) can respond to free-text queries without being specifically trained in the task in question, causing excitement and concern about their use in healthcare settings. ChatGPT is a generative artificial intelligence (AI) chatbot produced through sophisticated fine-tuning of an LLM, and other tools are emerging through similar developmental processes. Here we outline how LLM applications such as ChatGPT are developed, and we discuss how they are being leveraged in clinical settings. We consider the strengths and limitations of LLMs and their potential to improve the efficiency and effectiveness of clinical, educational and research work in medicine. LLM chatbots have already been deployed in a range of biomedical contexts, with impressive but mixed results. This review acts as a primer for interested clinicians, who will determine if and how LLM technology is used in healthcare for the benefit of patients and practitioners.