Background: HIV and sexually transmitted infections (STIs) are major global public health concerns. Over 1 million curable STIs occur every day among people aged 15 years to 49 years worldwide. Insufficient testing or screening substantially impedes the elimination of HIV and STI transmission. Objective: The aim of our study was to develop an HIV and STI risk prediction tool using machine learning algorithms. Methods: We used clinic consultations that tested for HIV and STIs at the Melbourne Sexual Health Centre between March 2, 2015, and December 31, 2018, as the development data set (training and testing data set). We also used 2 external validation data sets, including data from 2019 as external “validation data 1” and data from January 2020 and January 2021 as external “validation data 2.” We developed 34 machine learning models to assess the risk of acquiring HIV, syphilis, gonorrhea, and chlamydia. We created an online tool to generate an individual’s risk of HIV or an STI. Results: The important predictors for HIV and STI risk were gender, age, men who reported having sex with men, number of casual sexual partners, and condom use. Our machine learning–based risk prediction tool, named MySTIRisk, performed at an acceptable or excellent level on testing data sets (area under the curve [AUC] for HIV=0.78; AUC for syphilis=0.84; AUC for gonorrhea=0.78; AUC for chlamydia=0.70) and had stable performance on both external validation data from 2019 (AUC for HIV=0.79; AUC for syphilis=0.85; AUC for gonorrhea=0.81; AUC for chlamydia=0.69) and data from 2020-2021 (AUC for HIV=0.71; AUC for syphilis=0.84; AUC for gonorrhea=0.79; AUC for chlamydia=0.69). Conclusions: Our web-based risk prediction tool could accurately predict the risk of HIV and STIs for clinic attendees using simple self-reported questions. MySTIRisk could serve as an HIV and STI screening tool on clinic websites or digital health platforms to encourage individuals at risk of HIV or an STI to be tested or start HIV pre-exposure prophylaxis. The public can use this tool to assess their risk and then decide if they would attend a clinic for testing. Clinicians or public health workers can use this tool to identify high-risk individuals for further interventions.

Dermatologists often diagnose or rule out early melanoma by evaluating the follow-up dermoscopic images of skin lesions. However, existing algorithms for early melanoma diagnosis are developed using single time-point images of lesions. Ignoring the temporal, morphological changes of lesions can lead to misdiagnosis in borderline cases. In this study, we propose a framework for automated early melanoma diagnosis using sequential dermoscopic images. To this end, we construct our method in three steps. First, we align sequential dermoscopic images of skin lesions using estimated Euclidean transformations, extract the lesion growth region by computing image differences among the consecutive images, and then propose a spatio-temporal network to capture the dermoscopic changes from aligned lesion images and the corresponding difference images. Finally, we develop an early diagnosis module to compute probability scores of malignancy for lesion images over time. We collected 179 serial dermoscopic imaging data from 122 patients to verify our method. Extensive experiments show that the proposed model outperforms other commonly used sequence models. We also compared the diagnostic results of our model with those of seven experienced dermatologists and five registrars. Our model achieved higher diagnostic accuracy than clinicians (63.69% vs. 54.33%, respectively) and provided an earlier diagnosis of melanoma (60.7% vs. 32.7% of melanoma correctly diagnosed on the first follow-up images). These results demonstrate that our model can be used to identify melanocytic lesions that are at high-risk of malignant transformation earlier in the disease process and thereby redefine what is possible in the early detection of melanoma.

Background: More than one million people acquire sexually transmitted infections (STIs) every day globally. It is possible that predicting an individual’s future risk of HIV/STIs could contribute to behaviour change or improve testing. We developed a series of machine learning models and a subsequent risk-prediction tool for predicting the risk of HIV/STIs over the next 12 months. Methods: Our data included individuals who were re-tested at the clinic for HIV (65,043 consultations), syphilis (56,889 consultations), gonorrhoea (60,598 consultations), and chlamydia (63,529 consultations) after initial consultations at the largest public sexual health centre in Melbourne from 2 March 2015 to 31 December 2019. We used the receiver operating characteristic (AUC) curve to evaluate the model’s performance. The HIV/STI risk-prediction tool was delivered via a web application. Results: Our risk-prediction tool had an acceptable performance on the testing datasets for predicting HIV (AUC = 0.72), syphilis (AUC = 0.75), gonorrhoea (AUC = 0.73), and chlamydia (AUC = 0.67) acquisition. Conclusions: Using machine learning techniques, our risk-prediction tool has acceptable reliability in predicting HIV/STI acquisition over the next 12 months. This tool may be used on clinic websites or digital health platforms to form part of an intervention tool to increase testing or reduce future HIV/STI risk.

In the real world, medical datasets often exhibit a long-tailed data distribution (i.e., a few classes occupy the majority of the data, while most classes have only a limited number of samples), which results in a challenging long-tailed learning scenario. Some recently published datasets in ophthalmology AI consist of more than 40 kinds of retinal diseases with complex abnormalities and variable morbidity. Nevertheless, more than 30 conditions are rarely seen in global patient cohorts. From a modeling perspective, most deep learning models trained on these datasets may lack the ability to generalize to rare diseases where only a few available samples are presented for training. In addition, there may be more than one disease for the presence of the retina, resulting in a challenging label co-occurrence scenario, also known as multi-label , which can cause problems when some re-sampling strategies are applied during training. To address the above two major challenges, this paper presents a novel method that enables the deep neural network to learn from a long-tailed fundus database for various retinal disease recognition. Firstly, we exploit the prior knowledge in ophthalmology to improve the feature representation using a hierarchy-aware pre-training. Secondly, we adopt an instance-wise class-balanced sampling strategy to address the label co-occurrence issue under the long-tailed medical dataset scenario. Thirdly, we introduce a novel hybrid knowledge distillation to train a less biased representation and classifier. We conducted extensive experiments on four databases, including two public datasets and two in-house databases with more than one million fundus images. The experimental results demonstrate the superiority of our proposed methods with recognition accuracy outperforming the state-of-the-art competitors, especially for these rare diseases.

Retinal age has emerged as a promising biomarker of aging, offering a non-invasive and accessible assessment tool. We developed a deep learning model to estimate retinal age with enhanced accuracy, leveraging retinal images from diverse populations. Our approach integrates self-supervised learning to capture chronological information from both snapshot and sequential images, alongside a progressive label distribution learning module to model biological aging variability. Trained and validated on healthy cohorts (34,433 participants from the UK Biobank and three Chinese cohorts), the model achieved a mean absolute error of 2.79 years, surpassing previous methods. When applied to broader populations, analysis of the retinal age gap—the difference between retina-predicted and chronological age—revealed associations with increased risks of all-cause mortality and multiple age-related diseases. These findings highlight the potential of retinal age as a reliable biomarker for predicting survival and aging outcomes, supporting targeted risk management and precision health interventions.

Deep learning models for medical image analysis easily suffer from distribution shifts caused by dataset artifact bias, camera variations, differences in the imaging station, etc., leading to unreliable diagnoses in real-world clinical settings. Domain generalization (DG) methods, which aim to train models on multiple domains to perform well on unseen domains, offer a promising direction to solve the problem. However, existing DG methods assume domain labels of each image are available and accurate, which is typically feasible for only a limited number of medical datasets. To address these challenges, we propose a unified DG framework for medical image classification without relying on domain labels, called Prompt-driven Latent Domain Generalization (PLDG). PLDG consists of unsupervised domain discovery and prompt learning. This framework first discovers pseudo domain labels by clustering the bias-associated style features, then leverages collaborative domain prompts to guide a Vision Transformer to learn knowledge from discovered diverse domains. To facilitate cross-domain knowledge learning between different prompts, we introduce a domain prompt generator that enables knowledge sharing between domain prompts and a shared prompt. A domain mixup strategy is additionally employed for more flexible decision margins and mitigates the risk of incorrect domain assignments. Extensive experiments on three medical image classification tasks and one debiasing task demonstrate that our method can achieve comparable or even superior performance than conventional DG algorithms without relying on domain labels. Our code is publicly available at https://github.com/SiyuanYan1/PLDG/tree/main.