RESUMO
BACKGROUND: Digital health programs provide individualized support to patients with chronic diseases and their effectiveness is measured by the extent to which patients achieve target individual clinical outcomes and the program's ability to sustain patient engagement. However, patient dropout and inequitable intervention delivery strategies, which may unintentionally penalize certain patient subgroups, represent challenges to maximizing effectiveness. Therefore, methodologies that optimize the balance between success factors (achievement of target clinical outcomes and sustained engagement) equitably would be desirable, particularly when there are resource constraints. OBJECTIVE: Our objectives were to propose a model for digital health program resource management that accounts jointly for the interaction between individual clinical outcomes and patient engagement, ensures equitable allocation as well as allows for capacity planning, and conducts extensive simulations using publicly available data on type 2 diabetes, a chronic disease. METHODS: We propose a restless multiarmed bandit (RMAB) model to plan interventions that jointly optimize long-term engagement and individual clinical outcomes (in this case measured as the achievement of target healthy glucose levels). To mitigate the tendency of RMAB to achieve good aggregate performance by exacerbating disparities between groups, we propose new equitable objectives for RMAB and apply bilevel optimization algorithms to solve them. We formulated a model for the joint evolution of patient engagement and individual clinical outcome trajectory to capture the key dynamics of interest in digital chronic disease management programs. RESULTS: In simulation exercises, our optimized intervention policies lead to up to 10% more patients reaching healthy glucose levels after 12 months, with a 10% reduction in dropout compared to standard-of-care baselines. Further, our new equitable policies reduce the mean absolute difference of engagement and health outcomes across 6 demographic groups by up to 85% compared to the state-of-the-art. CONCLUSIONS: Planning digital health interventions with individual clinical outcome objectives and long-term engagement dynamics as considerations can be both feasible and effective. We propose using an RMAB sequential decision-making framework, which may offer additional capabilities in capacity planning as well. The integration of an equitable RMAB algorithm further enhances the potential for reaching equitable solutions. This approach provides program designers with the flexibility to switch between different priorities and balance trade-offs across various objectives according to their preferences.
RESUMO
Convolutional neural networks are a type of deep learning algorithm. They are mostly applied in visual recognition and can be used for the identification of melanomas. Multiple studies have evaluated the performance of convolutional neural networks, and most algorithms match or even surpass the accuracy of dermatologists. However, only 23.8% of dermatologists have good or excellent knowledge of the topic. We believe that the lack of knowledge physicians experience regarding artificial intelligence is an obstacle to its clinical implementation. We describe how a convolutional neural network differentiates a benign from a malignant lesion. We systematically searched the Web of Science, Medline (PubMed), and The Cochrane Library on the 9th February, 2022. We focused on articles describing the role and use of artificial intelligence in melanoma recognition between 2017 and 2022, using the following MeSH terms: "melanoma," "diagnosis," and "artificial intelligence". Traditional machine learning algorithms comprise different parts which must preprocess, segment, extract features and classify the lesion into benign or malignant. Deep learning algorithms can perform these steps simultaneously, which significantly enhances efficiency. Convolutional neural networks include a convolutional layer, a pooling layer, and a fully connected layer. Convolutional and pooling layers extract features from the lesion and reduce computational power, whereas fully connected layers classify the image into two or more categories. Additionally, we suggest that further studies should be performed to accelerate the clinical implementation of artificial intelligence, to create comprehensive datasets and to generate explainable algorithms.