Precision Medicine (PM) transforms the traditional "one-drug-fits-all" paradigm by customising treatments based on individual characteristics, and is an emerging topic for HCI research on digital health. A key element of PM, the Polygenic Risk Score (PRS), uses genetic data to predict an individual's disease risk. Despite its potential, PRS faces barriers to adoption, such as data inclusivity, psychological impact, and public trust. We conducted a mixed-methods study to explore how people perceive PRS, formed of surveys (n=254) and interviews (n=11) with UK-based participants. The interviews were supplemented by interactive storyboards with the ContraVision technique to provoke deeper reflection and discussion. We identified ten key barriers and five themes to PRS adoption and proposed design implications for a responsible PRS framework. To address the complexities of PRS and enhance broader PM practices, we introduce the term Human-Precision Medicine Interaction (HPMI), which integrates, adapts, and extends HCI approaches to better meet these challenges.
Large language models (LLMs) excel in various NLP tasks and modern medicine, but their evaluation in traditional Chinese medicine (TCM) is underexplored. To address this, we introduce TCM3CEval, a benchmark assessing LLMs in TCM across three dimensions: core knowledge mastery, classical text understanding, and clinical decision-making. We evaluate diverse models, including international (e.g., GPT-4o), Chinese (e.g., InternLM), and medical-specific (e.g., PLUSE). Results show a performance hierarchy: all models have limitations in specialized subdomains like Meridian & Acupoint theory and Various TCM Schools, revealing gaps between current capabilities and clinical needs. Models with Chinese linguistic and cultural priors perform better in classical text interpretation and clinical reasoning. TCM-3CEval sets a standard for AI evaluation in TCM, offering insights for optimizing LLMs in culturally grounded medical domains. The benchmark is available on Medbench's TCM track, aiming to assess LLMs' TCM capabilities in basic knowledge, classic texts, and clinical decision-making through multidimensional questions and real cases.
Recent advances in artificial intelligence (AI) and multimodal data collection are revolutionizing dermatology. Generative AI and machine learning approaches offer opportunities to enhance the diagnosis and treatment of inflammatory skin diseases, including atopic dermatitis, psoriasis, hidradenitis suppurativa, and autoimmune connective tissue disease. This review examines the current landscape of AI applications for inflammatory skin diseases and explores how generative AI and machine learning methods can advance the field through deep phenotyping, disease heterogeneity characterization, drug development, personalized medicine, and clinical care. We discuss the promises and challenges of these technologies and present a vision for their integration into clinical practice.
Appadurai Daniel Reegan, Sam Joy, Purushotham Jambulingam
et al.
Abstract Background Vector-borne diseases remain a major global health problem, mostly in tropical and subtropical areas. Effective vector control is crucial for controlling vector borne diseases (VBDs). Over the years various vector control tools and strategies have been employed globally. However, the recent challenges including insecticide-resistant, alterations in vector behaviour, and non-target effects have highlighted the need for novel vector control tools and alternate strategies. One such tool is the Attractive Targeted Sugar Baits (ATSBs), which uses the sugar-seeking habit of adult mosquitoes. The ATSB strategy operates on an “attract and kill” approach, where mosquitoes are lured to the bait and to feed on sugar combined with an insecticide. For this, a standard methodology needs to be developed for a uniform evaluation of ATSBs. Results The ATSB vector control strategy has shown promising results in studies carried out in various parts of Africa and the Middle East on controlling populations of mosquito species. Although numerous experiments have been conducted and are ongoing in various countries, there remains a lack of standardized guidelines for evaluating ATSBs. In 2023, the ICMR along with partners drafted the 3rd edition of Common Protocols for evaluating public health vector control products. The revised edition included a trial methodology for ATSB. Taking this into consideration, the phase-wise standard methodology is presented in this review for the uniform evaluation of different formulations/products of ATSBs. Conclusions The methodologies, outlined in this article will serve as the standard methodology for testing ATSB formulations/products under laboratory conditions (Phase I), small-phase (Phase II), and large-phase field trial (Phase III) conditions.
Arctic medicine. Tropical medicine, Infectious and parasitic diseases
Manlio De Domenico, Luca Allegri, Guido Caldarelli
et al.
The adoption of digital twins (DTs) in precision medicine is increasingly viable, propelled by extensive data collection and advancements in artificial intelligence (AI), alongside traditional biomedical methodologies. However, the reliance on black-box predictive models, which utilize large datasets, presents limitations that could impede the broader application of DTs in clinical settings. We argue that hypothesis-driven generative models, particularly multiscale modeling, are essential for boosting the clinical accuracy and relevance of DTs, thereby making a significant impact on healthcare innovation. This paper explores the transformative potential of DTs in healthcare, emphasizing their capability to simulate complex, interdependent biological processes across multiple scales. By integrating generative models with extensive datasets, we propose a scenario-based modeling approach that enables the exploration of diverse therapeutic strategies, thus supporting dynamic clinical decision-making. This method not only leverages advancements in data science and big data for improving disease treatment and prevention but also incorporates insights from complex systems and network science, quantitative biology, and digital medicine, promising substantial advancements in patient care.
Davide Belluomo, Tiziana Calamoneri, Giacomo Paesani
et al.
We present a new unified graph-based representation of medical data, combining genetic information and medical records of patients with medical knowledge via a unique knowledge graph. This approach allows us to infer meaningful information and explanations that would be unavailable by looking at each data set separately. The systematic use of different databases, managed throughout the built knowledge graph, gives new insights toward a better understanding of oncology medicine. Indeed, we reduce some useful medical tasks to well-known problems in theoretical computer science for which efficient algorithms exist.
While large language models (LLMs) have achieved state-of-the-art performance on a wide range of medical question answering (QA) tasks, they still face challenges with hallucinations and outdated knowledge. Retrieval-augmented generation (RAG) is a promising solution and has been widely adopted. However, a RAG system can involve multiple flexible components, and there is a lack of best practices regarding the optimal RAG setting for various medical purposes. To systematically evaluate such systems, we propose the Medical Information Retrieval-Augmented Generation Evaluation (MIRAGE), a first-of-its-kind benchmark including 7,663 questions from five medical QA datasets. Using MIRAGE, we conducted large-scale experiments with over 1.8 trillion prompt tokens on 41 combinations of different corpora, retrievers, and backbone LLMs through the MedRAG toolkit introduced in this work. Overall, MedRAG improves the accuracy of six different LLMs by up to 18% over chain-of-thought prompting, elevating the performance of GPT-3.5 and Mixtral to GPT-4-level. Our results show that the combination of various medical corpora and retrievers achieves the best performance. In addition, we discovered a log-linear scaling property and the "lost-in-the-middle" effects in medical RAG. We believe our comprehensive evaluations can serve as practical guidelines for implementing RAG systems for medicine.
Objective. To identify challenges that may raise pathogens’ resistance to antimicrobial drugs by exploring the private market for antimicrobials in two selected mining and frontier areas of Guyana.
Methods. The private sector supply was mapped by approaching all authorized pharmacies and informal outlets, e.g., street vendors and grocery stores, around the two selected towns. Interviews were conducted with a) sellers on the availability of drugs, expiration dates, prices, and main producers; and b) customers on purchased drugs, diagnoses, and prescriptions received before purchasing drugs, and intention to complete the treatment. The information collected was described, and the determinants of the self-reported intention of customers to complete the whole treatment were identified.
Results. From the perspective of the supply of antimicrobials, essential medicines faced low and insecure availability, and prescriptions frequently deviated from diagnoses. From the perspective of the demand for antimicrobials, one-third of purchased antibiotics had a high potential for antimicrobial resistance as per the World Health Organization AWaRe classification. A high price reduced the self-reported intention to complete the treatment among those who had a prescription, while buying the medication in a licensed pharmacy increased such intention.
Conclusions. In Guyana, there persists a need to establish and revise policies addressing both supply and demand, such as restricting the sale of antimicrobials to licensed pharmacies and upon prescription, improving prescription practices while reducing the financial burden to patients, guaranteeing access to first-line treatment drugs, and instructing patients on appropriate use of antimicrobials. Revising such policies is an essential step to contain antimicrobial resistance in the analyzed areas and across Guyana.
Theresa Blümlein, Joel Persson, Stefan Feuerriegel
Dynamic treatment regimes (DTRs) are used in medicine to tailor sequential treatment decisions to patients by considering patient heterogeneity. Common methods for learning optimal DTRs, however, have shortcomings: they are typically based on outcome prediction and not treatment effect estimation, or they use linear models that are restrictive for patient data from modern electronic health records. To address these shortcomings, we develop two novel methods for learning optimal DTRs that effectively handle complex patient data. We call our methods DTR-CT and DTR-CF. Our methods are based on a data-driven estimation of heterogeneous treatment effects using causal tree methods, specifically causal trees and causal forests, that learn non-linear relationships, control for time-varying confounding, are doubly robust, and explainable. To the best of our knowledge, our paper is the first that adapts causal tree methods for learning optimal DTRs. We evaluate our proposed methods using synthetic data and then apply them to real-world data from intensive care units. Our methods outperform state-of-the-art baselines in terms of cumulative regret and percentage of optimal decisions by a considerable margin. Our work improves treatment recommendations from electronic health record and is thus of direct relevance for personalized medicine.
Predrag Popović, Justin Finkel, Mary C. Silber
et al.
Our ability to predict the future of Arctic sea ice is limited by ice's sensitivity to detailed surface conditions such as the distribution of snow and melt ponds. Snow on top of the ice decreases ice's thermal conductivity, increases its reflectivity (albedo), and provides a source of meltwater for melt ponds during summer that decrease the ice's albedo. In this paper, we develop a simple model of pre-melt snow topography that accurately describes snow cover of flat, undeformed Arctic sea ice on several study sites for which data was available. The model considers a surface that is a sum of randomly sized and placed "snow dunes" represented as Gaussian mounds. This model generalizes the "void model" of Popović et al. (2018) and, as such, accurately describes the statistics of melt pond geometry. We test this model against detailed LiDAR measurements of the pre-melt snow topography. We show that the model snow-depth distribution is statistically indistinguishable from the measurements on flat ice, while small disagreement exists if the ice is deformed. We then use this model to determine analytic expressions for the conductive heat flux through the ice and for melt pond coverage evolution during an early stage of pond formation. We also formulate a criterion for ice to remain pond-free throughout the summer. Results from our model could be directly included in large-scale models, thereby improving our understanding of energy balance on sea ice and allowing for more reliable predictions of Arctic sea ice in a future climate.
Zeinab Rafiee, Maasoumeh Zare Moaiedi, Armita Valizadeh Gorji
et al.
Objective: To evaluate the effect of p-coumaric acid against adriamycin-induced hepatotoxicity in rats.
Methods: The rats were divided into 4 groups. The control group received solvent; the p-coumaric acid group was treated with 100 mg/kg of p-coumaric acid orally for five consecutive days; the adriamycin group was administered with a single dose of adriamycin (15 mg/kg, i.p.), and the p-coumaric acid + adriamycin group was given p-coumaric acid five days before adriamycin administration. Twenty-four hours after the last administration, blood samples were collected for biochemical analysis, and liver tissues were removed for histopathological and immunohistochemistrical studies. Moreover, the levels of tissue lipid peroxidation and enzyme activities of glutathione peroxidase, superoxide dismutase, and catalase in liver tissue were measured.
Results: Treatment with p-coumaric acid protected the liver from the toxicity of adriamycin by attenuating the increase in alkaline phosphatase, alanine transaminase, aspartate transaminase, total bilirubin, total cholesterol, triglyceride, and low-density lipoprotein cholesterol and lessening the decrease in high-density lipoprotein cholesterol and albumin. p-Coumaric acid also raised the levels of glutathione peroxidase, superoxide dismutase, and catalase, as well as decreased lipid peroxidation in liver tissue and hepatic IL- 1β expression. Additionally, histopathological study confirmed the protective effect of p-coumaric acid against liver damage.
Conclusions: p-Coumaric acid can alleviate adriamycin-induced hepatotoxicity.
Babatunde Adewale, Jonathan R Heintz, Christopher F Pastore
et al.
Helminth infections, including hookworms and Schistosomes, can cause severe disability and death. Infection management and control would benefit from identification of biomarkers for early detection and prognosis. While animal models suggest that Trefoil Factor Family proteins (TFF2 and TFF3) and interleukin-33 (IL-33) -driven type 2 immune responses are critical mediators of tissue repair and worm clearance in the context of hookworm infection, very little is known about how they are modulated in the context of human helminth infection. We measured TFF2, TFF3, and IL-33 levels in serum from patients in Brazil infected with Hookworm and/or Schistosomes, and compared them to endemic and non-endemic controls. TFF2 was specifically elevated by Hookworm infection in females, not Schistosoma or co-infection. This elevation was correlated with age, but not worm burden. TFF3 was elevated by Schistosoma infection and found to be generally higher in females. IL-33 was not significantly altered by infection. To determine if this might apply more broadly to other species or regions, we measured TFFs and cytokine levels (IFNγ, TNFα, IL-33, IL-13, IL-1β, IL-17A, IL-22, and IL-10) in both the serum and urine of Nigerian school children infected with S. haematobium. We found that serum levels of TFF2 and 3 were reduced by infection, likely in an age dependent manner. In the serum, only IL-10 and IL-13 were significantly increased, while in urine IFN-γ, TNF-α, IL-13, IL-1β, IL-22, and IL-10 were significantly increased in by infection. Taken together, these data support a role for TFF proteins in human helminth infection.
Arctic medicine. Tropical medicine, Public aspects of medicine
Traditional Chinese medicine (TCM) has played an important role in the prevention and control of the novel coronavirus pneumonia (COVID-19), and community prevention has become the most essential part in reducing the spread risk and protecting populations. However, most communities use a uniform TCM prevention program for all residents, which violates the "treatment based on syndrome differentiation" principle of TCM and limits the effectiveness of prevention. In this paper, we propose an intelligent optimization method to develop diversified TCM prevention programs for community residents. First, we use a fuzzy clustering method to divide the population based on both modern medicine and TCM health characteristics; we then use an interactive optimization method, in which TCM experts develop different TCM prevention programs for different clusters, and a heuristic algorithm is used to optimize the programs under the resource constraints. We demonstrate the computational efficiency of the proposed method and report its successful application to TCM-based prevention of COVID-19 in 12 communities in Zhejiang province, China, during the peak of the pandemic.
N. T. Bagraev, L. E. Klyachkin, A. M. Malyarenko
et al.
A spectrometer based on silicon nanosandwiches (SNS) is proposed for problems of personalized medicine. SNS structures exhibit properties of terahertz (THz) emitter and receiver of the THz response of biological tissue. Measurements of the current-voltage curves of the SNS structure make it possible to analyze the spectral composition of the THz response of biological tissue and determine relative contributions of various proteins and amino acids contained in the structure of DNA oligonucleotides and the corresponding compounds. Evident advantages of the proposed method are related to the fact that the THz response can be directly obtained from living biological tissue and, hence, used for express analysis of the DNA oligonucleotides. Tests of several control groups show that the further analysis of the specific features of the spectral peaks of the SNS current-voltage curves is of interest for methods of personalized diagnostics and treatment.
Abraham Geremew, Selamawit Gebremedhin, Yohannes Mulugeta
et al.
Abstract Background Globally, acute respiratory infections are among the leading causes of under-five child mortality, especially in lower-income countries; it is associated with indoor exposure to toxic pollutants from solid biomass fuel. In Ethiopia, 90% of the population utilizes solid biomass fuel; respiratory illness is a leading health problem. However, there is a paucity of nationally representative data on the association of household cooking place and respiratory infections. Besides, evidence on the variability in the infection based on the data collected at different times is limited. Therefore, this study is intended to assess the association of food cooking place with acute respiratory infections and the variability in households and surveys. Methods The current analysis is based on the Ethiopian Demographic and Health Survey data collected in 2005, 2011, and 2016 and obtained via online registration. The association of food cooking place with acute respiratory infection was assessed using multilevel modeling after categorizing all factors into child level and survey level, controlling them in a full model. The analyses accounted for a complex survey design using a Stata command “svy.” Result A total of 30,895 under-five children were included in this study, of which 3677 (11.9%) children had an acute respiratory infection, with 12.7% in 2005, 11.9% in 2011, and 11.1% in 2016. The risk of having an infection in under-five children in households that cooked food outdoors was 44% lower (AOR = 0.56, 95% CI = 0.40, 0.75) compared to those households that cooked the food inside the house. There was a statistically significant difference among the children among surveys to have an acute respiratory infection. Conclusion The risk of having children with acute respiratory infection is lower in the households of cooking food outdoor compared to indoor. The infection difference in different surveys suggests progress in the practices in either food cooking places or the fuel types used that minimize food cooking places location or the fuel types used that minimizes the risk. But, the infection is still high; therefore, measures promoting indoor cooking in a well-ventilated environment with alternative energy sources should take place.
Naim U. Rashid, Daniel J. Luckett, Jingxiang Chen
et al.
The complexity of human cancer often results in significant heterogeneity in response to treatment. Precision medicine offers potential to improve patient outcomes by leveraging this heterogeneity. Individualized treatment rules (ITRs) formalize precision medicine as maps from the patient covariate space into the space of allowable treatments. The optimal ITR is that which maximizes the mean of a clinical outcome in a population of interest. Patient-derived xenograft (PDX) studies permit the evaluation of multiple treatments within a single tumor and thus are ideally suited for estimating optimal ITRs. PDX data are characterized by correlated outcomes, a high-dimensional feature space, and a large number of treatments. Existing methods for estimating optimal ITRs do not take advantage of the unique structure of PDX data or handle the associated challenges well. In this paper, we explore machine learning methods for estimating optimal ITRs from PDX data. We analyze data from a large PDX study to identify biomarkers that are informative for developing personalized treatment recommendations in multiple cancers. We estimate optimal ITRs using regression-based approaches such as Q-learning and direct search methods such as outcome weighted learning. Finally, we implement a superlearner approach to combine a set of estimated ITRs and show that the resulting ITR performs better than any of the input ITRs, mitigating uncertainty regarding user choice of any particular ITR estimation methodology. Our results indicate that PDX data are a valuable resource for developing individualized treatment strategies in oncology.
Krzysztof J. Cios, Bartosz Krawczyk, Jacquelyne Cios
et al.
The paper describes how the new technologies and data they generate are transforming medicine. It stresses the uniqueness of heterogeneous medical data and the ways of dealing with them. It lists different sources that generate big medical data, their security, legal and ethical issues, as well as machine learning/AI methods of dealing with them. A unique feature of the paper is use of case studies to illustrate how the new technologies influence medical practice.
Machine learning (ML), deep learning (DL), and artificial intelligence (AI) are of increasing importance in biomedicine. The goal of this work is to show progress in ML in digital health, to exemplify future needs and trends, and to identify any essential prerequisites of AI and ML for precision health. High-throughput technologies are delivering growing volumes of biomedical data, such as large-scale genome-wide sequencing assays, libraries of medical images, or drug perturbation screens of healthy, developing, and diseased tissue. Multi-omics data in biomedicine is deep and complex, offering an opportunity for data-driven insights and automated disease classification. Learning from these data will open our understanding and definition of healthy baselines and disease signatures. State-of-the-art applications of deep neural networks include digital image recognition, single cell clustering, and virtual drug screens, demonstrating breadths and power of ML in biomedicine. Significantly, AI and systems biology have embraced big data challenges and may enable novel biotechnology-derived therapies to facilitate the implementation of precision medicine approaches.