Atopic dermatitis (AD) is a skin disease exhibiting clinical and molecular heterogeneity, thereby jeopardizing the development of personalized treatments. Here we pursue a cross-sectional and longitudinal cohort analysis of 951 whole-skin samples, employing an unsupervised decomposition analysis to link gene expression profiles to disease severity, six distinct skin phenotypes, and blood cytokines representative of given endotypes. Specifically, type 2 and type 17 responses are associated with major skin phenotypes such as erythema and induration, while type 1 response is upregulated in lichen amyloidosis of AD patients. Longitudinal analysis of patients treated with dupilumab finds sustained gene signatures related to type 17 response in lesional skin and upregulated transcription factors in non-lesional skin of patients with poor treatment outcomes. Lastly, several extracellular matrix organization-associated genes are correlated with clinical severity and treatment response to dupilumab. Our findings thus provide potential skin and blood biomarkers for assessing endotypes and therapeutic responses in AD to pave the way for personalized medicine.

Modern clinical oncology faces an unprecedented data complexity that exceeds human analytical capacity, making artificial intelligence (AI) integration essential rather than optional. This review examines the dual impact of AI on productivity enhancement and creative discovery in cancer care. We trace the evolution from traditional machine learning to deep learning and transformer-based foundation models, analyzing their clinical applications. AI enhances productivity by automating diagnostic tasks, streamlining documentation, and accelerating research workflows across imaging modalities and clinical data processing. More importantly, AI enables creative discovery by integrating multimodal data to identify computational biomarkers, performing unsupervised phenotyping to reveal hidden patient subgroups, and accelerating drug development. Finally, we introduce the FUTURE-AI framework, outlining the essential requirements for translating AI models into clinical practice. This ensures the responsible deployment of AI, which augments rather than replaces clinical judgment, while maintaining patient-centered care.

Digital transformation of healthcare is rapidly progressing. Digital transformation improves the quality of services and access to health information for users, reduces the workload and associated costs for healthcare providers, and supports clinical decision-making. Data and artificial intelligence (AI) play a key role in this process. The AI used for this purpose is called medical AI. Medical AI is currently undergoing a shift from task-specific to general-purpose models. Large language models have the potential to systematize existing medical knowledge in a standardized way.

As of summer 2020, the COVID-19 pandemic is having a major impact on our daily lives on a global scale, forcing us to change to the new normal. However, the effects are not only detrimental to our present socioeconomic conditions but also have the risk of having negative biological effects on our descendants. Of concern is the effect of maternal immune activation following maternal infection with COVID-19 on the fetus’ cerebral nervous system. While we are currently occupied with countering the imminent threats in front of us, we also need to take steps from a public health perspective to reduce the impact of maternal infection on the fetus, especially the risk of neurodevelopmental disorders. However, such a risk can be prevented and managed through the digital transformation of the nation’s health data and the strategic application of sophisticated data science approaches to those big data.

We developed a model to represent the time evolution phenomena of life through physics constraints. To do this, we took into account that living organisms are open systems that exchange messages through intracellular communication, intercellular communication and sensory systems, and introduced the concept of a message force field. As a result, we showed that the maximum entropy generation principle is valid in time evolution. Then, in order to explain life phenomena based on this principle, we modelled the living system as a nonlinear oscillator coupled by a message and derived the governing equations. The governing equations consist of two laws: one states that the systems are synchronized when the variation of the natural frequencies between them is small or the coupling strength through the message is sufficiently large, and the other states that the synchronization is broken by the proliferation of biological systems. Next, to simulate the phenomena using data obtained from observations of the temporal evolution of life, we developed an inference model that combines physics constraints and a discrete surrogate model using category theory, and simulated the phenomenon of early embryogenesis using this inference model. The results show that symmetry creation and breaking based on message force fields can be widely used to model life phenomena.

Background: Patients’ clinical status often evolves rapidly after an initial diagnosis, with each patient exhibiting a distinct disease trajectory. As a result, static risk scores fall short in supporting timely interventions—an issue highlighted by COVID-19, where deaths have stemmed from heterogeneous pathways such as pneumonia, multiorgan failure, or exacerbation of preexisting conditions. Objective: This study aims to propose a dynamic prognostic risk assessment framework based on longitudinal data collected during hospitalization, using COVID-19 as an example. Our aim was to develop and validate an interpretable framework that (1) screens prognosis at admission and (2) dynamically updates mortality risk throughout hospitalization, thereby providing clinicians with early, explainable warnings while minimizing additional cognitive load. Methods: In this retrospective study, we extracted electronic medical records of 382 COVID-19 cases treated at Tokyo Shinagawa Hospital between January 27 and September 30, 2020. At admission, gradient boosting decision trees (Light Gradient Boosting Machine) were used to predict the maximum clinical deterioration, including death, based on data available at initial diagnosis. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC). For in-hospital monitoring, random survival forests (RSF) were trained on a longitudinal dataset that combined static demographic characteristics with serially measured vital signs and laboratory results. The model dynamically assessed daily mortality risk by calculating a 7-day cumulative hazard function, with risk scores recalculated each day during hospitalization. RSF accuracy was evaluated in an independent one-third test set using the concordance index (C-index), an integrated Brier score (1-50 days), and mean time-dependent AUC. SurvSHAP(t), an extension of Shapley Additive Explanations, was applied to provide time-dependent explanations of each variable’s contribution to the prediction. Results: The prediction at initial diagnosis showed good agreement with the actual severity outcomes (AUC of 0.717 for predicting hospitalization/severity ≥2; 0.878 for severity ≥3; 0.951 for severity ≥4; 0.952 for severity ≥5; and 0.970 for death/severity=6), although some cases exhibited discrepancies between the predicted and actual prognoses. The dynamic mortality risk assessment during hospitalization using the RSF achieved a test-set C-index of 0.941, an integrated Brier score of 0.315, and a mean time-dependent AUC of 0.936. This dynamic assessment was able to distinguish between dead and surviving patients as early as 1‐2 weeks before the outcome. Early in hospitalization, C-reactive protein was an important risk factor for mortality; during the middle period, peripheral oxygen saturation (SpO₂) gained importance; and immediately before death, platelets and β-D-glucan were the primary risk factors. Conclusions: Integrating static admission triage with daily, explainable RSF predictions enables early identification of patients with COVID-19 at high risk of deterioration. By surfacing phase-specific, actionable predictors, the framework supports timely interventions and more efficient resource allocation. Prospective, multicenter studies are warranted to validate its generalizability and clinical impact.