Artificial intelligence is being studied across the stroke care pathway, but evidence from acute diagnosis, early prognosis, rehabilitation-outcome prediction, and long-term management is often discussed without clearly separating these clinical tasks. This structured narrative review adds an integrated framework that maps each application to its decision point, relevance to rehabilitation, validation level, and readiness for clinical use. Unlike previous technology-centered reviews, it explicitly separates acute prognostic evidence from rehabilitation-specific evidence and distinguishes technical performance from transportability, clinical impact, and rehabilitation benefit. Acute imaging and prognostic models may provide baseline information for later rehabilitation planning, but their diagnostic or prognostic performance does not establish rehabilitation efficacy. Most rehabilitation models and robotic, virtual-reality, brain–computer interface, wearable, and home-monitoring applications remain supported mainly by internal validation or early exploratory studies. Small or selected datasets, limited external and prospective validation, uncertain workflow effects, and sparse patient-centered outcomes continue to constrain clinical interpretation.
Multimorbidity is strongly associated with mortality, but existing comorbidity indices often generalize poorly across populations because they depend on fixed disease lists and context-specific weights. We developed the large-language-model-based multimorbidity score (LLM-MMS), a prompt-based large-language-model-derived multimorbidity phenotype score, as a bio-inspired artificial intelligence score for human–machine clinical risk stratification and evaluated it for all-cause mortality prediction in 770,439 adults from 9 international longitudinal cohorts. Harmonized participant-level data were converted into standardized health narratives and processed without model fine-tuning. In the UK Biobank, LLM-MMS achieved strong discrimination, calibration, and prediction accuracy. Across 8 external cohorts, it maintained consistent performance, with C-indices of 0.67 to 0.86 and observed-to-expected ratios close to 1.00. This outperformed recalibrated conventional comorbidity indices in every cohort with absolute C-index gains of 0.12 to 0.21. Performance remained stable across sex and age subgroups, including adults younger than 60 years, and decision-curve analysis showed greater or comparable clinical net benefit in most cohorts. Proteomic and interpretability analyses supported the biological plausibility of LLM-MMS, linking high multimorbidity burden to inflammatory, metabolic, and tissue-damage pathways and identifying clinically coherent drivers of risk. These findings suggest that LLM-MMS offers a transportable and interpretable bio-inspired framework that integrates clinician-like multimodal reasoning with population-level validation for multimorbidity risk stratification across diverse populations.
Irreversible electroporation is a promising nonthermal ablation for gastric mucosa, but nonconformal contact between the electrode and the rough surface of the gastric mucosa causes an inhomogeneous distribution of the high-voltage electric field. Here, we enhanced gap filling and substantially reduced distortion of the delivered high-voltage electric field by fabricating a soft, highly conductive sintered silver hydrogel as the bioelectronic tissue interface, thereby achieving uniform and complete irreversible electroporation. The sintering reaction was initiated by Cl− and H+, which can work synergistically to partially eliminate the insulating surfactant on silver flakes, facilitating a sintering reaction through the dynamic redeposition of silver nanoparticles on silver flakes. Via a room-temperature sintering process, the conductivity of the hydrogel was promoted from below 1 to >104 S/m at a low silver flake loading (4 vol%), and the mechanical property was still kept at a low Young’s modulus (91 kPa), even after swelling from digestive juices. In vitro experiments demonstrated that ablation uniformity improved by up to 86%, with the ablation area increasing by 30% to 52% and a maximum depth of 5.39 mm. Preclinical validation using porcine models demonstrated uniform, complete gastric mucosal ablation, reaching a depth of 2.50 mm, extending through the muscularis mucosae and leaving no residual cells. This sintered silver hydrogel-enhanced irreversible electroporation addresses key challenges and reinforces its potential as a reliable, advanced treatment for gastrointestinal lesions.
Axial dissections of the thoracic artery are common causes of death in people diagnosed with aortic dissection; however, decisions to intervene on ascending thoracic aortic patients are determined by the size of the ascending thoracic aorta based on its diameter. Diameter-based criteria fail to take into consideration the biomechanical properties of the aorta as well as other characteristics of the patient, and finite element analysis (in determining aortic wall stresses) would ideally address the issues associated with today’s diameter-based criteria. A novel computational solution, termed BioPINN-LM, integrates 2 computational methods for the rapid real-time prediction of aortic wall stress: a physics-informed neural network (PINN) trained with mechanical simulation data to predict wall stress and a multimodal large language model that uses output data from the PINN along with image-based geometry descriptors to provide interpretable risk assessments from both ends of the aorta. Comparison of the PINN to the reference database of finite element method results demonstrates that the PINN produces an average wall stress prediction error of 8.34 kPa (6.12% relative error) for a blood pressure of 120/80 mmHg, with an average prediction time of 0.83 s per geometry compared to 38.6 min for the traditional finite element method. The conversational component of BioPINN-LM achieves 87.4% agreement with board-certified specialist recommendations on a benchmark of 200 simulated clinical scenario vignettes. As a simulation-based proof of concept, these results suggest that integrating mechanistic simulations with language-based inquiry may complement biomechanical decision-making for ascending thoracic aortic aneurysms; clinical validation on real patient cohorts with longitudinal outcomes is deferred to future work.
