Cardiovascular medicine is inherently multimodal, but the data available at the clinical decision point are rarely as complete or as synchronized as benchmark evaluations assume. Recent reviews identify incomplete datasets, heterogeneous data characteristics, and missing modalities as persistent barriers to multimodal clinical AI. A correspondence published in Medicine Discovery argues that the central problem is not how to fuse more data, but how to reason when clinically relevant data are incomplete, temporally misaligned, or no longer representative of the patient's current state. The authors distinguish five linked but non-equivalent problems — conventional multimodal fusion, robustness to missing modalities, temporally aware modeling, uncertainty-aware selective prediction, and clinically informed interpretation of why a modality is unavailable — and treat modality availability as an observation state rather than a data defect. They define deferral operationally, separate it from calibration, uncertainty estimation, and distribution-shift detection, propose hybrid deferral rules that combine non-compensatory clinical hard stops with graded model-derived signals, and set out five candidate conditions for an intended-use-specific minimum evaluation suite. The framework is offered as a complement to existing clinical AI guidance (TRIPOD+AI, PROBAST+AI, FUTURE-AI, DECIDE-AI, CONSORT-AI, SPIRIT-AI) rather than a replacement, and as a conceptual proposal requiring prospective evaluation and multi-stakeholder consensus.

KAIST, Caltech, and Nanyang Technological University (NTU) in Singapore develop “BeetleBot,” a soft robot based on artificial muscles. The robot combines walking and object gripping with visual and tactile sensing, so users can steer it while checking camera images and contact information. In demonstrations, the robot avoided obstacles and picked up and carried a target object, which lays the groundwork for soft robots used in remote tasks.

Researchers have developed a new electrochemical sensor for rapidly and accurately detecting a naturally occurring compound widely used in the food, beverage and fragrance industries.

A team of researchers and engineers at Penn State is taking inspiration from the natural computer of the human brain to build soft networks of water-based droplets, connected by membranes like those found in the walls of living cells. 

For decades, physicists have sought a practical two-dimensional topological insulator: an ultrathin material whose interior blocks electricity but whose edges conduct it. In ordinary wires, electrons constantly bounce off imperfections, losing energy. But along the edges of a 2D topological insulator, electrons with opposite spins travel in opposite directions, like cars in one-way lanes, so they rarely scatter and lose energy. Now, researchers at the University of Chicago Pritzker School of Molecular Engineering (UChicago PME) have shown that ultrathin films of bismuth telluride are such a material. The work, published in ACS Nano, used a new approach to produce a uniform-thickness bismuth telluride film and confirm theoretical predictions about the material’s properties. 

Stanford researchers developed a flexible glycine-based piezoelectric material with improved stability for potential use in medical and environmental sensors.

A University of Tennessee professor of soil science is among the nine newest Fellows of the Soil Science Society of America (SSSA). Jie Zhuang, a professor in the Department of Biosystems Engineering and Soil Science within the UT Institute of Agriculture, will formally receive the honor November 3, during CANVAS 2026, an international meeting of multiple scientific communities involved in crop, agronomic, environmental and soil science research. 

A new study compares archived real-time and post-processed precise satellite products for multi-constellation, multi-frequency precise point positioning with ambiguity resolution (PPP-AR).