Research field
Artificial intelligence, computing, robotics, energy, and engineering.
An analysis of lung-cancer safety reports found positive myotoxicity reporting signals for nivolumab, pembrolizumab and atezolizumab, but not durvalumab. Fatal outcomes appeared in 20.1% of reports, while the database could not estimate incidence or prove causation.
Frontiers in pharmacology5 min read
A study of 139 Beijing adults found strong internal performance when machine-learning models separated phlegm-dampness and balanced constitutions, but larger validation is still needed.
Frontiers in endocrinology4 min read
A machine-learning model identified concurrent fear of movement in older patients after coronary procedures, with strong results in a time-separated test group but important limits on wider use.
Frontiers in medicine4 min read
Among 36 people completing three-month follow-up, robot-assisted gait training was associated with more frequent functional improvement than conventional rehabilitation, with the largest gap in those starting with the poorest gait.
Frontiers in rehabilitation sciences4 min read
A model built from six clinical measures performed better than three comparison methods in an internal test of 518 children with allergic rhinitis. The study found associations involving IgE, Vitamin D, BMI, sleep and screen time, but it did not show that any of these factors causes ADHD or that changing them would alter symptoms.
Frontiers in public health5 min read
In a retrospective study, LightGBM ranked in-hospital mortality risk in a held-out ICU cohort and an external database, but only 30.3% of external high-risk predictions were followed by death.
Frontiers in neurology5 min read
Among 768 young and middle-aged adults receiving maintenance hemodialysis, 40.23% were in paid work at survey time, and a random-forest model performed well in an independent group of 203 patients.
Frontiers in public health4 min read
Researchers compared machine-learning and Cox models for predicting recorded fasting-glucose-defined prediabetes in adults whose baseline glucose was normal. The selected model performed moderately in internal and hospital-based external testing, but the study did not test whether using it improves care.
Frontiers in endocrinology4 min read
Camera-based AI scoring closely matched consensus video review for total BESS scores and produced smaller discrepancies than real-time on-site manual scoring in 80 participants.
Sports Medicine - Open4 min read
The model was strongest on rhythm abnormalities and weaker on conduction and morphological conditions, with results varying across diagnoses and datasets.
Health information science and systems4 min read
Researchers found immune and tissue-related gene signals in separate datasets on disc degeneration and osteoporosis, but say the findings need larger, clinically matched human studies.
Frontiers in immunology5 min read
Researchers built a mobile system that reminds people to take medicines, collects short intake videos and uses artificial intelligence to classify what is happening. The model performed well on held-out test data, but the clinical pilot was small, short and uncontrolled.
Revista da Associacao Medica Brasileira (1992)5 min read
Survey data from eastern South Georgia show a marked decline in significant species pairings between 1991 and 2023, alongside major changes in the predator community.
Philosophical transactions of the Royal Society of London. Series B, Biological sciences4 min read
DMPP and ATU were associated with different physiological and molecular responses in a laboratory culture of Nitrososphaera viennensis, offering clues that the inhibitors may act through different pathways.
Environmental science & technology4 min read
A simulated waveform was associated with better OOK detection in the reported tests, but its effect on existing OFDM data varied with channel complexity and signal shape.
Ouakouak, B.E., Zegrar, S.E. and Arslan, H., 2025. CP-Aware OFDM-Based OOK Signaling. IEEE Wireless Communications Letters, 15, pp.935-9394 min read
A 30 TB GaussDB TPC-H test reported a composite score 40% above Hologres, alongside smaller tests of execution, networking, Bloom filters and memory use. The paper is an unaudited arXiv preprint.
Scientific publication4 min read
A conceptual framework proposes hybrid AI support for medication optimization under clinician oversight, but the paper reports no validation or real-world performance evidence.
International journal of clinical pharmacy3 min read
A field evaluation of a battery-operated fenugreek harvester reported high machine efficiency across tested settings, alongside calculated savings in harvesting cost and labor.
Scientific reports4 min read
A polymer-metal binder built around PVA-Cu led the reported comparisons in capacity, rate performance and reaction kinetics, while pouch-cell evidence remains limited.
Advanced science (Weinheim, Baden-Wurttemberg, Germany)5 min read
A laboratory comparison associates higher effective ALD doses with continuous MoS2 films and stronger piezoelectric output, while leaving the causal pathway unproven.
Advanced science (Weinheim, Baden-Wurttemberg, Germany)5 min read
APEW-Fed stayed 2.7 F1 points below a centralised baseline on the main ERP test while reporting 94% lower communication than FedAvg, but its formal privacy accounting and simulated attack tests answer different questions.
Scientific reports4 min read
A public EMG-IMU dataset produced near-99% benchmark accuracy for attention-enhanced models, while the test design limits what the scores say about unseen users and real-world use.
Scientific reports4 min read
A machine-learning model identified liver fibrosis more accurately than standard scoring tools in a validation group of people previously infected with Schistosoma japonicum. The result is promising, but the study was cross-sectional and drew on one province in China, so it does not yet show that the model improves care or works elsewhere.
Infectious diseases of poverty4 min read
The models tracked measured exon inclusion well in some assays, but interpretable surrogates exposed sequence biases and missed structure-linked changes in selected variants.
Genome biology4 min read
A two-phase method called TP-MPPO posted the highest reward and higher simulated goodput than four benchmark algorithms. The work was based on synthetic wireless-edge simulations, so its practical reach remains tied to the modeled settings.
Scientific publication3 min read
SPALT combines local sensor patterns with a pruned linear model tree, and its overall accuracy advantage came with a smaller model rather than a faster one.
Machine Learning, Volume 114, article number 231 (2025)4 min read
A cloud-management framework reported lower average power use, fewer active servers and higher simulated profit than OP-PMF− across Google Cluster Data and PlanetLab traces.
IEEE Transactions on Services Computing 20244 min read
Simulation-based tests of REE-TM reported higher reliability and lower energy use than two reduced versions, while resource utilization was 1% to 4% below OPTIMAL.
IEEE Transactions on Cloud Computing 20253 min read
A qubit-based model reported lower prediction errors than several comparison methods across six benchmark workload traces, but the simulated study did not test live cloud operations.
IEEE Transactions on Systems, Man, and Cybernetics: Systems 20254 min read
A physics-based compact model reproduced measured electrical behavior in an analog ReRAM cell and found a simulated correspondence between pulsed and quasi-static equilibrium states.
Adv. Electron. Mater. 12, no. 7 (2026): e003734 min read
A CMO/HfOx analog ReRAM platform showed no tendency to drift under 100,000 half-voltage pulses in array tests, while its neural-network results came from software simulations rather than physical hardware training.
Adv. Sci. 13, no. 4 (2026): e045783 min read
A numerical study reports lower error scores for two data-driven reductions than for SAL in three simulated cases and than for OVB where it was available, alongside fewer listed variables.
Scientific publication4 min read
An exploratory study maps the language and ideas people use to make sense of AI, finding broad debates over development methods, the nature of AI systems and the pace of progress.
Scientific publication3 min read
A preprint reports that an adaptive odometry and sensor-fusion system maintained low reported errors in degraded robot tests, with cross-platform gains and online adaptation alongside unresolved calibration and generalization gaps.
Science Robotics 20254 min read
A new preprint presents a large dataset covering 18,635 educational institutions. Expert testing produced strong name-disambiguation scores, while benchmark checks were less complete for nested organizational relationships.
Liang, Z., Mao, J. & Li, G. A large-scale dataset of sub-institution name disambiguation and hierarchical structures from OpenAlex. Sci Data (2026)5 min read