AI Medical Compendium

How accurate are foundational machine learning interatomic potentials for heterogeneous catalysis?

The Journal of chemical physics May 21, 2026

Foundational machine-learning interatomic potentials (MLIPs) are being developed at a rapid pace, promising closer and closer approximation to ab initio accuracy. This unlocks the possibility to simulate much larger length and time scales. However, b... read more

Proximal Junctional Kyphosis Prevention in Adult Spinal Deformity Surgery: A Technical Review of Tethering and Adjunctive Strategies.

Operative neurosurgery (Hagerstown, Md.) May 21, 2026

BACKGROUND AND OBJECTIVES: Proximal junctional kyphosis (PJK) and proximal junctional failure (PJF) remain significant complications after long-segment posterior fusion for adult spinal deformity. Preventive strategies-including tethering, vertebral ... read more

Artificial Intelligence Algorithm to Monitor Inspiratory Muscle Effort and Patient-Ventilator Dyssynchrony During Mechanical Ventilation.

Critical care medicine May 21, 2026

OBJECTIVE: Current methods for estimating inspiratory muscle pressure (Pmus) during mechanical ventilation are either invasive or dependent on occlusion maneuvers. A noninvasive artificial intelligence (AI) algorithm estimating in real-time the ampli... read more

LFaB: Low Fidelity as Bias for Active Learning in the Chemical Configuration Space.

Journal of chemical theory and computation May 21, 2026

Active learning promises to provide an optimal training sample selection procedure in the construction of machine learning models. It often relies on minimizing the model's variance, which is assumed to decrease the prediction error. Still, it is fre... read more

ATBiGRU: an interpretable temporal model for in-hospital mortality prediction in acute kidney injury.

Computer methods in biomechanics and biomedical engineering May 21, 2026

Acute kidney injury (AKI) is associated with high mortality and healthcare burden, particularly in developing countries. Existing machine learning models mainly rely on static data and cannot effectively capture dynamic clinical features. We propose ... read more

THBS1: a biomarker for PCOS and its role in pathogenesis via the PI3K/AKT signaling pathway.

Mammalian genome : official journal of the International Mammalian Genome Society May 21, 2026

This study identified thrombospondin-1 (THBS1) as a potential biomarker for polycystic ovary syndrome (PCOS) and its pivotal role in disease pathogenesis through multi-level bioinformatics analysis and experimental validation. By integrating five PCO... read more

Training-set conditionally valid prediction sets with right-censored data.

Lifetime data analysis May 21, 2026

Uncertainty quantification of prediction models through prediction sets is increasingly popular and successful, but most existing methods rely on directly observing the outcome and do not appropriately handle censored outcomes, such as time-to-event ... read more

Integrating network pharmacology, molecular docking, machine learning, and experimental validation: puerarin improves sepsis-induced acute kidney injury via the Sirt1-Nrf2-HO-1 pathway.

Naunyn-Schmiedeberg's archives of pharmacology May 21, 2026

Acute kidney injury (AKI) associated with sepsis has a high clinical mortality rate, and there is a lack of effective therapeutic targets; uncontrolled oxidative stress and inflammatory responses are central pathological mechanisms. The Sirt1-Nrf2-HO... read more

Acquisition time/dose reduction in pediatric PET imaging using patch-based deep learning.

EJNMMI physics May 21, 2026

BACKGROUND: Deep learning (DL)-based denoising methods have shown promise for reducing radiation dose and/or acquisition time in pediatric PET imaging. However, conventional DL approaches typically require large and diverse training datasets to achie... read more

Noninvasive detection and prognostic stratification of biliary tract cancer using cell-free DNA fragmentomics: a model development and validation study.

Molecular biomedicine May 21, 2026

Biliary tract cancer (BTC) is typically diagnosed at an advanced stage due to the lack of effective screening tools, resulting in limited therapeutic options and poor survival outcomes. Therefore, there is a critical need for non-invasive strategies ... read more

Artificial Intelligence Medical Compendium