A drug mix and dose decision algorithm for individualized type 2 diabetes management.

Pharmacotherapy guidelines for type 2 diabetes (T2D) emphasize patient-centered care, but applying this approach effectively in outpatient practice remains challenging. Data-driven treatment optimization approaches could enhance individualized T2D management, but current approaches cannot account for drug-specific and dose-dependent variations in safety and efficacy. We developed and evaluated an AI Drug mix and dose Advisor (AIDA) for glycemic management, using electronic medical records from 107,854 T2D patients in the SingHealth Diabetes Registry.

Towards More Efficient Data Valuation in Healthcare Federated Learning using Ensembling.

Federated Learning (FL) wherein multiple institutions collaboratively train a machine learning model without sharing data is becoming popular. Participating institutions might not contribute equally - some contribute more data, some better quality data or some more diverse data. To fairly rank the contribution of different institutions, Shapley value (SV) has emerged as the method of choice.

Cryptic asymptomatic parasellar high signal on time-of-flight MR angiography: how to resolve the clinical conundrum.

Purpose: Hyperintense parasellar signal on time-of-flight MR angiography (TOF-MRA) in asymptomatic patients may be due to a variety of nonpathological causes and mimic parasellar high flow signal in pathological arteriovenous shunts at the cavernous sinus (CSAVS). This creates a clinical conundrum between diagnosing an aggressive yet asymptomatic CSAVS subtype against exposing patients without CSAVS to potential complications of an invasive angiographic evaluation. We reviewed common nonpathological causes of hyperintense parasellar signal and contrast their imaging features against those of pathological CSAVS and proposed a systemic approach to resolve such conundrum.

Individual differences in physiologic measures are stable across repeated exposures to total sleep deprivation.

Some individuals show severe cognitive impairment when sleep deprived, whereas others are able to maintain a high level of performance. Such differences are stable and trait-like, but it is not clear whether these findings generalize to physiologic responses to sleep loss. Here, we analyzed individual differences in behavioral and physiologic measures in healthy ethnic-Chinese male volunteers (n = 12; aged 22-30 years) who were kept awake for at least 26 h in a controlled laboratory environment on two separate occasions.

Effects of exposure to intermittent versus continuous red light on human circadian rhythms, melatonin suppression, and pupillary constriction.

Exposure to light is a major determinant of sleep timing and hormonal rhythms. The role of retinal cones in regulating circadian physiology remains unclear, however, as most studies have used light exposures that also activate the photopigment melanopsin. Here, we tested the hypothesis that exposure to alternating red light and darkness can enhance circadian resetting responses in humans by repeatedly activating cone photoreceptors.

Melanopsin and rod-cone photoreceptors play different roles in mediating pupillary light responses during exposure to continuous light in humans.

In mammals, the pupillary light reflex is mediated by intrinsically photosensitive melanopsin-containing retinal ganglion cells that also receive input from rod-cone photoreceptors. To assess the relative contribution of melanopsin and rod-cone photoreceptors to the pupillary light reflex in humans, we compared pupillary light responses in normally sighted individuals (n = 24) with a blind individual lacking rod-cone function. Here, we show that visual photoreceptors are required for normal pupillary responses to continuous light exposure at low irradiance levels, and for sustained pupillary constriction during exposure to light in the long-wavelength portion of the visual spectrum.

Heart rate variability can be used to estimate sleepiness-related decrements in psychomotor vigilance during total sleep deprivation.

Study Objectives: To assess whether changes in psychomotor vigilance during sleep deprivation can be estimated using heart rate variability (HRV).

Design: HRV, ocular, and electroencephalogram (EEG) measures were compared for their ability to predict lapses on the Psychomotor Vigilance Task (PVT).

Setting: Chronobiology and Sleep Laboratory, Duke-NUS Graduate Medical School Singapore.