The following is the summary of “Identification of discriminative neuroimaging markers for patients on hemodialysis with insomnia: a fractional amplitude of low-frequency fluctuation-based machine learning analysis” published in the January 2023 issue of Psychiatry by Wen, et al.

Sleep disturbances are widespread in the hemodialysis (HD) population, although the underlying causes are poorly understood. The study’s objectives were to use the fractional amplitude of low-frequency fluctuation (fALFF) method to detect the pattern of spontaneous brain activity in HD patients with insomnia (HDWI) and use the identification of brain regions showing altered fALFF as neural markers to distinguish HDWI patients from those on hemodialysis but without insomnia (HDWoI) and healthy controls (HCs). Researchers retrieved modified fALFF characteristics based on our comparison of 28 HDWI individuals, 28 HDWoI subjects, and 28 HCs, and used these results as the basis for a discriminative analysis.

Investigators then developed a support vector machine (SVM) classifier to isolate diagnostic neuroimaging indicators for HDWI. Both HDWI and HDWoI patients showed increased fALFF in the bilateral cerebellum, and right insula compared to HCs, and decreased fALFF in the bilateral calcarine (CAL), right middle occipital gyrus (MOG), left precentral gyrus (PreCG), bilateral postcentral gyrus (PoCG), and bilateral temporal middle gyrus (TMG). HDWI patients, in contrast to HDWoI patients, showed increased fALFF in the bilateral CAL/right MOG and decreased fALFF in the right cerebellum. 

Consensus brain areas with the biggest contributions to classification were located in the right MOG and the right cerebellum, and the SVM classification produced a strong performance [accuracy = 82.14%, area under the curve (AUC) =0.8202]. Their findings lend further credence to the pathogenic mechanism of HDWI by revealing that individuals with HDWI exhibited aberrant neural activity in the right medial orbitofrontal cortex (MOG) and right cerebellum.