Sleep-wake rhythm disturbances and perceived sleep in adolescent chronic fatigue syndrome.

Chronic fatigue syndrome (CFS) is characterized by long-lasting, disabling and unexplained fatigue that is often accompanied by unrefreshing sleep. The aim of this cross-sectional study was to investigate sleep-wake rhythm and perceived sleep in adolescent CFS patients compared to healthy individuals. We analysed baseline data on 120 adolescent CFS patients and 39 healthy individuals included in the NorCAPITAL project. Activity measures from a uniaxial accelerometer (activPAL) were used to estimate mid-sleep time (mid-point of a period with sleep) and time in bed. Scores from the Karolinska Sleep Questionnaire (KSQ) were also assessed. The activity measures showed that the CFS patients stayed significantly longer in bed, had a significantly delayed mid-sleep time and a more varied sleep-wake rhythm during weekdays compared with healthy individuals. On the KSQ, the CFS patients reported significantly more insomnia symptoms, sleepiness, awakening problems and a longer sleep onset latency than healthy individuals. These results might indicate that disrupted sleep-wake phase could contribute to adolescent CFS; however, further investigations are warranted.

A Pragmatic Machine Learning Approach to Quantify Tumor-Infiltrating Lymphocytes in Whole Slide Images.

Increased levels of tumor-infiltrating lymphocytes (TILs) indicate favorable outcomes in many types of cancer. The manual quantification of immune cells is inaccurate and time-consuming for pathologists. Our aim is to leverage a computational solution to automatically quantify TILs in standard diagnostic hematoxylin and eosin-stained sections (H&E slides) from lung cancer patients. Our approach is to transfer an open-source machine learning method for the segmentation and classification of nuclei in H&E slides trained on public data to TIL quantification without manual labeling of the data. Our results show that the resulting TIL quantification correlates to the patient prognosis and compares favorably to the current state-of-the-art method for immune cell detection in non-small cell lung cancer (current standard CD8 cells in DAB-stained TMAs HR 0.34, 95% CI 0.17-0.68 vs. TILs in HE WSIs: HoVer-Net PanNuke Aug Model HR 0.30, 95% CI 0.15-0.60 and HoVer-Net MoNuSAC Aug model HR 0.27, 95% CI 0.14-0.53). Our approach bridges the gap between machine learning research, translational clinical research and clinical implementation. However, further validation is warranted before implementation in a clinical setting.