The COVID-19 pandemic has placed substantial pressure on intensive care units (ICUs), particularly in managing patients who require oxygen therapy and must be safely weaned from it. This study evaluated an HRV-guided respiratory biofeedback program as a non-pharmacological method to reduce respiratory discomfort and psychological distress during oxygen weaning in COVID-19 patients. A non-randomized quasi-experimental study was conducted with 80 ICU patients at Albehera Hospital, Beheira, Egypt. Patients were allocated to either a biofeedback group ([Formula: see text]) or a control group ([Formula: see text]). Both groups received standard oxygen-weaning care and routine nursing support, but only the biofeedback group received structured sessions combining diaphragmatic breathing with heart rate variability based respiratory training. The Respiratory Distress Observation Scale (RDOS) and the Depression Anxiety Stress Scale (DASS-21) were administered before and after the intervention. After adjusting for baseline scores, the biofeedback group demonstrated a markedly larger reduction in RDOS scores (from 14.48 to 4.23; [Formula: see text]) and significant improvements in DASS-21 depression, anxiety, and stress subscales ([Formula: see text]), whereas the control group showed only minimal changes. These findings suggest that HRV-guided respiratory biofeedback may enhance both respiratory comfort and psychological well-being during oxygen weaning in COVID-19 patients and could serve as a valuable adjunct to standard ICU care. Further randomized controlled trials are warranted to confirm these results and guide clinical implementation.
Computational prediction of ABL1 tyrosine-kinase inhibitor (TKI) resistance is difficult because available mutation-drug datasets are small, imbalanced, and heterogeneous. This study evaluates structure-aware resistance prediction under mutation-disjoint internal validation and temporal cross-study outcome validation. The development benchmark comprised 144 ABL1 mutation-TKI records (19 resistant and 125 susceptible) labelled by a ten-fold affinity-loss criterion. A fixed panel of 11 documented structural and energetic predictors was used to minimize data-adaptive feature selection within the validation framework. A calibrated ensemble combining Elastic-Net logistic regression, radial-basis-function support-vector machines, random forests, and XGBoost was evaluated using mutation-disjoint five-fold grouped out-of-fold prediction repeated ten times. Temporal validation used a later prime-editing resistance map, yielding 84 exact mutation-TKI matches across imatinib, nilotinib, bosutinib, and ponatinib; 61 had binary Sensitive/Resistant outcomes and 23 were retained as Intermediate. The 11-feature stack achieved grouped internal AUROC 0.645 (95% CI 0.429-0.830) and PR-AUC 0.230, with mean ± SD AUROC 0.583 ± 0.101 across repeated grouped splits. On the 61 binary later-study outcomes, AUROC was 0.605 (95% CI 0.431-0.874) and PR-AUC 0.835, modestly above the resistance-prevalence baseline of 0.770. External calibration was poor (Brier score 0.583; calibration slope 0.441). Elastic-Net showed somewhat higher temporal discrimination (AUROC 0.643; PR-AUC 0.877). These results indicate limited transportability across mutation identities and experimental platforms and support use of the framework for hypothesis-generating resistance screening rather than clinically calibrated treatment selection.