The objective of the article was to study the common requested radiographs and relative exposure dose in Qassim state in Kingdom of Saudi Arabia. The method was retrospective and analytical study for collected variables as radiographs, relative entrance surface dose (ESD) and the effective dose, patient age, gender and causative factors. The analysis with excel software revealed that: the common requested radiographs were skull, abdomen and chest with male incidence as 75%, 72.2% and 64% respectively relative to whole sample. Traffic accident (71%) and fall-down (45%) were the most causative factors among male and female respectively, with injuries as skull fissure fracture (77%) and intracranial hemorrhage (23%). The skull radiographs noted among the age group of 11-21 years and peaking at 36% among the age group of 22-32 years. The requested abdominal radiographs appeared among the age group of 13-21 years; with frequency of (19%) and peaking at 30% among the age group of 22-30 years; with injuries as spleen ruptures (42%) and liver (27%). The chest radiographs observed among age group of 3-13 years; with frequency of 4% and peaking among age groups of 14-24 & 25-35 years old with frequencies of 19% and 21% respectively, and injuries as Ribs fracture (55%), ribs dislocation (15%), pierced lung (20%) hemorrhage (10%). The average ESD for abdomen, skull and the chest radiographs were 1.93±0.8, 1.53±0.6 and 0.21±0.2 mGy which were increase linearly following the aging. And the average effective doses were 0.24±0.1, 0.1±0.1 and 0.4±0.2 mSv respectively.

Heart failure (HF) remains a major global cause of morbidity and mortality, where early diagnosis is critical for improving patient outcomes. Conventional single-modality approaches often fail to capture the complex and multifactorial nature of HF. This study investigates the feasibility of a late-fusion framework that integrates modality-specific predictions derived independently from cine-MRI, electrocardiographic signals, biomarkers and demographic data for HF prediction. Independent cine-MRI data from 281 patients, ECG recordings from the PTB-XL PhysioNet database and biomarker profiles from 157 patients were retrospectively analyzed as separate modality-specific cohorts. Twenty-five features were extracted and processed. Modality-specific models (Attention U-Net, MLP, XGBoost) were trained separately on pre-extracted features to preserve predictive accuracy while minimizing computational cost. Their outputs were combined through ensemble meta-learning (XGBoost, LightGBM, Random Forest) with sample weighting to handle missing data. The final HF prediction probability was obtained by averaging the outputs across the three meta-learners. The proposed framework achieved competitive diagnostic performance, with 98.00% (95% CI: 94.96–99.45%) accuracy, 97.80% (95% CI: 92.28–99.73%) sensitivity, 98.17% (95% CI: 93.53–99.78%) specificity, an F1-score of 97.80% (95% CI: 93.6–99.8%) and an AUC of 0.978 (95% CI: 0.945–0.996) when evaluated against state-of-the-art methods. The results highlight the potential of late-fusion strategies for integrating independently trained modality-specific predictions, offering a feasible approach for HF risk assessment under heterogeneous data availability.