Pre-trained machine learning models have recently been widely used to detect COVID-19 automatically from X-ray images. Although these models can selectively retrain their layers for the desired task, the output remains biased due to the massive number of pre-trained weights and parameters. This paper proposes a novel batch normalized convolutional neural network (BNCNN) model to identify COVID-19 cases from chest X-ray images in binary and multi-class frameworks with a dual aim to extract salient features that improve model performance over pre-trained image analysis networks while reducing computational complexity. The BNCNN model has three phases: Data pre-processing to normalize and resize X-ray images, Feature extraction to generate feature maps, and Classification to predict labels based on the feature maps. Feature extraction uses four repetitions of a block comprising a convolution layer to learn suitable kernel weights for the features map, a batch normalization layer to solve the internal covariance shift of feature maps, and a max-pooling layer to find the highest-level patterns by increasing the convolution span. The classifier section uses two repetitions of a block comprising a dense layer to learn complex feature maps, a batch normalization layer to standardize internal feature maps, and a dropout layer to avoid overfitting while aiding the model generalization. Comparative analysis shows that when applied to an open-access dataset, the proposed BNCNN model performs better than four other comparative pre-trained models for three-way and two-way class datasets. Moreover, the BNCNN requires fewer parameters than the pre-trained models, suggesting better deployment suitability on low-resource devices.

Rapid diagnosis to test diseases, such as COVID-19, is a significant issue. It is a routine virus test in a reverse transcriptase-polymerase chain reaction. However, a test like this takes longer to complete because it follows the serial testing method, and there is a high chance of a false-negative ratio (FNR). Moreover, there arises a deficiency of R.T.–PCR test kits. Therefore, alternative procedures for a quick and accurate diagnosis of patients are urgently needed to deal with these pandemics. The infrared image is self-sufficient for detecting these diseases by measuring the temperature at the initial stage. C.T. scans and other pathological tests are valuable aspects of evaluating a patient with a suspected pandemic infection. However, a patient's radiological findings may not be identified initially. Therefore, we have included an Artificial Intelligence (A.I.) algorithm-based Machine Intelligence (MI) system in this proposal to combine C.T. scan findings with all other tests, symptoms, and history to quickly diagnose a patient with a positive symptom of current and future pandemic diseases. Initially, the system will collect information by an infrared camera of the patient's facial regions to measure temperature, keep it as a record, and complete further actions. We divided the face into eight classes and twelve regions for temperature measurement. A database named patient-info-mask is maintained. While collecting sample data, we incorporate a wireless network using a cloudlets server to make processing more accessible with minimal infrastructure. The system will use deep learning approaches. We propose convolution neural networks (CNN) to cross-verify the collected data. For better results, we incorporated tenfold cross-verification into the synthesis method. As a result, our new way of estimating became more accurate and efficient. We achieved 3.29% greater accuracy by incorporating the "decision tree level synthesis method" and "ten-folded-validation method". It proves the robustness of our proposed method.

Artificial intelligence (AI) is increasingly positioned as a transformative force in healthcare. The translation of AI from technical validation to real-world clinical impact remains a critical challenge. This systematic review aims to synthesize the evidence on the AI translational pathway in healthcare, focusing on the systemic barriers and facilitators to integration. Following PRISMA 2020 guidelines, we searched PubMed, Scopus, Web of Science, and IEEE Xplore for studies published between 2000 and 2025. We included peer-reviewed original research, clinical trials, observational studies, and reviews reporting on AI technical validation, clinical deployment, implementation outcomes, or ethical governance. While AI models consistently demonstrate high diagnostic accuracy (92–98% in radiology) and robust predictive performance (AUC 0.76–0.82 in readmission forecasting), clinical adoption remains limited, with only 15–25% of departments integrating AI tools and approximately 60% of projects failing beyond pilot testing. Key barriers include interoperability limitations affecting over half of implementations, lack of clinician trust in unsupervised systems (35%), and regulatory immaturity, with only 27% of countries establishing AI governance frameworks. Moreover, performance disparities exceeding 10% were identified in 28% of models, alongside a pronounced global divide, as 73% of low-resource health systems lack enabling infrastructure. These findings underscore the need for systemic, trustworthy, and equity-driven AI integration strategies.

The ability to detect facial landmarks is in high demand because of its usefulness in monitoring driver health in real time. Heat map-based approaches are well-known for their exact accuracy in landmark position prediction, tiny, and excellent-resolution networks may accomplish quick estimations. While tiny high-resolution networks (THRN) have been successful in connecting feature maps of varying resolutions, the fusion block’s costly computation remains an issue. Furthermore, THRN does not make use of the powerful output module seen in high-resolution networks. We propose an entirely novel design called THRN to address these issues. Using multi-resolution feature maps and an innovative fusion block, THRN Plus improves in two ways. First, it reduces the processing timing of its output module. On two different face landmark datasets, we ran extensive trials and showed that THRN greatly improved baseline techniques while keeping the latest in exactness at a cost to computation of roughly ten million FLOPS.