experimental-protocols-for-developing-validating-explainable-ai

Experimental Protocols for Developing and Validating Explainable AI Models in Secure Healthcare Diagnostics

Artificial Intelligence (AI) has drastically enhanced healthcare diagnostics with automated disease detection, predictive analytics, and intelligent ...

Symbiosis International (Deemed University)

In recent years, there has been an increase in the interest in adopting Explainable Artificial Intelligence (XAI) for healthcare. The proposed system includes•An XAI model for cancer drug value prediction. The model provides data that is easy to understand and explain, which is critical for medical decision-making. It also produces accurate projections.•A model outperformed existing models due to extensive training and evaluation on a large cancer medication chemical compounds dataset.•Insights into the causation and correlation between the dependent and independent actors in the chemical composition of the cancer cell. While the model is evaluated on Lung Cancer data, the architecture offered in the proposed solution is cancer agnostic. It may be scaled out to other cancer cell data if the properties are similar. The work presents a viable route for customizing treatments and improving patient outcomes in oncology by combining XAI with a large dataset. This research attempts to create a framework where a user can upload a test case and receive forecasts with explanations, all in a portable PDF report.

An explainable AI-assisted web application in cancer drug value prediction.

With the medical condition of pneumothorax, also known as collapsed lung, air builds up in the pleural cavity and causes the lung to collapse. It is a critical disorder that needs to be identified and treated right as it can cause breathing difficulties, low blood oxygen levels, and, in extreme circumstances, death. Chest X-rays are frequently used to diagnose pneumothorax. Using the Mask R-CNN model and medical transfer learning, the proposed work offers•A novel method for pneumothorax segmentation from chest X-rays.•A method that takes advantage of the Mask R-CNN architecture's for object recognition and segmentation.•A modified model to address the issue of segmenting pneumothoraxes and then polish it using a sizable dataset of chest X-rays. The proposed method is tested against other pneumothorax segmentation techniques using a dataset of 'chest X-rays' with 'pneumothorax annotations. The test findings demonstrate that proposed method outperforms other cutting-edge techniques in terms of segmentation accuracy and speed. The proposed method could lead to better patient outcomes by increasing the precision and effectiveness of pneumothorax diagnosis and therapy. Proposed method also benefits other medical imaging activities by using the medical transfer learning approaches which increases the precision of computer-aided diagnosis and treatment planning.

Data mining approaches to pneumothorax detection: Integrating mask-RCNN and medical transfer learning techniques.

The accurate prediction of the host of influenza viruses is a significant challenge in bioinformatics, as it is crucial for understanding viral transmission dynamics and host-virus interactions. This research•Introduces a novel approach for predicting the host of influenza viruses by leveraging protein sequences.•Extraction of features, including sequence length, Amino Acid Composition (AAC), Dipeptide Composition (DPC), Tripeptide Composition (TPC), aromaticity, secondary structure fraction, and entropy from protein sequence.•Addresses the data imbalance and improves model generalization, the oversampling technique is applied for data augmentation. The prediction model employs a Deep Recurrent Neural Network (DRNN) optimized by Fractional Addax Optimization 34 Algorithm (FAOA), a hybrid of Addax Optimization Algorithm (AOA) and Fractional Concept (FC), designed to perform 35 influenza virus host prediction. The model's performance is evaluated using metrics, such as Matthews's Correlation 36 Coefficient (MCC), F1-Score, and Mean Squared Error (MSE). Experimental results demonstrate that the DRNN_FAOA 37 model significantly outperforms existing methods, achieving the highest MCC of 0.937, F1-Score of 0.917, and the 38 lowest MSE of 0.038. The proposed DRNN_FAOA model's ability to accurately predict influenza virus hosts suggests its 39 potential as a robust model in virus-host prediction.

Deep recurrent neural network with fractional addax optimization algorithm for influenza virus host prediction.

Improving soil health evaluation and crop output forecasting are essential for developing sustainable agricultural methods. By applying data-driven insights, farmers may optimize resources, increase productivity, and promote environmental sustainability. The intricacy of environmental conditions and the lack of access to trustworthy data make it difficult to anticipate crop yields and evaluate soil health accurately. The goal of this research is•to make sophisticated models for precise crop production forecasting and thorough evaluation of soil health,•to improve sustainability by optimize farming methods, and•to assist farmers in making well-informed decisions.Iterative Partitioning-Ensemble Filter (IP-EF) is a technique used for feature selection, enhancing model performance by iteratively partitioning data and refining feature subsets. Back-propagation Neural Network (BPNN) is an SL algorithm applied for predicting complex patterns, especially in crop yield and soil health assessments. Multi-Source Data Fusion-Geographical Information Systems (MSDF-GIS) combines diverse data sources with GIS to map and analyze spatial agricultural data, improving decision-making for sustainable farming practices. These methods collectively optimize prediction accuracy and resource management. The result shows that the suggested model significant improvement in precision, recall, and F1-Score for crop yield, reaching 93 %, 94 %, and 93 %, implemented using Python software. Future advancements may include real-time monitoring, integrating AI by IoT expedients for dynamic decision-making, and enhancing sustainability by minimizing water usage, fertilizers, and environmental impact in agriculture.

Enhancing prediction of crop yield and soil health assessment for sustainable agriculture using machine learning approach.

The study created a detailed database for apple quality inspection using a cost-effective, self-designed multi-spectral imaging system. The system was optimized to allow spectral information to be obtained in 8 discrete wavebands, which enabled non-destructive determination of such key fruit components as ripeness, sugar type and cultivar. Stringent environmental conditions were maintained during image acquisition for optimal measurement consistency and experimental repeatability. The detailed dataset encompasses 32,463 multi-spectral images across three distinct classification categories. For sweetness evaluation, 1620 images spanning Brix values from 10 % to 15 % were collected from five apple varieties. Ripeness evaluation includes 29,160 images documenting the complete maturation cycle over 18 days, while variety classification contains 1683 images from three distinct cultivars. Each image was captured under controlled lighting conditions using eight specific wavelengths, ensuring spectral consistency crucial for machine learning applications. These multi-spectral images were concatenated for grading by sweetness, ripeness, and variety, creating a processed dataset of concatenated images optimized for AppleNet processing. The concatenation process combines the eight wavelength channels into unified image representations suitable for deep learning applications. Sample collection included the picking of different apple cultivars at different physiological development phases of fruit from local orchards. Single specimens were imaged sequentially using a multi-spectral technique. Information on sugar content concentration ( % Brix), maturation phase classification and varietal identification was recorded according to standard laboratory procedure. The resulting annotated database includes such quantitative reference points, which can be used to train supervised learning classifiers in computational classification systems. The reuse value of the dataset covers a wide range of applications such as machine learning-based fruit quality evaluation, agricultural automation and food industry examination. This dataset of ours can be used by researchers to develop and test algorithms to classify apples and estimate their ripeness and the presence of diseases. Furthermore, the proposed multi-spectral imaging can be generalized to cover other fruits and agricultural products, extending the application of the method in smart agriculture. This dataset serves as a valuable resource for researchers in computer vision, machine learning, and agricultural technology, fostering advancements in non-destructive fruit quality evaluation methodologies.

Dataset of apples for grading by sweetness, ripeness and variety.

Mobile Edge Computing (MEC) is an advanced technology that has the ability to decentralize and transform the working functionality of phone networks. The MEC is implanted in the cell phone base stations. The available resources in the mobile applications are processed by the MEC. Yet, the user experience and Quality of Service (QoS) are affected by the problem of inevitable optimization. A practical and efficient option to transfer workloads is MEC servers that are equipped with tiny or large base stations. By shifting the tasks from mobile devices to edge servers, MEC can provide low-latency computing services and high throughput. This research work aims at scheduling security-critical workflow tasks in the MEC environment that significantly improves the computing power of the devices by scheduling the service workflows from computing mobile devices to the edges of the mobile network. The major objective to be considered during the scheduling of critical tasks is the minimization of workflow execution time and total energy consumption. The major contributions of the recommended security-critical tasks scheduling approach in resource-limited MEC are listed here.•••

An efficient framework for scheduling security-critical tasks in resource-limited mobile edge computing using hybridized gold rush with golden jackal optimization strategy.

Article	Year
An explainable AI-assisted web application in cancer drug value prediction. MethodsX\| PubMed ID: 38633421	2024
Data mining approaches to pneumothorax detection: Integrating mask-RCNN and medical transfer learning techniques. MethodsX\| PubMed ID: 38638453	2024
Deep recurrent neural network with fractional addax optimization algorithm for influenza virus host prediction. MethodsX\| PubMed ID: 40292191	2025
Enhancing prediction of crop yield and soil health assessment for sustainable agriculture using machine learning approach. MethodsX\| PubMed ID: 40534600	2025
Dataset of apples for grading by sweetness, ripeness and variety. Data in brief\| PubMed ID: 40718145	2025
An efficient framework for scheduling security-critical tasks in resource-limited mobile edge computing using hybridized gold rush with golden jackal optimization strategy. MethodsX\| PubMed ID: 41362665	2025

Sonali Kothari

Biography

JoVE Journal Publications

Other Publications