Search

Abstract Early diagnosis of breast cancer is exceptionally important in signifying the treatment results, of women’s health. The present study outlines a novel approach for analyzing breast cancer data by using the CatBoost classification model with a multi-layer perceptron neural network (CatBoost+MLP). Explainable artificial intelligence techniques are used to cohere with the proposed CatBoost with the MLP model. The proposed model aims to enhance the interpretability of predictions in breast cancer diagnosis by leveraging the benefits of CatBoost classification technique in feature identification and also contributing towards the interpretability of the decision model. The proposed CatBoost+MLP has been evaluated using the Shapley additive explanations values to analyze the feature significance in decision-making. Initially, the feature engineering is done using the analysis of variance technique to identify the significant features. The MLP model alone and the CatBoost+MLP model are being analyzed using divergent performance metrics, and the results obtained are compared with contemporary breast cancer identification techniques.

Abstract Cancer detection poses a significant challenge for researchers and clinical experts due to its status as the leading cause of global mortality. Early detection is crucial, but traditional cancer detection methods often rely on invasive procedures and time-consuming analyses, creating a demand for more efficient and accurate solutions. This paper addresses these challenges by utilizing automated cancer detection through AI-based techniques, specifically focusing on deep learning models. Convolutional Neural Networks (CNNs), including DenseNet121, DenseNet201, Xception, InceptionV3, MobileNetV2, NASNetLarge, NASNetMobile, InceptionResNetV2, VGG19, and ResNet152V2, are evaluated on image datasets for seven types of cancer: brain, oral, breast, kidney, Acute Lymphocytic Leukemia, lung and colon, and cervical cancer. Initially, images undergo segmentation techniques, proceeded by contour feature extraction where parameters such as perimeter, area, and epsilon are computed. The models are rigorously evaluated, with DenseNet121 achieving the highest validation accuracy as 99.94%, 0.0017 as loss, and the lowest Root Mean Square Error (RMSE) values as 0.036056 for training and 0.045826 for validation. These results revealed the capability of AI-based techniques in improving cancer detection accuracy, with DenseNet121 emerging as the most effective model in this study.

Abstract Background Bouveret syndrome is a rare etiology of gastric outlet obstruction, presenting with clinical manifestations that resemble those of several gastric pathologies. Timely diagnosis is imperative to mitigate potentially fatal consequences associated with this condition. Case presentation This case report involves a male patient, aged 35, who exhibited symptoms of intense abdominal discomfort, nausea, and vomiting over a 24-h period. The individual experienced identical symptoms of lesser intensity on three separate occasions throughout the preceding 4-month period, during which they resorted to analgesic medication for temporary relief. A contrast-enhanced computed tomography (CT) scan of the abdomen was performed, which identified the presence of the Rigler triad, characterized by pneumobilia, a cholecysto-antral fistula, and an ectopic gallstone lodged in the gastric antrum resulting in an obstruction. The patient’s diagnosis of Bouveret syndrome was determined based on the imaging findings. A surgical procedure known as cholecystectomy was conducted, which confirmed the existence of the sizable cholecystoduodenal fistula that was previously detected in the computed tomography (CT) scan. The surgical procedures that were conducted included a partial duodenectomy, a gastrojejunostomy, a cholecystectomy, and a common bile duct exploration with the removal of common bile duct stones. After examining the bile duct, a t-tube was inserted into the bile duct. Conclusion This case demonstrates a distinctive occurrence of a condition in a young man, typically observed in elderly females. There is a lack of established treatment guidelines for this particular entity. The appropriate course of action depends on various factors, including the patient’s condition, CT scan results, medical history, presence of co-existing illnesses, and intraoperative circumstances. These considerations are taken into account when determining whether a single-step surgical strategy or a multi-step approach should be pursued in order to minimize complications in patients. In this case, due to favorable conditions, a single-step approach was taken that yielded promising results.

Abstract In recent years, the growth spurt of medical imaging data has led to the development of various machine learning algorithms for various healthcare applications. The MedMNISTv2 dataset, a comprehensive benchmark for 2D biomedical image classification, encompasses diverse medical imaging modalities such as Fundus Camera, Breast Ultrasound, Colon Pathology, Blood Cell Microscope etc. Highly accurate classifications performed on these datasets is crucial for identification of various diseases and determining the course of treatment. This research paper presents a comprehensive analysis of four subsets within the MedMNISTv2 dataset: BloodMNIST, BreastMNIST, PathMNIST and RetinaMNIST. Each of these selected datasets is of diverse data modalities and comes with various sample sizes, and have been selected to analyze the efficiency of the model against diverse data modalities. The study explores the idea of assessing the Vision Transformer Model’s ability to capture intricate patterns and features crucial for these medical image classification and thereby transcend the benchmark metrics substantially. The methodology includes pre-processing the input images which is followed by training the ViT-base-patch16-224 model on the mentioned datasets. The performance of the model is assessed using key metrices and by comparing the classification accuracies achieved with the benchmark accuracies. With the assistance of ViT, the new benchmarks achieved for BloodMNIST, BreastMNIST, PathMNIST and RetinaMNIST are 97.90%, 90.38%, 94.62% and 57%, respectively. The study highlights the promise of Vision transformer models in medical image analysis, preparing the way for their adoption and further exploration in healthcare applications, aiming to enhance diagnostic accuracy and assist medical professionals in clinical decision-making.

The precise classification of medical images is crucial in various healthcare applications, especially in fields like disease diagnosis and treatment planning. In recent times, machine-intelligent models are desired to work in remote settings. However, the potential privacy concerns that arise from sharing confidential patient information to train traditional centralized machine learning models cannot be ignored. Federated learning (FL) offers a promising method for collaborative training on distributed data held by various entities, ensuring the privacy of patient information. This study evaluated the efficiency of the pre-trained models in the FL environment for medical image classification. The Convolutional Neural Network (CNN) model with Gray-Level Co-occurrence Matrix (GLCM) and Local Binary Patterns (LBP), along with the EfficientNet model, are being used as the local models. The trainable parameters from the local models are fed as input for building the global model. Pre-trained models trained on extensive datasets, possess valuable characteristics that can be utilized by FL models trained on proprietary datasets. Implementing this method can improve the efficacy and precision of FL models while also ensuring data confidentiality. The proposed model is evaluated using two distinct medical imaging datasets: Magnetic Resonance Image(MRI) and Computed Tomography (CT) scan images. The research highlights the advantages of utilizing pre-trained models in federated learning for medical image classification (MIC). The model’s performance is assessed across several assessment criteria, demonstrating the model exhibited a satisfactory accuracy rate of 97.4% and 98.8% for MRI and CT scan images, respectively. The model is evaluated concerning to Diagnostic Odds Ratio (DOR), where the proposed global model has exhibited 1164.54 for the MRI images and 6825.17 for CT scan images, and the values have outperformed the pretrained model.

IntroductionThe rapid advancement of science and technology has significantly expanded the capabilities of artificial intelligence, enhancing diagnostic accuracy for gastric cancer.MethodsThis research aims to utilize endoscopic images to identify various gastric disorders using an advanced Convolutional Neural Network (CNN) model. The Kvasir dataset, comprising images of normal Z-line, normal pylorus, ulcerative colitis, stool, and polyps, was used. Images were pre-processed and graphically analyzed to understand pixel intensity patterns, followed by feature extraction using adaptive thresholding and contour analysis for morphological values. Five deep transfer learning models—NASNetMobile, EfficientNetB5, EfficientNetB6, InceptionV3, DenseNet169—and a hybrid model combining EfficientNetB6 and DenseNet169 were evaluated using various performance metrics.Results & discussionFor the complete images of gastric cancer, EfficientNetB6 computed the top performance with 99.88% accuracy on a loss of 0.049. Additionally, InceptionV3 achieved the highest testing accuracy of 97.94% for detecting normal pylorus, while EfficientNetB6 excelled in detecting ulcerative colitis and normal Z-line with accuracies of 98.8% and 97.85%, respectively. EfficientNetB5 performed best for polyps and stool with accuracies of 98.40% and 96.86%, respectively.The study demonstrates that deep transfer learning techniques can effectively predict and classify different types of gastric cancer at early stages, aiding experts in diagnosis and detection.

Abstract Identifying and recognizing the food on the basis of its eating sounds is a challenging task, as it plays an important role in avoiding allergic foods, providing dietary preferences to people who are restricted to a particular diet, showcasing its cultural significance, etc. In this research paper, the aim is to design a novel methodology that helps to identify food items by analyzing their eating sounds using various deep learning models. To achieve this objective, a system has been proposed that extracts meaningful features from food-eating sounds with the help of signal processing techniques and deep learning models for classifying them into their respective food classes. Initially, 1200 audio files for 20 food items labeled have been collected and visualized to find relationships between the sound files of different food items. Later, to extract meaningful features, various techniques such as spectrograms, spectral rolloff, spectral bandwidth, and mel-frequency cepstral coefficients are used for the cleaning of audio files as well as to capture the unique characteristics of different food items. In the next phase, various deep learning models like GRU, LSTM, InceptionResNetV2, and the customized CNN model have been trained to learn spectral and temporal patterns in audio signals. Besides this, the models have also been hybridized i.e. Bidirectional LSTM + GRU and RNN + Bidirectional LSTM, and RNN + Bidirectional GRU to analyze their performance for the same labeled data in order to associate particular patterns of sound with their corresponding class of food item. During evaluation, the highest accuracy, precision,F1 score, and recall have been obtained by GRU with 99.28%, Bidirectional LSTM + GRU with 97.7% as well as 97.3%, and RNN + Bidirectional LSTM with 97.45%, respectively. The results of this study demonstrate that deep learning models have the potential to precisely identify foods on the basis of their sound by computing the best outcomes.

Abstract Parasitic organisms pose a major global health threat, mainly in regions that lack advanced medical facilities. Early and accurate detection of parasitic organisms is vital to saving lives. Deep learning models have uplifted the medical sector by providing promising results in diagnosing, detecting, and classifying diseases. This paper explores the role of deep learning techniques in detecting and classifying various parasitic organisms. The research works on a dataset consisting of 34,298 samples of parasites such as Toxoplasma Gondii, Trypanosome, Plasmodium, Leishmania, Babesia, and Trichomonad along with host cells like red blood cells and white blood cells. These images are initially converted from RGB to grayscale followed by the computation of morphological features such as perimeter, height, area, and width. Later, Otsu thresholding and watershed techniques are applied to differentiate foreground from background and create markers on the images for the identification of regions of interest. Deep transfer learning models such as VGG19, InceptionV3, ResNet50V2, ResNet152V2, EfficientNetB3, EfficientNetB0, MobileNetV2, Xception, DenseNet169, and a hybrid model, InceptionResNetV2, are employed. The parameters of these models are fine-tuned using three optimizers: SGD, RMSprop, and Adam. Experimental results reveal that when RMSprop is applied, VGG19, InceptionV3, and EfficientNetB0 achieve the highest accuracy of 99.1% with a loss of 0.09. Similarly, using the SGD optimizer, InceptionV3 performs exceptionally well, achieving the highest accuracy of 99.91% with a loss of 0.98. Finally, applying the Adam optimizer, InceptionResNetV2 excels, achieving the highest accuracy of 99.96% with a loss of 0.13, outperforming other optimizers. The findings of this research signify that using deep learning models coupled with image processing methods generates a highly accurate and efficient way to detect and classify parasitic organisms.

Abstract Background The most prevalent cyanotic congenital heart disease is Tetralogy of Fallot (TOF). It has a variety of presentations and is made up of four anatomic abnormalities. Documented literature shows an incidence of 13–20% of a right aortic arch with an anomalous left subclavian artery among individuals diagnosed with TOF. This is the first case that discusses the rare occurrence of overriding of the aortic arch along with the left aberrant subclavian artery and vertebral defect in a 3-week-old girl. Timely identification and management are pivotal in ensuring the best possible outcomes for these young patients. Case presentation A 3-week-old female child came with complaints of dyspnea, dysphagia, fatigue, and cyanosis on extreme crying, feeding, and moderate activity. Echocardiography revealed severe pulmonary stenosis with right ventricular dilatation and ventricular septal defect (VSD); a chest computed tomography was performed that revealed four characteristic features of TOF (pulmonary artery stenosis, VSD, right aortic root deviation, and concentric right ventricular hypertrophy) along with overriding of the aortic arch accompanied with the left aberrant subclavian artery (compressing the trachea and infundibulum) and vertebral defect (butterfly vertebra). Conclusions The case of this 3-week-old female infant emphasizes the importance of early and accurate diagnosis in congenital heart diseases, particularly when faced with complex presentations such as the TOF. It serves as a testament to the valuable role of advanced diagnostic imaging techniques in unraveling the complexity of congenital heart conditions.

Background: Psoriasis Vulgaris (PsV) is one of the most severe chronic, immune mediated skin diseases. The Notch signaling pathway, a key regulator for epidermal renewal, contributes in differentiation, proliferation and survival of keratinocytes. Alterations in the NOTCH4 gene disrupts Notch pathway. The current study aimed to find out the association of NOTCH4 gene polymorphism(s) in Pakistani psoriatic patients. Methods: A case control study, 390 DNA samples (190 samples of Psoriasis Vulgaris and 200 healthy control individuals), from January-December 2019, were selected from Rawalpindi Leprosy Hospital and healthy population, respectively. For amplification of (rs387071) SNP of NOTCH4 gene, lab standard protocols for T-ARMS-PCR were followed. Frequencies of genotype and allele were calculated by using Hardy Weinberg theorem. Data were analyzed by using SPSS and p-value ≤0.05 was considered statistically significant. Results: The mean age of patients was 34.6±14 while among control subjects it was 32.8±10.0. In cases, genotype homozygous A/A119 (62.6%) was more prevalent, followed by heterozygous A/G171 (90%) while homozygous G/G19 (10%) was the least prevalent between cases and controls. Allele A frequency in diseased subjects was 0.76 while, for controls it was 0.78. In addition, allele G frequency in patients and controls was 0.24 and 0.22 respectively. Based on Hardy Weinberg equilibrium, no association of (rs387071) NOTCH4 gene with psoriasis cases was found. Conclusion: NOTCH4 gene (rs387071) polymorphism was not significantly associated with patients of psoriasis Vulgaris in Pakistan. Larger studies are required to establish ethnic-specific markers for psoriasis in Pakistani population. Keywords: Psoriasis Vulgaris; PCR; NOTCH4; Polymorphism.

Dear Editor First identified in Wuhan, China, on December 31 2019, coronavirus spread like bush fire. The WHO declared it as a Global Pandemic on March 11 2021. COVID-19 was termed novel based on newly identified pathogens, thus leading to a state of uncertainty regarding treatment and prevention1. This virus can present with an array of symptoms; dry cough, breathlessness, chest pain, myalgia, and diarrhea2. Undergraduate medical education has shifted to virtual learning systems to halt the transmission of the virus. This letter elaborates on the challenges faced and the impact of COVID-19 on the life of undergraduate medical students.

Background: Even though organ transplants save thousands of lives globally, there exists a wide mismatch between an increasing demand for organ transplants and limited number of organ donors. The aim of the study was to assess the reasons and inspect differences between donors and non-donors in both students of medical and non-medical universities. Methods: A cross-sectional study was conducted over a period of 6 months (May 2018-March 2021). Sample of 400 participants enrolled from three medical colleges, two business/social sciences institutions and one engineering university of Karachi. Categorical variables were compared using the Chi-squared test. Continuous variables were compared using a student t-test. Variables with a univariate p-value ≤ 0.10 were included in multiple logistic regression models. Adjusted odds ratio (OR) with 95% confidence interval were reported. Results: With a very high response rate 383(96%) for knowledge about organ donation, a subdued response 201(52.3%) for willingness to donate. Most common source of knowledge regarding organ donation was social media 249(65%), followed by university 207(54%), family/friends 184(48%) and television 172(45%). Multiple logistic regression model identified being comfortable discussing organ donation as a positive predictor of willingness to donate (OR: 2.71, p=0.005), and the belief that organ donation disfigures the body as a negative predictor (OR: 0.40, p

The emergence of federated learning (FL) technique in fog-enabled healthcare system has leveraged enhanced privacy towards safeguarding sensitive patient information over heterogeneous computing platforms. In this paper, we introduce the FedHealthFog framework, which was meticulously developed to overcome the difficulties of distributed learning in resource-constrained IoT-enabled healthcare systems, particularly those sensitive to delays and energy efficiency. Conventional federated learning approaches face challenges stemming from substantial compute requirements and significant communication costs. This is primarily due to their reliance on a singular server for the aggregation of global data, which results in inefficient training models. We present a transformational approach to address these problems by elevating strategically placed fog nodes to the position of local aggregators within the federated learning architecture. A sophisticated greedy heuristic technique is used to optimize the choice of a fog node as the global aggregator in each communication cycle between edge devices and the cloud. The FedHealthFog system notably accounts for drop in communication latency of 87.01%, 26.90%, and 71.74%, and energy consumption of 57.98%, 34.36%, and 35.37% respectively, for three benchmark algorithms analyzed in this study. The effectiveness of FedHealthFog is strongly supported by outcomes of our experiments compared to cutting-edge alternatives while simultaneously reducing number of global aggregation cycles. These findings highlight FedHealthFog's potential to transform federated learning in resource-constrained IoT environments for delay-sensitive applications.

Malignant lymphoma, which impacts the lymphatic system, presents diverse challenges in accurate diagnosis due to its varied subtypes—chronic lymphocytic leukemia (CLL), follicular lymphoma (FL), and mantle cell lymphoma (MCL). Lymphoma is a form of cancer that begins in the lymphatic system, impacting lymphocytes, which are a specific type of white blood cell. This research addresses these challenges by proposing ensemble and non-ensemble transfer learning models employing pre-trained weights from VGG16, VGG19, DenseNet201, InceptionV3, and Xception. For the ensemble technique, this paper adopts a stack-based ensemble approach. It is a two-level classification approach and best suited for accuracy improvement. Testing on a multiclass dataset of CLL, FL, and MCL reveals exceptional diagnostic accuracy, with DenseNet201, InceptionV3, and Xception exceeding 90% accuracy. The proposed ensemble model, leveraging InceptionV3 and Xception, achieves an outstanding 99% accuracy over 300 epochs, surpassing previous prediction methods. This study demonstrates the feasibility and efficiency of the proposed approach, showcasing its potential in real-world medical applications for precise lymphoma diagnosis.

Economic policy uncertainty (EPU) may pose a risk or provide an opportunity for corporations. This study empirically investigates the impact of EPU on the corporate innovation of Chinese firms using patent information as a proxy for corporate innovation. The study then examines whether family ownership and political connections impede/boost corporate innovation. Using a longitudinal panel dataset of 3,085 Chinese firms listed during the period from 2009 to 2020, the study observes that EPU enhances corporate innovation in China. The study also finds that family firms negatively impact innovative projects during EPU. The study then shows that political connections positively moderate the effects of EPU on corporate innovation. The results of the study are robust to time and industry fixed effects, endogeneity issues, and firm-level time-varying factors. [ABSTRACT FROM AUTHOR]

Degree-based topological indices are very useful tools to model and characterize the molecular structure of drugs in order to predict their physicochemical properties without going into laborious and time-consuming laboratory experiments. These indices are numerical descriptors derived for the molecular structures using the principles of graph theory. Degree-based topological indices play a vital role in the QSPR analysis of heart attack drugs by providing molecular descriptors to predict their properties. The main goal of this paper is to compute six degree-based topological indices and a regression model for seven heart attack drugs. These drugs are nitroglycerin, clopidogrel, beta-blockers (metoprolol), ACE inhibitors (lisinopril), statins (atorvastatin), (ARBs) losartan, and beta-adrenergic blockers (propranolol). Regression analysis and degree-based indices correlate with various physicochemical properties related to drug activities, such as molecular weight, complexity, melting point, and boiling point. Correlations provide insights into how the molecular structure influences these properties, helping design and optimize new drugs. In the results, various statistical parameters are used to analyze heart attack drugs. [ABSTRACT FROM AUTHOR]

Introduction: The rapid advancement of science and technology has significantly expanded the capabilities of artificial intelligence, enhancing diagnostic accuracy for gastric cancer. Methods: This research aims to utilize endoscopic images to identify various gastric disorders using an advanced Convolutional Neural Network (CNN) model. The Kvasir dataset, comprising images of normal Z-line, normal pylorus, ulcerative colitis, stool, and polyps, was used. Images were pre-processed and graphically analyzed to understand pixel intensity patterns, followed by feature extraction using adaptive thresholding and contour analysis for morphological values. Five deep transfer learning models—NASNetMobile, EfficientNetB5, EfficientNetB6, InceptionV3, DenseNet169—and a hybrid model combining EfficientNetB6 and DenseNet169 were evaluated using various performance metrics. Results & discussion: For the complete images of gastric cancer, EfficientNetB6 computed the top performance with 99.88% accuracy on a loss of 0.049. Additionally, InceptionV3 achieved the highest testing accuracy of 97.94% for detecting normal pylorus, while EfficientNetB6 excelled in detecting ulcerative colitis and normal Z-line with accuracies of 98.8% and 97.85%, respectively. EfficientNetB5 performed best for polyps and stool with accuracies of 98.40% and 96.86%, respectively.The study demonstrates that deep transfer learning techniques can effectively predict and classify different types of gastric cancer at early stages, aiding experts in diagnosis and detection. [ABSTRACT FROM AUTHOR]

Caudal regression syndrome (CRS), also known as caudal agenesis, results from abnormal development of the caudal aspect of the spinal cord and vertebral column due to an earlier abnormality of gastrulation. This report showcases a unique scenario where three siblings, devoid of any prior family history or identifiable risk factors, exhibit symptoms of CRS and receive care at a government-run tertiary facility dedicated to children's health. In establishing a concrete diagnosis, we relied on skeletal surveys, comprehensive symptom evaluation, and medical history assessment. Additionally, we recommended further investigation through magnetic resonance imaging and genetic testing to attain a more in-depth understanding and confirmation of the condition. Unfortunately, the financial constraints faced by the parents led to the unfeasibility of pursuing these advanced diagnostic options. Given the rarity of this syndrome and the limited existing literature, our report is a significant contribution. It marks the first comprehensive exploration of CRS from the genetic and familial predisposition perspective, shedding new light on this rare condition. This case series pioneers our understanding of the familial and genetic connections between CRS and sacral agenesis. Strikingly, each subsequent generation has experienced more severe manifestations earlier, furnishing compelling evidence that underpins the genetic predisposition to CRS. [ABSTRACT FROM AUTHOR]

Fetal health care is vital in ensuring the health of pregnant women and the fetus. Regular check-ups need to be taken by the mother to determine the status of the fetus' growth and identify any potential problems. To know the status of the fetus, doctors monitor blood reports, Ultrasounds, cardiotocography (CTG) data, etc. Still, in this research, we have considered CTG data, which provides information on heart rate and uterine contractions during pregnancy. Several researchers have proposed various methods for classifying the status of fetus growth. Manual processing of CTG data is time-consuming and unreliable. So, automated tools should be used to classify fetal health. This study proposes a novel neural network-based architecture, the Dynamic Multi-Layer Perceptron model, evaluated from a single layer to several layers to classify fetal health. Various strategies were applied, including pre-processing data using techniques like Balancing, Scaling, Normalization hyperparameter tuning, batch normalization, early stopping, etc. to enhance the model's performance. A comparative analysis of the proposed method is done against the traditional machine learning models to showcase its accuracy (97%). An ablation study without any pre-processing techniques is also illustrated. This study easily provides valuable interpretations for healthcare professionals in the decision-making process. [ABSTRACT FROM AUTHOR]

Reverse degree-based topological indices (RDTIs) are applied to analyze the structural properties of molecules such as gamma graphyne and armchair graphyne nanoribbons. RDTIs provide valuable information about the connectivity patterns of atoms within a molecule, aiding in understanding its chemical and physical properties. For gamma graphyne and armchair graphyne nanoribbons, RDTIs would involve calculating the contributions from various atom pairs based on the degree differences between them. These indices consider the reverse order in which degrees are subtracted. RDTIs capture important aspects of molecular structure, including branching, degree distribution, and connectivity. Using RDTIs, one can assess the complexity, stability, and other characteristics of gamma graphyne and armchair graphyne nanoribbons. This paper focus on two structures made from hexagonal honeycomb graphite lattices, like gamma graphyne, and armchair graphyne nanoribbons. The methodology used in this study is First and second reverse Gourava indices, hyper first and second reverse Gourava indices, reverse multiplicative sum connectivity Gourava index, and reverse multiplicative product connectivity Gourava. Furthermore, these indices play a vital role in quantitative structure–property relationships and offer insights into the behaviour and reactivity of these unique molecular structures. Further research and computational analysis of RDTIs will deepen our understanding of these fascinating carbon-based materials. [ABSTRACT FROM AUTHOR]

Agriculture serves as the predominant driver of a country's economy, constituting the largest share of the nation's manpower. Most farmers are facing a problem in choosing the most appropriate crop that can yield better based on the environmental conditions and make profits for them. As a consequence of this, there will be a notable decline in their overall productivity. Precision agriculture has effectively resolved the issues encountered by farmers. Today's farmers may benefit from what's known as precision agriculture. This method takes into account local climate, soil type, and past crop yields to determine which varieties will provide the best results. The explainable artificial intelligence (XAI) technique is used with radial basis functions neural network and spider monkey optimization to classify suitable crops based on the underlying soil and environmental conditions. The XAI technology would provide assets in better transparency of the prediction model on deciding the most suitable crops for their farms, taking into account a variety of geographical and operational criteria. The proposed model is assessed using standard metrics like precision, recall, accuracy, and F1‐score. In contrast to other cutting‐edge approaches discussed in this study, the model has shown fair performance with approximately 12% better accuracy than the other models considered in the current study. Similarly, precision has improvised by 10%, recall by 11%, and F1‐score by 10%. [ABSTRACT FROM AUTHOR]