Intelligence-based medicine最新文献

{"title":"NUC-Fuse: Multimodal medical image fusion using nuclear norm & classification of brain tumors using ARBFN","authors":"Shihabudeen H. ,&nbsp;Rajeesh J.","doi":"10.1016/j.ibmed.2024.100181","DOIUrl":"10.1016/j.ibmed.2024.100181","url":null,"abstract":"<div><div>Medical imaging has been widely used to diagnose diseases over the past two decades. The lack of information in this field makes it difficult for medical experts to diagnose diseases with a single modality. The combination of image fusion techniques enables the integration of pictures depicting various tissues and disorders from multiple medical imaging devices, facilitating enhanced research and treatment by providing complementary information through multimodal medical imaging fusion. The proposed work employs the nuclear norm and residual connections to combine the complementary features from both CT and MRI imaging approaches. The autoencoder eventually creates a merged image. The fused pictures are categorized as benign or malignant in the following phase using the present Radial Basis Function Network (RBFN). The performance measures, such as Mutual Information, Structural Similarity Index Measure, <span><math><msub><mrow><mi>Q</mi></mrow><mrow><mi>w</mi></mrow></msub></math></span>, and <span><math><msub><mrow><mi>Q</mi></mrow><mrow><mi>e</mi></mrow></msub></math></span>, have shown improved values, specifically 4.6328, 0.6492, 0.8300, and 0.8185 respectively, when compared with different fusion methods. Additionally, the classification algorithm yields 97% accuracy, 89% precision, and 92% recall when combined with the proposed fusion algorithm.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"10 ","pages":"Article 100181"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142578623","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The trend of artificial intelligence application in medicine and neurology; the state-of-the-art systematic scoping review 2010–2022","authors":"Mohammad Hossein Abbasi ,&nbsp;Melek Somai ,&nbsp;Hamidreza Saber","doi":"10.1016/j.ibmed.2024.100179","DOIUrl":"10.1016/j.ibmed.2024.100179","url":null,"abstract":"<div><h3>Background</h3><div>Artificial Intelligence (AI) is an increasingly popular research focus for multiple areas of science. The trend of using AI-based clinical research in different fields of medicine and defining the shortcomings of those trials will guide researchers and future studies.</div></div><div><h3>Methods</h3><div>We systematically reviewed trials registered in <span><span>ClinicalTrials.gov</span><svg><path></path></svg></span> that apply AI in clinical research. We explored the trend of AI-applied clinical research and described the design and conduct of such trials. Also, we considered high-quality trials to represent their enrollees’ and other characteristics.</div></div><div><h3>Results</h3><div>Our search yielded 839 trials involving a direct application of AI, among which 330 (39.3 %) trials were interventional, and the rest were observational (60.7 %). Most of the studies aimed to improve diagnosis (70.2 %); in less than a quarter of trials, management was targeted (22.8 %), and AI was implemented in an acute setting (13 %). Gastrointestinal, cardiovascular, and neurology were the significant fields of medicine with the application of AI in their research. High-quality published AI trials showed good generalizability in terms of their enrollees’ characteristics, with an average age of 52.46 years old and 50.28 % female participants.</div></div><div><h3>Conclusion</h3><div>The incorporation of AI in different fields of medicine needs to be more balanced, and attempts should be made to broaden the spectrum of AI-based clinical research and to improve its deployment in real-world practice.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"10 ","pages":"Article 100179"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142572059","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A conceptual IoT framework based on Anova-F feature selection for chronic kidney disease detection using deep learning approach","authors":"Md Morshed Ali,&nbsp;Md Saiful Islam,&nbsp;Mohammed Nasir Uddin,&nbsp;Md. Ashraf Uddin","doi":"10.1016/j.ibmed.2024.100170","DOIUrl":"10.1016/j.ibmed.2024.100170","url":null,"abstract":"<div><div>Chronic kidney disease (CKD) is becoming an increasingly significant health issue, especially in low-income countries where access to affordable treatment is limited. Additionally, CKD is associated with various dietary factors, including liver failure, diabetes, anemia, nerve damage, inflammation, peroxidation, obesity, and other related conditions. Therefore, early prediction of CKD is important to progress the functionality of the kidney. In recent times, IoT has been widely used in a diversity of healthcare sectors through the incorporation of monitoring devices such as digital sensors and medical devices for patient monitoring from remote places. To overcome the problem, this research proposed a conceptual architecture for CKD detection. The sensor layer of the architecture includes IoT devices to collect data and the proposed classifier, MLP (Multi-Layer Perceptron), utilizes the Anova-F feature selection technique to effectively detect CKD (Chronic Kidney Disease). In addition to MLP, four other classifiers including ANN (Artificial Neural Network), Simple RNN (Recurrent Neural Network), GRU (Gated Recurrent Unit), and SVM (Support Vector Machine), are employed for comparative analysis of accuracy. Furthermore, three additional feature selection techniques, namely Chi-squared, SFFS (Sequential Floating Forward Selection), and SBFS (Sequential Backward Floating Selection), are utilized to evaluate their impact on the accuracy of CKD detection. Our proposed method outperforms all other approaches with a remarkable accuracy of 99 % while maintaining efficient computational time. This advancement is crucial in developing a highly accurate machine capable of predicting CKD in remote areas with ease.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"10 ","pages":"Article 100170"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142532833","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A hybrid of supervised and unsupervised deep learning models for multi-vendor kernel conversion of chest CT images","authors":"Yujin Nam ,&nbsp;Jooae Choe ,&nbsp;Sang Min Lee ,&nbsp;Joon Beom Seo ,&nbsp;Hyunna Lee","doi":"10.1016/j.ibmed.2024.100169","DOIUrl":"10.1016/j.ibmed.2024.100169","url":null,"abstract":"<div><h3>Objective</h3><div>When reconstructing a computed tomography (CT) volume, different filter kernels can be used to highlight different structures depending on the medical purpose. The aim of this study was to perform CT conversion for intra-/inter-vendor kernel conversion while preserving image quality.</div></div><div><h3>Materials and methods</h3><div>This study used CT scans from 632 patients who underwent contrast-enhanced chest CT on either a GE or Siemens scanner. Raw data from each CT scan was reconstructed with Standard and Chest kernels of GE or B10f, B30f, B50f, and B70f kernels of Siemens. In intra-vendor, all images reconstructed with one kernel are paired with another kernel, so the U-Net based supervised method was applied. In the case of inter-vendor where the input and target kernels have each different vendor, Siemens' B30f and GE's Standard kernel were trained through unsupervised image-to-image translation using contrastive learning.</div></div><div><h3>Results</h3><div>In the intra-vendor, quantitative evaluation of the image quality of our model showed reasonable performance on the internal test set (structural similarity index measure (SSIM) &gt; 0.96, peak signal-to-noise ratio (PSNR) &gt; 42.55) compared with the SR-block model (SSIM &gt; 0.93, PSNR &gt; 42.92). In the 6-class classification to evaluate the inter-vendor conversion performance, similar accuracy was shown in the converted image (0.977) compared to the original image (0.998).</div></div><div><h3>Conclusions</h3><div>In this study, we developed a network that can translate a given CT image into a target kernel among multi-vendors. Our model showed clinically acceptable quality in quantitative and qualitative evaluations, including image quality metrics.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"10 ","pages":"Article 100169"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142446011","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine Learning-aided Computational Fragment-based Design of Small Molecules for Hypertension Treatment","authors":"Odifentse Mapula-e Lehasa,&nbsp;Uche A.K. Chude-Okonkwo","doi":"10.1016/j.ibmed.2024.100171","DOIUrl":"10.1016/j.ibmed.2024.100171","url":null,"abstract":"<div><div>With over 1 billion affected adults, hypertension is one of the most critical public health challenges worldwide. If left untreated over time, hypertension increases the likelihood of premature disability or death from cardiovascular diseases. Despite the range of medications available for the treatment of hypertension, many individuals do not respond positively to the treatment. Additionally, a significant percentage of the population does not take the medication as prescribed, which is sometimes attributed to intolerable side effects. Hence, there is still the need to develop new hypertension drugs that provide patients with favourable treatment outcomes. This paper explores the computational method of drug discovery to generate new lead drug molecules for hypertension by targeting the renin-angiotensin-aldosterone system (RAAS). Specifically, we proposed a framework that integrates computational fragment-based methods and an unsupervised machine learning technique to generate new lead Angiotensin-Converting Enzyme Inhibitor (ACEI) and Angiotensin-Receptor Blocker (ARB) molecules. The molecule generation process is initiated using all the approved agents acting on the RAAS that are available in the ChEMBL and DrugBank databases to create a fragment pool. The fragments are used to generate new molecules, which are categorised into ACEI and ARB clusters using unsupervised machine learning techniques. The generated molecules in each category are screened to determine their suitability as oral drug molecules, considering their physicochemical properties. Further screening is performed to determine the molecules’ suitability as ACEIs or ARBs, based on the presence of the appropriate functional groups and their similarities with existing drug molecules. The resultant molecules that passed screening are proposed as new lead antihypertensive agents. A synthesizability test is also performed on the final new lead molecules to determine the ease of making them compared to the original molecules.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"10 ","pages":"Article 100171"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142442513","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Heterogenous analysis of KeyBERT, BERTopic, PyCaret and LDAs methods: P53 in ovarian cancer use case","authors":"R.O. Oveh ,&nbsp;M. Adewunmi ,&nbsp;A.O. Solomon ,&nbsp;K.Y. Christopher ,&nbsp;P.N. Ezeobi","doi":"10.1016/j.ibmed.2024.100182","DOIUrl":"10.1016/j.ibmed.2024.100182","url":null,"abstract":"<div><div>In recent times, researchers with Computational background have found it easier to relate to Artificial Intelligence with the advancement of the transformer model, and unstructured medical data. This paper explores the heterogeneity of keyBERT, BERTopic, PyCaret and LDAs as key phrase generators and topic model extractors with P53 in ovarian cancer as a use case. PubMed abstract on mutant p53 was first extracted with the Entrez-global database and then preprocessed with Natural Toolkit (NLTK). keyBERT was then used for extracting keyphrases, and BERTopic modelling was used for extracting the related themes. PyCaret was further used for unigram topics and LDAs for examining the interaction among the topics in the word corpus. Lastly, Jaccard similarity index was used to check the similarity among the four methods. The results showed no relationship exists with KeyBERT, having a score of 0.0 while relationship exists among the three other topic models with score of 0.095, 0.235, 0.4 and 0.111. Based on the result, it was observed that keywords, keyphrases, similar topics, and entities embedded in the data use a closely related framework, which can give insights into medical data before modelling.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"10 ","pages":"Article 100182"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142662590","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cycle Generative Adversarial Aetwork approach for normalization of Gram-stain images for bacteria detection","authors":"V. Shwetha ,&nbsp;Keerthana Prasad ,&nbsp;Chiranjay Mukhopadhyay ,&nbsp;Barnini Banerjee","doi":"10.1016/j.ibmed.2024.100138","DOIUrl":"https://doi.org/10.1016/j.ibmed.2024.100138","url":null,"abstract":"<div><p>The Gram staining method is one of the most effective morphological identification procedures for detecting bacteria from direct smear microscopy. This staining process is inexpensive. It aids in diagnosing bacterial infections quickly as it is used for direct clinical sample specimens such as pus, urine, and sputum. The computer-aided diagnostic system aids the clinician by avoiding tedious manual evaluation procedures. However, images captured often suffer from contrast, illumination, and stain variations due to various camera settings and situations. These differences are due to image acquisition conditions, sample quality, and poor staining procedures. These variations affect the diagnosis process, lowering the image analysis performance of the computer-aided diagnosis system. In this context, the present work proposes a novel color normalization approach based on a Cycle Generative Adversarial Network(GAN). We introduce a novel normalization loss function, <em>L</em>_{<em>cycm</em>}, which is integrated into our dedicated normalization loss, <em>L</em>_<em>N</em>, within the framework of Cycle GAN(CGAN). The proposed method is compared with the state-of-the-art normalization algorithms qualitatively and quantitatively using the KMC dataset. In addition, the study demonstrates the impact of normalization on the Convolutional Neural Network (CNN) -based segmentation and classification process. Furthermore, a bacteria detection framework is proposed based on the U2Net segmentation model and a CNN classifier. The proposed normalization achieved an SSIM score of <strong>0.93 ± 0.07</strong> and PSNR of <strong>29 ± 3.7</strong>. The accuracy of the CNN-based classifier improved by 40 % after normalization.</p></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"9 ","pages":"Article 100138"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S266652122400005X/pdfft?md5=0d3ebedcc6a7f6f11414a2556ff844f2&pid=1-s2.0-S266652122400005X-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141291378","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cognitive behavioral therapy for chronic pain supported by digital patient feedback and artificial intelligence: Do patients with socioeconomic risk factors benefit?","authors":"John D. Piette ,&nbsp;Mary A. Driscoll ,&nbsp;Eugenia Buta ,&nbsp;Robert D. Kerns ,&nbsp;Alicia A. Heapy","doi":"10.1016/j.ibmed.2024.100164","DOIUrl":"10.1016/j.ibmed.2024.100164","url":null,"abstract":"<div><h3>Background</h3><p>In a recent comparative effectiveness trial, patients with chronic pain receiving cognitive behavioral therapy supported by artificial intelligence and digital feedback (AI-CBT-CP) were more likely to report clinically meaningful improvements in pain-related disability and intensity at six months than patients randomized to standard telephone CBT-CP. Concerns persist about the impact of AI and digital interventions among socially disadvantaged patients. We examined variation in the proportion of patients completing all treatment sessions and reporting clinically meaningful improvements in pain-related disability and intensity across subgroups of patients defined by social determinants of health (SDOH).</p></div><div><h3>Methods</h3><p>SDOH indicators included age, race, gender, education, income, marital status, geographic access, and clinical severity. Multivariate models with interaction terms tested SDOH indicators as potential moderators of treatment engagement and response to AI-CBT-CP versus standard telephone CBT-CP.</p></div><div><h3>Findings</h3><p>Roughly half of participants (52.9 %) were 65+ years of age, 10.8 % were women, and 19.1 % reported Black race or multiple racial identities. Relatively favorable session completion was observed among patients randomized to AI-CBT-CP across SDOH subgroup, with no groups more likely to complete all session weeks when receiving standard telephone CBT-CP. The relative benefits of AI-CBT-CP in terms of pain-related disability and intensity were generally confirmed across SDOH subgroups. AI-CBT-CP had a greater relative impact on pain-related disability among patients &lt;65 years old (p = .002). In none of the SDOH subgroups, did standard telephone CBT-CP have a greater impact on pain-related disability or intensity than AI-CBT-CP.</p></div><div><h3>Interpretation</h3><p>These findings do not suggest that patients with SDOH disadvantages experience poorer treatment engagement or outcomes when offered CBT-CP supported by AI and digital feedback instead of standard telephone CBT-CP. AI-CBT-CP can help overcome treatment access barriers without exacerbating disparities, benefiting underserved populations with chronic pain.</p></div><div><h3>Funding</h3><p>US Department of Veterans Affairs Health Services Research and Development program.</p></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"10 ","pages":"Article 100164"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666521224000310/pdfft?md5=5c1471fbfd9d71069624e91047fada5d&pid=1-s2.0-S2666521224000310-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142040143","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine-learning-enabled prognostic models for sepsis","authors":"Chunyan Li ,&nbsp;Lu Wang ,&nbsp;Kexun Li ,&nbsp;Hongfei Deng ,&nbsp;Yu Wang ,&nbsp;Li Chang ,&nbsp;Ping Zhou ,&nbsp;Jun Zeng ,&nbsp;Mingwei Sun ,&nbsp;Hua Jiang ,&nbsp;Qi Wang","doi":"10.1016/j.ibmed.2024.100167","DOIUrl":"10.1016/j.ibmed.2024.100167","url":null,"abstract":"<div><h3>Background and Objectives:</h3><div>Sepsis is a leading cause of mortality in intensive care units (ICUs). The development of a robust prognostic model utilizing patients’ clinical data could significantly enhance clinicians’ ability to make informed treatment decisions, potentially improving outcomes for septic patients. This study aims to create a novel machine-learning framework for constructing prognostic tools capable of predicting patient survival or mortality outcome.</div></div><div><h3>Methods:</h3><div>A novel dataset is created using concatenated triples of static data, temporal data, and clinical outcomes to expand data size. This structured input trains five machine learning classifiers (KNN, Logistic Regression, SVM, RF, and XGBoost) with advanced feature engineering. Models are evaluated on an independent cohort using AUROC and a new metric, <span><math><mi>γ</mi></math></span>, which incorporates the F1 score, to assess discriminative power and generalizability.</div></div><div><h3>Results:</h3><div>We developed five prognostic models using the concatenated triple dataset with 10 dynamic features from patient medical records. Our analysis shows that the Extreme Gradient Boosting (XGBoost) model (AUROC = 0.777, F1 score = 0.694) and the Random Forest (RF) model (AUROC = 0.769, F1 score = 0.647), when paired with an ensemble under-sampling strategy, outperform other models. The RF model improves AUROC by 6.66% and reduces overfitting by 54.96%, while the XGBoost model shows a 0.52% increase in AUROC and a 77.72% reduction in overfitting. These results highlight our framework’s ability to enhance predictive accuracy and generalizability, particularly in sepsis prognosis.</div></div><div><h3>Conclusion:</h3><div>This study presents a novel modeling framework for predicting treatment outcomes in septic patients, designed for small, imbalanced, and high-dimensional datasets. By using temporal feature encoding, advanced sampling, and dimension reduction techniques, our approach enhances standard classifier performance. The resulting models show improved accuracy with limited data, offering valuable prognostic tools for sepsis management. This framework demonstrates the potential of machine learning in small medical datasets.</div></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"10 ","pages":"Article 100167"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142578721","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Novel efficient feature selection: Classification of medical and immunotherapy treatments utilising Random Forest and Decision Trees","authors":"Ahsanullah Yunas Mahmoud","doi":"10.1016/j.ibmed.2024.100151","DOIUrl":"10.1016/j.ibmed.2024.100151","url":null,"abstract":"<div><p>Immunotherapy is an important topic in healthcare as it affects patients' treatments for breast cancer, diabetes, and immunotherapy. However, immunotherapy for warts is less representative because of the lack of data. Machine learning is frequently utilised for treatment diagnosis by converting raw immunotherapy data into useful insights. Efficient classification of immunotherapy treatments is crucial for a productive diagnosis. This study considers immunotherapy with a data-driven and ’less is more perspective’. Despite using a portion of the available imbalance and complex data, the process of diagnosis of immunotherapy treatment is made reasonably precise by considering the parameters of accuracy, sensitivity, and specificity. The contribution of this study is focused on ”more is less” feature selection, which states that approximately 80 % of the effects or results of a system are caused by 20 % of the inputs. The features that contribute most to the classification of immunotherapy treatments are prioritised. This study proposes the implementation of Random Forest and Decision Trees for the classification of immunotherapy treatments. The relevant experimental medical data are explored as a case study. The experiments are conducted using Weka and Python data analysis tools, performing data preprocessing, class balancing, and feature selection. Random Forest performed better than the Decision Trees. By Applying Random Forest and utilising only one feature (time) as an input variable, a classification accuracy of 88.88 %, sensitivity of 95.45 %, and specificity of 60 % are attained. By using 12.5 % of the dataset, when implementing Random Forest together with ordinary feature selection, the diagnosis of immunotherapy treatments is become more efficient, despite using a portion of data features reasonable results are obtained.</p></div>","PeriodicalId":73399,"journal":{"name":"Intelligence-based medicine","volume":"10 ","pages":"Article 100151"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666521224000188/pdfft?md5=e93dc97987b02f29f0f70f8ab813e2a6&pid=1-s2.0-S2666521224000188-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141708632","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}