Computers in biology and medicine最新文献

{"title":"An adaptive enhanced human memory algorithm for multi-level image segmentation for pathological lung cancer images.","authors":"Mahmoud Abdel-Salam, Essam H Houssein, Marwa M Emam, Nagwan Abdel Samee, Mona M Jamjoom, Gang Hu","doi":"10.1016/j.compbiomed.2024.109272","DOIUrl":"10.1016/j.compbiomed.2024.109272","url":null,"abstract":"<p><p>Lung cancer is a critical health issue that demands swift and accurate diagnosis for effective treatment. In medical imaging, segmentation is crucial for identifying and isolating regions of interest, which is essential for precise diagnosis and treatment planning. Traditional metaheuristic-based segmentation methods often struggle with slow convergence speed, poor optimized thresholds results, balancing exploration and exploitation, leading to suboptimal performance in the multi-thresholding segmenting of lung cancer images. This study presents ASG-HMO, an enhanced variant of the Human Memory Optimization (HMO) algorithm, selected for its simplicity, versatility, and minimal parameters. Although HMO has never been applied to multi-thresholding image segmentation, its characteristics make it ideal to improve pathology lung cancer image segmentation. The ASG-HMO incorporating four innovative strategies that address key challenges in the segmentation process. Firstly, the enhanced adaptive mutualism phase is proposed to balance exploration and exploitation to accurately delineate tumor boundaries without getting trapped in suboptimal solutions. Second, the spiral motion strategy is utilized to adaptively refines segmentation solutions by focusing on both the overall lung structure and the intricate tumor details. Third, the gaussian mutation strategy introduces diversity in the search process, enabling the exploration of a broader range of segmentation thresholds to enhance the accuracy of segmented regions. Finally, the adaptive t-distribution disturbance strategy is proposed to help the algorithm avoid local optima and refine segmentation in later stages. The effectiveness of ASG-HMO is validated through rigorous testing on the IEEE CEC'17 and CEC'20 benchmark suites, followed by its application to multilevel thresholding segmentation in nine histopathology lung cancer images. In these experiments, six different segmentation thresholds were tested, and the algorithm was compared to several classical, recent, and advanced segmentation algorithms. In addition, the proposed ASG-HMO leverages 2D Renyi entropy and 2D histograms to enhance the precision of the segmentation process. Quantitative result analysis in pathological lung cancer segmentation showed that ASG-HMO achieved superior maximum Peak Signal-to-Noise Ratio (PSNR) of 31.924, Structural Similarity Index Measure (SSIM) of 0.919, Feature Similarity Index Measure (FSIM) of 0.990, and Probability Rand Index (PRI) of 0.924. These results indicate that ASG-HMO significantly outperforms existing algorithms in both convergence speed and segmentation accuracy. This demonstrates the robustness of ASG-HMO as a framework for precise segmentation of pathological lung cancer images, offering substantial potential for improving clinical diagnostic processes.</p>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"183 ","pages":"109272"},"PeriodicalIF":7.0,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142459858","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The efficient classification of breast cancer on low-power IoT devices: A study on genetically evolved U-Net.","authors":"Mohit Agarwal, Amit Kumar Dwivedi, Dibyanarayan Hazra, Preeti Sharma, Suneet Kumar Gupta, Deepak Garg","doi":"10.1016/j.compbiomed.2024.109296","DOIUrl":"10.1016/j.compbiomed.2024.109296","url":null,"abstract":"<p><p>Breast cancer is the most common cancer among women, and in some cases, it also affects men. Since early detection allows for proper treatment, automated data classification is essential. Although such classifications provide timely results, the resource requirements for such models, i.e., computation and storage, are high. As a result, these models are not suitable for resource-constrained devices (for example, IOT). In this work, we highlight the U-Net model, and to deploy it to IOT devices, we compress the same model using a genetic algorithm. We assess the proposed method using a publicly accessible, bench-marked dataset. To verify the efficacy of the suggested methodology, we conducted experiments on two more datasets, specifically CamVid and Potato leaf disease. In addition, we used the suggested method to shrink the MiniSegNet and FCN 32 models, which shows that the compressed U-Net approach works for classifying breast cancer. The results of the study indicate a significant decrease in the storage capacity of UNet with 96.12% compression for the breast cancer dataset with 1.97x enhancement in inference time. However, after compression of the model, there is a drop in accuracy of only 1.33%.</p>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"183 ","pages":"109296"},"PeriodicalIF":7.0,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142581370","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A conflict-free multi-modal fusion network with spatial reinforcement transformers for brain tumor segmentation.","authors":"Tianyun Hu, Hongqing Zhu, Ziying Wang, Ning Chen, Bingcang Huang, Weiping Lu, Ying Wang","doi":"10.1016/j.compbiomed.2024.109331","DOIUrl":"10.1016/j.compbiomed.2024.109331","url":null,"abstract":"<p><p>Brain gliomas are a leading cause of cancer mortality worldwide. Existing glioma segmentation approaches using multi-modal inputs often rely on a simplistic approach of stacking images from all modalities, disregarding modality-specific features that could optimize diagnostic outcomes. This paper introduces STE-Net, a spatial reinforcement hybrid Transformer-based tri-branch multi-modal evidential fusion network designed for conflict-free brain tumor segmentation. STE-Net features two independent encoder-decoder branches that process distinct modality sets, along with an additional branch that integrates features through a cross-modal channel-wise fusion (CMCF) module. The encoder employs a spatial reinforcement hybrid Transformer (SRHT), which combines a Swin Transformer block and a modified convolution block to capture richer spatial information. At the output level, a conflict-free evidential fusion mechanism (CEFM) is developed, leveraging the Dempster-Shafer (D-S) evidence theory and a conflict-solving strategy within a complex network framework. This mechanism ensures balanced reliability among the three output heads and mitigates potential conflicts. Each output is treated as a node in the complex network, and its importance is reassessed through the computation of direct and indirect weights to prevent potential mutual conflicts. We evaluate STE-Net on three public datasets: BraTS2018, BraTS2019, and BraTS2021. Both qualitative and quantitative results demonstrate that STE-Net outperforms several state-of-the-art methods. Statistical analysis further confirms the strong correlation between predicted tumors and ground truth. The code for this project is available at https://github.com/whotwin/STE-Net.</p>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"183 ","pages":"109331"},"PeriodicalIF":7.0,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142590258","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Simulation of hip bony range of motion (BROM) corresponds to the observed functional range of motion (FROM) for pure flexion, internal rotation in deep flexion, and external rotation in minimal flexion-extension - A cadaver study.","authors":"Arnab Palit, Mark A Williams, Ercihan Kiraci, Vineet Seemala, Vatsal Gupta, Jim Pierrepont, Christopher Plaskos, Richard King","doi":"10.1016/j.compbiomed.2024.109270","DOIUrl":"10.1016/j.compbiomed.2024.109270","url":null,"abstract":"<p><strong>Background: </strong>The study investigated the relationship between computed bony range of motion (BROM) and actual functional range of motion (FROM) as directly measured in cadaveric hips. The hypothesis was that some hip movements are not substantially restricted by soft tissues, and therefore, computed BROM for these movements may effectively represent FROM, providing a reliable parameter for computational pre-operative planning.</p><p><strong>Methods: </strong>Maximum passive FROM was measured in nine cadaveric hips using optical tracking. Each hip was measured in at least ninety FROM positions, covering flexion, extension, abduction, flexion-internal rotation (IR), flexion-external rotation (ER), extension-IR, and extension-ER movements. The measured FROM was virtually recreated using 3D models of the femur and pelvis derived from CT scans, and the corresponding BROM was computed. The relationship between FROM and BROM was classified into three groups: close (mean difference<5°), moderate (mean difference 5-15°), and weak (mean difference>15°).</p><p><strong>Results: </strong>The relationship between FROM and BROM was close for pure flexion (difference = 3.1° ± 3.9°) and IR in deep (>70°) flexion (difference = 4.3° ± 4.6°). The relationship was moderate for ER in minimal flexion (difference = 10.3° ± 5.8°) and ER in minimal extension (difference = 11.7° ± 7.2°). Bony impingement was observed in some cases during these movements. Other movements showed a weak relationship: large differences were observed in extension (51.9° ± 14.4°), abduction (18.6° ± 11.3°), flexion-IR at flexion<70° (37.1° ± 9.4°), extension-IR (79.6° ± 4.8°), flexion-ER at flexion>30° (45.9° ± 11.3°), and extension-ER at extension>20° (15.8° ± 4.8°).</p><p><strong>Conclusion: </strong>BROM simulations of hip flexion, IR in deep flexion, and ER in low flexion/extension may be useful in dynamic pre-operative planning of total hip arthroplasty.</p>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"183 ","pages":"109270"},"PeriodicalIF":7.0,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142590285","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The untapped potential of 3D virtualization using high resolution scanner-based and photogrammetry technologies for bone bank digital modeling.","authors":"Anuar Giménez-El-Amrani, Andres Sanz-Garcia, Néstor Villalba-Rojas, Vicente Mirabet, Alfonso Valverde-Navarro, Carmen Escobedo-Lucea","doi":"10.1016/j.compbiomed.2024.109340","DOIUrl":"10.1016/j.compbiomed.2024.109340","url":null,"abstract":"<p><p>Three-dimensional (3D) scanning technologies could transform medical practices by creating virtual tissue banks. In bone transplantation, new approaches are needed to provide surgeons with accurate tissue measurements while minimizing contamination risks and avoiding repeated freeze-thaw cycles of banked tissues. This study evaluates three prominent non-contact 3D scanning methods-structured light scanning (SLG), laser scanning (LAS), and photogrammetry (PHG)-to support tissue banking operations. We conducted a thorough examination of each technology and the precision of the 3D scanned bones using relevant anatomical specimens under sterile conditions. Cranial caps were scanned as separate inner and outer surfaces, automatically aligned, and merged with post-processing. A colorimetric analysis based on CIEDE2000 was performed, and the results were compared with questionnaires distributed among neurosurgeons. The findings indicate that certain 3D scanning methods were more appropriate for specific bones. Among the technologies, SLG emerged as optimal for tissue banking, offering a superior balance of accuracy, minimal distortion, cost-efficiency, and ease of use. All methods slightly underestimated the volume of the specimens in their virtual models. According to the colorimetric analysis and the questionnaires given to the neurosurgeons, our low-cost PHG system performed better than others in capturing cranial caps, although it exhibited the least dimensional accuracy. In conclusion, this study provides valuable insights for surgeons and tissue bank personnel in selecting the most efficient 3D non-contact scanning technology and optimizing protocols for modernized tissue banking. Future work will advance towards smart healthcare solutions, explore the development of virtual tissue banks.</p>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"183 ","pages":"109340"},"PeriodicalIF":7.0,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142590297","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Differences in brain spindle density during sleep between patients with and without type 2 diabetes.","authors":"Deryck Yeung, Amlan Talukder, Min Shi, David M Umbach, Yuanyuan Li, Alison Motsinger-Reif, Janice J Hwang, Zheng Fan, Leping Li","doi":"10.1016/j.compbiomed.2024.109484","DOIUrl":"https://doi.org/10.1016/j.compbiomed.2024.109484","url":null,"abstract":"<p><strong>Background: </strong>Sleep spindles may be implicated in sensing and regulation of peripheral glucose. Whether spindle density in patients with type 2 diabetes mellitus (T2DM) differs from that of healthy subjects is unknown.</p><p><strong>Methods: </strong>Our retrospective analysis of polysomnography (PSG) studies identified 952 patients with T2DM and 952 sex-, age- and BMI-matched control subjects. We extracted spindles from PSG electroencephalograms and used rank-based statistical methods to test for differences between subjects with and without diabetes. We also explored potential modifiers of spindle density differences. We replicated our analysis on independent data from the Sleep Heart Health Study.</p><p><strong>Results: </strong>We found that patients with T2DM exhibited about half the spindle density during sleep as matched controls (P < 0.0001). The replication dataset showed similar trends. The patient-minus-control paired difference in spindle density for pairs where the patient had major complications were larger than corresponding paired differences in pairs where the patient lacked major complications, despite both patient groups having significantly lower spindle density compared to their respective control subjects. Patients with a prescription for a glucagon-like peptide 1 receptor agonist had significantly higher spindle density than those without one (P ≤ 0.03). Spindle density in patients with T2DM monotonically decreased as their highest recorded HbA1C level increased (P ≤ 0.003).</p><p><strong>Conclusions: </strong>T2DM patients had significantly lower spindle density than control subjects; the size of that difference was correlated with markers of disease severity (complications and glycemic control). These findings expand our understanding of the relationships between sleep and glucose regulation.</p>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"184 ","pages":"109484"},"PeriodicalIF":7.0,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142766994","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"In silico exploration of phytochemicals as inhibitors for acute myeloid leukemia by targeting LIN28A gene: A cheminformatics study.","authors":"Amr Hassan, Sameh E Hassanein, Elsayed A Elabsawy","doi":"10.1016/j.compbiomed.2024.109286","DOIUrl":"10.1016/j.compbiomed.2024.109286","url":null,"abstract":"<p><strong>Background: </strong>Recent discoveries have illustrated that Lin28A is an oncogene in various cancers, particularly acute myeloid leukemia (AML). The upregulation of Lin28A can actively contribute to tumorigenesis and migration processes in multiple organs. Hence, the inhibition of Lin28A can be achieved by applying phytochemical herbals and targeting Lin28A protein using a computer-aided drug design (CAAD) approach.</p><p><strong>Methods: </strong>In this study, we comprehensively applied several bioinformatics tools, including gene ontologies, gene enrichment analysis, and protein-protein interactions (PPI), to determine the biological pathways, functional gene ontology, and biological pathway. Furthermore, we investigated a list of phytochemical herbs as a candidate drug by applying a computation technique involving molecular docking, density functional theory (DFT), molecular dynamics simulation (MDs), and pharmacokinetic and physiochemical properties by applying the SwissADME, pkCSM, and Molsoft LLC web-servers.</p><p><strong>Results: </strong>The Lin28A gene is related to two significant enrichment pathways, including proteoglycans in cancer and the pluripotency of stem cells through interactions with different genes such as MAPK12, MYC, MTOR, and PIK3CA. Interestingly, limonin, 18β Glycyrrhetic Acid, and baicalein have the highest binding energy scores of -8.4, -8.2, and -7.3 kcal/mol, respectively. The DFT study revealed that baicalein has a higher reactivity than limonin and 18β-Glycyrrhetic due to a small energy gap between LUMO and HUMO. Molecular dynamics simulation exhibited that baicalein complex with Lin28A protein is more stable than other complexes during simulation time due to low fluctuation with simulation periods as compared with other complexes, which indicated that baicalein was more fitting to docking and combining in the protein cave because of the largest number of H-bonds available for the docking simulation process. Furthermore, the drug-likeness and ADMET profiles revealed the activity of limonin, baicalein, and 18β-glycyrrhizic Acid, which possess significant inhibiting Lin28A proteins.</p><p><strong>Conclusion: </strong>This study elucidated that baicalein, 18β-glycyrrhizic, and limonin may be applied as potential candidates for targeting Lin28A as an active oncogene for acute myeloid leukemia.</p>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"183 ","pages":"109286"},"PeriodicalIF":7.0,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142590270","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-lesion segmentation guided deep attention network for automated detection of diabetic retinopathy.","authors":"Feng Li, Xinyu Sheng, Hao Wei, Shiqing Tang, Haidong Zou","doi":"10.1016/j.compbiomed.2024.109352","DOIUrl":"10.1016/j.compbiomed.2024.109352","url":null,"abstract":"<p><p>Accurate multi-lesion segmentation together with automated grading on fundus images played a vital role in diagnosing and treating diabetic retinopathy (DR). Nevertheless, the intrinsic patterns of fundus lesions aggravated challenges in DR detection process. Therefore, we proposed a novel multi-lesion segmentation guided deep attention network (MSGDA-Net) for accurate and automated DR detection, consisting of a DR lesion segmentation pathway as an auxiliary task to produce a lesion regional prior knowledge and a DR grading pathway to extract local fine-grained features and long-range dependency. In DR lesion segmentation pathway, we designed a Multi-Scale Attention Block (MSAB) and a Lesion-Aware Relation Block (LARB) to allow interactions among multi-lesion features for alleviating ambiguity in lesion segmentation, generating lesion regional prior knowledge. As for DR grading pathway, we presented a Spatial-Fusion Block (SFB) to enhance the lesion-related local fine-grained feature representations and eliminate irrelevant noise information under the guidance of the resulting lesion regional priors, while constructed an Enhanced Self-Attention Block (ESAB) to optimally fuse fine-grained features from SFB with long-range global-context information for grading DR. The experimental results showed that our MSGDA-Net not only achieved state-of-the-art performance in the tasks of multi-lesion segmentation and DR grading, reaching up to 49.21 % Dice, 38.05 % IoU and 51.15 % AUPR for DR lesion segmentation on the DDR dataset, as well as accuracy values of 75.00 % and 87.18 % for DR grading on local newly-built VisionDR and publicly available APTOS datasets, but also manifested good generalization and robustness on cross-data evaluation. It could serve as a promising tool for computer aided DR screening and diagnosis.</p>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"183 ","pages":"109352"},"PeriodicalIF":7.0,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142590273","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Transformative artificial intelligence in gastric cancer: Advancements in diagnostic techniques.","authors":"Mobina Khosravi, Seyedeh Kimia Jasemi, Parsa Hayati, Hamid Akbari Javar, Saadat Izadi, Zhila Izadi","doi":"10.1016/j.compbiomed.2024.109261","DOIUrl":"10.1016/j.compbiomed.2024.109261","url":null,"abstract":"<p><p>Gastric cancer represents a significant global health challenge with elevated incidence and mortality rates, highlighting the need for advancements in diagnostic and therapeutic strategies. This review paper addresses the critical need for a thorough synthesis of the role of artificial intelligence (AI) in the management of gastric cancer. It provides an in-depth analysis of current AI applications, focusing on their contributions to early diagnosis, treatment planning, and outcome prediction. The review identifies key gaps and limitations in the existing literature by examining recent studies and technological developments. It aims to clarify the evolution of AI-driven methods and their impact on enhancing diagnostic accuracy, personalizing treatment strategies, and improving patient outcomes. The paper emphasizes the transformative potential of AI in overcoming the challenges associated with gastric cancer management and proposes future research directions to further harness AI's capabilities. Through this synthesis, the review underscores the importance of integrating AI technologies into clinical practice to revolutionize gastric cancer management.</p>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"183 ","pages":"109261"},"PeriodicalIF":7.0,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142564110","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting the physiological effects of multiple drugs using electronic health record.","authors":"Junhyeok Jeon, Eujin Hong, Jong-Yeup Kim, Suehyun Lee, Hyun Uk Kim","doi":"10.1016/j.compbiomed.2024.109485","DOIUrl":"https://doi.org/10.1016/j.compbiomed.2024.109485","url":null,"abstract":"<p><p>Various computational models have been developed to understand the physiological effects of drug-drug interactions, which can contribute to more effective drug treatments. However, they mostly focus on interactions of only two drugs, and do not consider the patient information. To address this challenge, we use publicly available electronic health record (EHR), MIMIC-IV, to develop machine learning models that predict the physiological effects of two or more drugs. This study involves extensive preprocessing of laboratory measurement data, prescription data and patient data. The resulting machine learning models predict potential abnormalities across 20 selected measurement items (e.g., concentrations of metabolites and blood cells) in the form of a sentence. Analysis of the model predictions showed that age, specific active pharmaceutical ingredients, and male/female appeared to be the most influential features. The model development process showcased in this study can be extended to other measurement items for a target EHR.</p>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"184 ","pages":"109485"},"PeriodicalIF":7.0,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142767094","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}