Acute (destructive) pancreatitis: prediction of outcomes using artificial intelligence, a comprehensive reviewAbstract
Acute pancreatitis (AP) is a serious and potentially life-threatening condition characterized by a broad spectrum of disease severity, ranging from mild, self-limiting cases to severe, destructive forms associated with significant morbidity and mortality. Accurate prediction of clinical outcomes in AP is essential for timely intervention, effective resource allocation, and improved patient care. Recent advancements in artificial intelligence (AI) and machine learning (ML) have demonstrated significant potential in enhancing the accuracy of outcome prediction for acute pancreatitis. This article reviews the literature concerning the role of predictive models powered by artificial intelligence in acute pancreatitis (AP) focusing on their methods, evaluation criteria, and clinical usefulness. In addition, the review draws attention to data-related issues with the authors saying that the data is of insufficient quality, and the models cannot be properly explained, as well as other forms of bias in the algorithms used. Other ways are discussed, such as the use of real-time monitoring via wearable devices and the construction of explainable AI models, which shed light on the ways artificial intelligence is capable of changing the clinical approach to acute pancreatitis in the future.
Keywords:
acute pancreatitis; artificial intelligence; machine learning; predictive models; clinical outcomes
Resumo
A pancreatite aguda (PA) é uma condição grave e potencialmente fatal, caracterizada por um amplo espectro de gravidade da doença, variando de casos leves e autolimitados a formas graves e destrutivas associadas a morbidade e mortalidade significativas. A predição precisa dos resultados clínicos na PA é essencial para uma intervenção oportuna, alocação eficaz de recursos e melhoria do atendimento ao paciente. Avanços recentes em inteligência artificial (IA) e aprendizado de máquina (ML) demonstraram potencial significativo para aumentar a precisão da predição de resultados para pancreatite aguda. Este artigo revisa a literatura sobre o papel dos modelos preditivos alimentados por inteligência artificial na pancreatite aguda (PA), com foco em seus métodos, critérios de avaliação e utilidade clínica. Além disso, a revisão chama a atenção para questões relacionadas aos dados, com os autores afirmando que os dados são de qualidade insuficiente e os modelos não podem ser explicados adequadamente, bem como outras formas de viés nos algoritmos utilizados. Outras formas são discutidas, como o uso de monitoramento em tempo real por meio de dispositivos vestíveis e a construção de modelos de IA explicáveis, que esclarecem como a inteligência artificial é capaz de mudar a abordagem clínica da pancreatite aguda no futuro.
Palavras-chave:
pancreatite aguda; inteligência artificial; aprendizado de máquina; modelos preditivos; resultados clínicos
1. Background
Acute pancreatitis (AP) is one of the most frequent gastrointestinal conditions leading to hospitalization globally (Iannuzzi et al., 2022; Trikudanathan et al., 2024). While the majority of cases are mild and self-limiting, around 20% of patients progress to severe acute pancreatitis (SAP), a critical condition marked by systemic inflammation, organ failure, and pancreatic necrosis (Ramírez-Maldonado et al., 2025). The early identification of patients at risk for SAP is vital, as timely intervention can significantly improve outcomes and reduce mortality rates (Dai et al., 2024; Wu et al., 2024). However, achieving accurate and timely risk stratification remains a challenge in clinical practice. Traditional scoring systems, such as the Ranson criteria, APACHE II, and BISAP, have been widely used to predict the severity and outcomes of acute pancreatitis (Gupta and Gupta, 2024; Özdede et al., 2025). While these tools provide valuable insights, they are often limited by their reliance on static variables, delayed availability of results, and moderate predictive accuracy (Abbas et al., 2025). These limitations can hinder their effectiveness in guiding early clinical decision-making, particularly in dynamic and high-stakes scenarios. As a result, there is a growing need for more advanced and reliable methods to enhance risk prediction and patient management (Abbas et al., 2025).
Artificial intelligence (AI) and machine learning (ML) represent a transformative approach to addressing these challenges (Rehman et al., 2024; Hanna et al., 2025). By leveraging large datasets and sophisticated algorithms, AI-driven models can identify complex patterns and relationships that are beyond the scope of traditional methods (Ahamed and Sridevi, 2025). These technologies have the potential to improve the accuracy, speed, and personalization of outcome prediction in acute pancreatitis, enabling clinicians to make more informed decisions (Jin et al., 2025) (Figure 1). However, the integration of AI into clinical practice requires careful consideration of challenges such as data quality, model interpretability, and ethical concerns, which must be addressed to fully realize its potential in improving patient care (Rehman et al., 2024).
Illustrates the diagnostic and therapeutic landscape of acute pancreatitis and highlights the potential integration points for AI models. It provides a schematic view of how AI can assist in patient stratification, treatment planning, and prognosis.
This review was designed to thoroughly examine the state of artificial intelligence (AI) and machine learning models currently in use for forecasting acute pancreatitis (AP) outcomes, such as severity, organ failure, mortality, and hospital stay duration. Further, to evaluate the integration and effect on prediction accuracy of the various forms and sources of data (clinical, laboratory, imaging, and omics) used in AP AI model training. Moreover, to evaluate AI-powered methods against conventional scoring methods (like Ranson, APACHE II, and BISAP) using performance indicators like AUC, sensitivity, and specificity. To assess AI models' interpretability, limitations, and clinical applicability in practical contexts, taking into account issues with data quality, algorithmic bias, and healthcare integration. To determine future research and development avenues, such as explainable AI and wearable technology (XAI), as well as standardised datasets to improve patient care and outcome prediction in AP.
2. AI and Machine Learning in Healthcare
Artificial intelligence (AI) and machine learning (ML) are revolutionizing healthcare by offering advanced tools for disease prediction, diagnosis, and treatment optimization (Rehman et al., 2024; Fatima, 2024; Hanna et al., 2025). AI encompasses a broad spectrum of technologies, including ML, deep learning (DL), and natural language processing (NLP), which are increasingly being utilized to analyze complex datasets and uncover insights that were previously unattainable (Rashid and Kausik, 2024; Velastegui et al., 2025). In the context of acute pancreatitis (AP), these technologies hold significant promise for improving patient outcomes by enabling more accurate and timely predictions. AI models in acute pancreatitis can integrate and analyze diverse data sources, such as clinical records, laboratory results, imaging studies, and even omics data (e.g., genomics, proteomics) (Ramírez-Maldonado et al., 2025). By processing these multifaceted datasets, AI systems can identify subtle patterns and correlations that traditional methods might overlook (Rehman et al., 2024; Wu and Xie, 2025). This capability allows for the prediction of critical outcomes, including disease severity, the likelihood of organ failure, mortality risk, and the expected length of hospital stay (He et al., 2025). Such predictions are invaluable for clinicians, as they facilitate early intervention, personalized treatment plans, and optimized resource allocation.
The application of AI in acute pancreatitis exemplifies its potential to transform healthcare delivery. By leveraging advanced algorithms and large-scale data integration, AI-driven models can enhance clinical decision-making, improve patient outcomes, and reduce the burden on healthcare systems (Udegbe et al., 2024; Tan et al., 2025). However, the successful implementation of these technologies requires addressing challenges such as data quality, model interpretability, and ethical considerations (Rane et al., 2024; Kehinde, 2025). As AI continues to evolve, its integration into clinical practice promises to usher in a new era of precision medicine for acute pancreatitis and beyond (Figure 2).
The progression from acute pancreatitis (AP) diagnosis to better patient outcomes through AI-driven methods is depicted in this flow diagram. AI and machine learning models that use a variety of data sources (clinical, lab, imaging, and omics) for predictive analytics are contrasted with conventional scoring systems. The figure highlights the ways in which AI improves clinical decision-making, strengthens risk assessment, and advances patient care.
3. AI Models for Outcome Prediction in Acute Pancreatitis
Artificial intelligence (AI) has shown significant promise in improving the prediction of outcomes in acute pancreatitis (AP), offering advantages over traditional methods in terms of accuracy, speed, and personalization. Several studies have highlighted the potential of AI models in this domain (Cui et al., 2024; Antel et al., 2025).
4. Severity Prediction
AI and machine learning (ML) models have demonstrated superior performance compared to traditional scoring systems like Ranson criteria, APACHE II, and BISAP (Tan et al., 2025). For instance, algorithms such as random forest and gradient boosting have achieved high accuracy in distinguishing between mild and severe cases of AP (Gowroju et al., 2025). These models leverage a combination of clinical, laboratory, and imaging data to provide more precise and timely predictions, enabling clinicians to identify high-risk patients earlier and initiate appropriate interventions (Tolu‐Akinnawo et al., 2025).
5. Organ Failure and Mortality
Deep learning (DL) models, particularly convolutional neural networks (CNNs), have been employed to analyze imaging data, such as CT scans, to predict complications like pancreatic necrosis and organ failure (Zhang et al., 2024; Cheng et al., 2025). These models can detect subtle patterns in imaging that may not be apparent to the human eye, improving diagnostic accuracy. Additionally, natural language processing (NLP) techniques have been used to extract and analyze relevant information from electronic health records (EHRs), such as clinical notes and lab results, to predict mortality risk (Bhandari, 2024; Huang et al., 2025). This integration of multimodal data enhances the robustness of AI-driven predictions.
6. Personalized Treatment
AI models have the unique ability to identify patient subgroups that may benefit from specific interventions, such as early enteral feeding or intensive care admission (Kittrell et al., 2024; Liu et al., 2025). AI models are transforming the management of acute pancreatitis by providing more accurate and timely predictions of disease severity, organ failure, mortality, and personalized treatment options (Rêgo and Araújo-Filho, 2024; Li et al., 2025). While these advancements hold great promise, challenges such as data quality, model interpretability, and ethical considerations must be addressed to integrate AI into clinical practice fully. As research and technology evolve, AI is poised to play an increasingly critical role in improving outcomes for patients with acute pancreatitis (Figure 3).
AI model investigating acute pancreatitis, analyzing the patient’s data, suggesting and enhancing more suitable and effective treatment.
7. Data Sources and Methodologies
Artificial Intelligence (AI) models used in the study and management of Acute Pancreatitis (AP) rely on a variety of data sources to enhance their predictive and diagnostic capabilities (Hu et al., 2023; Villasante et al., 2024; Ramírez-Maldonado et al., 2025). One of the primary sources is clinical and laboratory data, which includes demographic information, vital signs, and laboratory results such as amylase, lipase, and C-reactive protein (CRP). These features are crucial for understanding the patient's condition and for making initial assessments. Laboratory results, in particular, provide quantitative measures that can be easily integrated into machine learning algorithms to predict outcomes or severity of the disease (Alshahrani, 2025).
Imaging data is another critical component, with modalities like CT scans, MRI, and ultrasound offering detailed visual insights into the pancreas and surrounding tissues. These imaging techniques help in identifying morphological changes, complications, and the extent of inflammation or necrosis, which are vital for accurate diagnosis and treatment planning. The integration of imaging data into AI models allows for a more comprehensive analysis, enabling the detection of patterns that may not be evident through clinical or laboratory data alone (Irizato et al., 2025).
Omics data, encompassing genomics, proteomics, and metabolomics, represents a more advanced layer of information that can be leveraged for personalized medicine (Ghosh et al., 2025). By analyzing genetic variations, protein expressions, and metabolic profiles, AI models can stratify patients based on their risk levels and tailor interventions accordingly. This personalized approach holds promise for improving outcomes by addressing the unique biological characteristics of each patient (Quazi, 2022).
Electronic Health Records (EHRs) are another rich source of data, particularly when combined with Natural Language Processing (NLP) techniques (Hossain et al., 2023). EHRs contain a wealth of unstructured data in the form of clinical notes, which can be challenging to analyze using traditional methods (Kim et al., 2024). NLP enables the extraction of meaningful information from these notes, such as patient history, symptoms, and treatment responses, thereby enhancing the predictive capabilities of AI models (Kumar et al., 2025). This integration of structured and unstructured data provides a more holistic view of the patient's condition. There are still a number of restrictions even with the wide range of data inputs available for AI modelling. Model training may be jeopardised by the frequent inconsistencies, missing values, and institutional biases found in Electronic Health Records (EHRs). The generalisability of radiomics-based AI models is also impacted by the notable differences in imaging protocols between centers (Kim et al., 2024). To guarantee reliable and repeatable AI solutions for AP, these discrepancies emphasise the necessity of external validation frameworks and standardised data collection procedures.
In terms of methodologies, a range of machine learning (ML) algorithms are employed in AP research, including logistic regression, support vector machines (SVMs), random forests, and neural networks (Antúnez et al., 2025). These algorithms are chosen based on their ability to handle different types of data and their performance in predictive tasks. More recently, deep learning (DL) models, such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), have gained popularity due to their ability to analyze complex and high-dimensional data, such as imaging and omics data (Younesi et al., 2024). The use of these advanced models is expected to grow as the volume and complexity of data in healthcare continue to increase, offering new opportunities for improving the diagnosis, prognosis, and treatment of AP (Figure 4).
An overview of the many data sources used for AI analysis in acute pancreatitis is given in this figure. These sources include clinical records, laboratory results, imaging modalities (CT, MRI, ultrasound), and omics data (genomics, proteomics). AI models combine and process these various inputs to find intricate patterns, forecast the severity of diseases, and direct treatment choices. The multifaceted nature of data used to improve predictive accuracy and individualized patient care is highlighted in the figure.
8. Performance and Clinical Applicability
AI models have been shown to outperform traditional scoring systems in terms of sensitivity, specificity, and overall accuracy, as reflected by metrics such as the area under the receiver operating characteristic curve (AUC-ROC) (El-Menyar et al., 2024). For example, a machine learning model significantly outperformed the BISAP score (AUC: 0.75), achieving an AUC of 0.92 in predicting SAP, according to a recent study by Hu et al. (2023). It is not appropriate to interpret these values as pooled metrics because they come from individual validation studies. This demonstrates the potential of AI models to provide more precise predictions in clinical settings, offering significant improvements over traditional scoring systems. Some of the currently used AI models for acute pancreatitis data management and analysis are listed in Table 1.
Summarizing the current AI models used in the prediction of outcomes in acute pancreatitis (AP), particularly focusing on severe or destructive forms of the disease. These models leverage machine learning (ML) and deep learning (DL) techniques to predict outcomes such as mortality, severity, organ failure, and complications.
Despite these promising results, the clinical applicability of AI models remains limited by several challenges. One of the primary concerns is data quality. Machine learning models rely heavily on large, high-quality datasets for accurate predictions, and incomplete or biased data can lead to misleading results (Aminizadeh et al., 2024). Additionally, the diversity of patient populations and the heterogeneity of clinical data further complicate model training and validation, making it difficult to generalize findings across different healthcare settings.
Another barrier to the widespread use of AI models in clinical practice is model interpretability. Unlike traditional scoring systems, which offer straightforward, understandable metrics, AI models often function as “black boxes,” making it difficult for healthcare professionals to understand how predictions are generated. This lack of transparency can undermine trust in the models and hinder their adoption (Esmaeilzadeh, 2024). Furthermore, integrating AI models into existing clinical workflows presents logistical challenges, requiring adaptation of systems, training of staff, and careful consideration of ethical and regulatory implications. These factors collectively limit the practical implementation of AI models in healthcare.
9. Challenges and Limitations
AI models hold great potential for transforming clinical practice, but several challenges hinder their effective use. One of the primary issues is data quality and availability. For AI models to be accurate and reliable, they require high-quality, labeled datasets. Unfortunately, such datasets are often scarce, particularly in areas like acute pancreatitis (AP). The lack of comprehensive and well-curated clinical data can limit the training and generalization capabilities of AI models, making them less effective in real-world clinical settings (Esmaeilzadeh, 2024; Sezgin and Kocaballi, 2025). Model interpretability is another significant challenge. Many AI models, especially deep learning (DL) models, operate as “black boxes,” meaning that their decision-making process is not transparent to users (Khan, 2025). This lack of interpretability makes it difficult for clinicians to understand how predictions are made and raises concerns about the trustworthiness of the models. Without clear insights into how AI systems arrive at their conclusions, healthcare professionals may be hesitant to rely on them, which limits their widespread adoption in clinical practice (Nasarian et al., 2024).
In addition to these technical challenges, there are also ethical and legal concerns surrounding the use of AI in healthcare. Issues like data privacy, algorithmic bias, and liability need to be addressed to ensure that AI models are used responsibly (Cascella et al., 2025). Ensuring that models do not perpetuate biases or make inaccurate predictions based on incomplete data is essential for their ethical deployment (Gadani and Bhattacharya, 2025). Furthermore, integrating AI into existing clinical workflows poses its own set of challenges. For AI models to be effective, they must seamlessly integrate with Electronic Health Record (EHR) systems and fit into the day-to-day operations of healthcare providers. Overcoming these hurdles is crucial for the practical implementation of AI in clinical settings. The poor performance of AI models when applied to minority populations where under-representation in training datasets leads to decreased accuracy is a prominent illustration of algorithmic bias. Another example is age-related bias, which limits the predictive reliability of geriatric AP cases by under-representing elderly patients in model training.
10. Future Directions
Future research in AI for healthcare, particularly in predicting outcomes for acute pancreatitis (AP), should focus on several key areas (Tripathi et al., 2024). One of the most critical needs is the development of standardized datasets and benchmarks specifically for AP outcome prediction (Wang et al., 2024). Currently, there is a lack of consistent, high-quality data that could be used to train AI models, limiting their generalizability and effectiveness. Creating standardized datasets will ensure that AI models can be validated across different populations and clinical settings, making them more reliable and accurate. There are encouraging opportunities for real-time risk assessment in acute pancreatitis through the integration of wearable technology, such as continuous heart rate and oxygen saturation monitors. These devices can assist in identifying early indicators of deterioration, such as imminent organ failure or sepsis, by feeding continuous biometric data into AI systems. This prevents complications and allows for prompt interventions.
Improving model interpretability is another crucial direction for future research. As AI models, especially deep learning models, often function as “black boxes,” it is essential to develop techniques that make these models more understandable for clinicians. Explainable AI (XAI) techniques could provide insights into how models arrive at their predictions, allowing healthcare professionals to gain more trust in the technology. By improving model transparency, clinicians will be better equipped to use AI in clinical decision-making, knowing the reasoning behind each prediction. Additionally, conducting prospective studies to validate AI models in diverse clinical settings is necessary to assess their real-world applicability. These studies can help determine how well AI models perform in different hospitals, regions, or patient populations, and whether they are consistently effective across various scenarios. Furthermore, exploring the integration of AI with wearable devices and real-time monitoring systems presents an exciting opportunity for early detection of complications in conditions like AP. By combining AI's predictive power with the continuous data provided by wearable devices, it may be possible to identify early signs of deterioration and intervene before complications arise, leading to better patient outcomes.
11. Conclusions
In conclusion, AI has the potential to revolutionize the management of acute pancreatitis by offering accurate, timely, and personalized predictions of patient outcomes. The ability to predict complications early can lead to better clinical decision-making, improved patient care, and potentially better survival rates. However, despite the considerable advancements in AI research, significant challenges remain in translating these innovations into routine clinical practice. Issues such as data quality, model interpretability, and integration with existing healthcare systems must be addressed before AI can be widely adopted.
The successful implementation of AI in clinical settings requires collaboration among a diverse group of stakeholders, including clinicians, data scientists, and policymakers. Clinicians provide essential insights into the practical challenges of patient care, while data scientists can help develop and refine AI models to meet clinical needs. Policymakers play a critical role in addressing ethical, legal, and regulatory concerns, ensuring that AI applications are safe, effective, and equitable. By working together, these groups can help unlock the full potential of AI and improve outcomes for patients with acute pancreatitis and other medical conditions.
Acknowledgements
The authors are very grateful to Ala-Too International University for financial Support.
Data Availability Statement
The entire data set that supports the results of this study was published in the article itself
References
-
ABBAS, S., SHAFIK, R., SOOMRO, N., HEER, R. and ADHIKARI, K., 2025. AI predicting recurrence in non-muscle-invasive bladder cancer: systematic review with study strengths and weaknesses. Frontiers in Oncology, vol. 14, pp. 1509362. http://doi.org/10.3389/fonc.2024.1509362 PMid:39839785.
» http://doi.org/10.3389/fonc.2024.1509362 - AHAMED, N.N. and SRIDEVI, S., 2025. DDM: Data-Driven Marketing Using AI, ML, and Big Data. In: A.K. NATARAJAN, M.G. GALETY, C. IWENDI, D. DAS and A. SHANKAR, eds. AI-Powered Business Intelligence for Modern Organizations Hershey, PA: IGI Global Scientific Publishing, pp. 79-102.
-
ALSHAHRANI, M.M., 2025. A critical evaluation of biochemical markers for the diagnosis of acute pancreatitis. Cellular and Molecular Biology, vol. 71, no. 1, pp. 20-38. http://doi.org/10.14715/cmb/2025.70.1.3 PMid:39910944.
» http://doi.org/10.14715/cmb/2025.70.1.3 -
AMINIZADEH, S., HEIDARI, A., DEHGHAN, M., TOUMAJ, S., REZAEI, M., NAVIMIPOUR, N.J., STROPPA, F. and UNAL, M., 2024. Opportunities and challenges of artificial intelligence and distributed systems to improve the quality of healthcare service. Artificial Intelligence in Medicine, vol. 149, pp. 102779. http://doi.org/10.1016/j.artmed.2024.102779 PMid:38462281.
» http://doi.org/10.1016/j.artmed.2024.102779 -
ANTEL, R., WHITELAW, S., GORE, G. and INGELMO, P., 2025. Moving towards the use of artificial intelligence in pain management. European Journal of Pain (London, England), vol. 29, no. 3, pp. e4748. http://doi.org/10.1002/ejp.4748 PMid:39523657.
» http://doi.org/10.1002/ejp.4748 -
ANTÚNEZ, P., WEHENKEL, C., BASAVE-VILLALOBOS, E., CALIXTO-VALENCIA, C.G., VALENZUELA-ENCINAS, C., RUIZ-AQUINO, F. and SARMIENTO-BUSTOS, D., 2025. Predictive modeling of volume and biomass in Pinus pseudostrobus using machine learning and allometric approaches. Forest Science and Technology, vol. 21, no. 1, pp. 110-122. http://doi.org/10.1080/21580103.2025.2456295
» http://doi.org/10.1080/21580103.2025.2456295 -
BHANDARI, A., 2024. Revolutionizing radiology with artificial intelligence. Cureus, vol. 16, no. 10, pp. e72646. https://doi.org/10.7759/cureus.72646
» https://doi.org/10.7759/cureus.72646 -
CASCELLA, M., SHARIFF, M.N., VISWANATH, O., LEONI, M.L.G. and VARRASSI, G., 2025. Ethical considerations in the use of artificial intelligence in pain medicine. Current Pain and Headache Reports, vol. 29, no. 1, pp. 10. http://doi.org/10.1007/s11916-024-01330-7 PMid:39760779.
» http://doi.org/10.1007/s11916-024-01330-7 -
CHENG, C.T., OOYANG, C.H., LIAO, C.H. and KANG, S.C., 2025. Applications of deep learning in trauma radiology: a narrative review. Biomedical Journal, vol. 48, no. 1, pp. 100743. http://doi.org/10.1016/j.bj.2024.100743 PMid:38679199.
» http://doi.org/10.1016/j.bj.2024.100743 -
CUI, H., ZHAO, Y., XIONG, S., FENG, Y., LI, P., LV, Y., CHEN, Q., WANG, R., XIE, P., LUO, Z., CHENG, S., WANG, W., LI, X., XIONG, D., CAO, X., BAI, S., YANG, A. and CHENG, B., 2024. Diagnosing solid lesions in the pancreas with multimodal artificial intelligence: a randomized crossover trial. JAMA Network Open, vol. 7, no. 7, pp. e2422454. http://doi.org/10.1001/jamanetworkopen.2024.22454 PMid:39028670.
» http://doi.org/10.1001/jamanetworkopen.2024.22454 -
DAI, L., YANG, X., LI, H., ZHAO, X., LIN, L., JIANG, Y., WANG, Y., LI, Z. and SHEN, H., 2024. A clinically actionable and explainable real-time risk assessment framework for stroke-associated pneumonia. Artificial Intelligence in Medicine, vol. 149, pp. 102772. http://doi.org/10.1016/j.artmed.2024.102772 PMid:38462273.
» http://doi.org/10.1016/j.artmed.2024.102772 -
EL-MENYAR, A., NADUVILEKANDY, M., ASIM, M., RIZOLI, S. and AL-THANI, H., 2024. Machine learning models predict triage levels, massive transfusion protocol activation, and mortality in trauma utilizing patients hemodynamics on admission. Computers in Biology and Medicine, vol. 179, pp. 108880. http://doi.org/10.1016/j.compbiomed.2024.108880 PMid:39018880.
» http://doi.org/10.1016/j.compbiomed.2024.108880 -
ESMAEILZADEH, P., 2024. Challenges and strategies for wide-scale artificial intelligence (AI) deployment in healthcare practices: A perspective for healthcare organizations. Artificial Intelligence in Medicine, vol. 151, pp. 102861. http://doi.org/10.1016/j.artmed.2024.102861 PMid:38555850.
» http://doi.org/10.1016/j.artmed.2024.102861 -
FATIMA, S., 2024. Transforming Healthcare with AI and Machine Learning: Revolutionizing Patient Care Through Advanced Analytics. International Journal of Education and Science Research Review, vol. 11, no. 6, pp. 58-75. https://doi.org/10.39124/ijesrr%2012.1147860
» https://doi.org/10.39124/ijesrr%2012.1147860 - GADANI, N.N. and BHATTACHARYA, P., 2025. Ethical Considerations in AI Development for Cloud Computing and Data-Driven Software Solutions. In: P. BHATTACHARYA, A. HASSAN, H. LIU and B. BHUSHAN, eds. Ethical Dimensions of AI Development Hershey, PA: IGI Global Scientific Publishing, pp. 23-58.
-
GHOSH, S., ZHAO, X., ALIM, M., BRUDNO, M. and BHAT, M., 2025. Artificial intelligence applied to ‘omics data in liver disease: towards a personalised approach for diagnosis, prognosis and treatment. Gut, vol. 74, no. 2, pp. 295-311. http://doi.org/10.1136/gutjnl-2023-331740 PMid:39174307.
» http://doi.org/10.1136/gutjnl-2023-331740 - GOWROJU, S., CHOUDHARY, S., JAIN, A. and SRILAKSHMI, R., 2025. Classification of Moderate and Advanced Dementia Patients Using Gradient Boosting Machine Technique: Classification of Moderate and Advanced Dementia Patients. In: U.K. LILHORE, Y.K. SHARMA, S. SIMAIYA, S. KUMAR and M. KUMAR, eds. Revolutionizing AI with Brain-Inspired Technology: Neuromorphic Computing Hershey, PA: IGI Global Scientific Publishing, pp. 261-288.
-
GUPTA, R. and GUPTA, S.K., 2024. Comparing and evaluating the role of early predictors like BISAP and Ranson Scoring System with Modified CT Severity Index in assessing the severity of acute pancreatitis. Indian Journal of Surgery, vol. 87, pp. 43-51. https://doi.org/10.1007/s12262-024-04080-3
» https://doi.org/10.1007/s12262-024-04080-3 -
HANNA, M.G., PANTANOWITZ, L., DASH, R., HARRISON, J.H., DEEBAJAH, M., PANTANOWITZ, J. and RASHIDI, H.H., 2025. Future of artificial intelligence - machine learning trends in pathology and medicine. Modern Pathology, vol. 38, no. 4, pp. 100705. http://doi.org/10.1016/j.modpat.2025.100705 PMid:39761872.
» http://doi.org/10.1016/j.modpat.2025.100705 -
HE, Y., LUO, Q., WANG, H., ZHENG, Z., LUO, H. and OOI, O.C., 2025. Real-time estimated Sequential Organ Failure Assessment (SOFA) score with intervals: improved risk monitoring with estimated uncertainty in health condition for patients in intensive care units. Health Information Science and Systems, vol. 13, no. 1, pp. 12. https://doi.org/10.1007/s13755-024-00331-5 PMid:39748912.
» https://doi.org/10.1007/s13755-024-00331-5 -
HOSSAIN, E., RANA, R., HIGGINS, N., SOAR, J., BARUA, P.D., PISANI, A.R. and TURNER, K., 2023. Natural language processing in electronic health records in relation to healthcare decision-making: a systematic review. Computers in Biology and Medicine, vol. 155, pp. 106649. http://doi.org/10.1016/j.compbiomed.2023.106649 PMid:36805219.
» http://doi.org/10.1016/j.compbiomed.2023.106649 -
HU, J.X., ZHAO, C.F., WANG, S.L., TU, X.Y., HUANG, W.B., CHEN, J.N., XIE, Y. and CHEN, C.R., 2023. Acute pancreatitis: A review of diagnosis, severity prediction and prognosis assessment from imaging technology, scoring system and artificial intelligence. World Journal of Gastroenterology, vol. 29, no. 37, pp. 5268-5291. http://doi.org/10.3748/wjg.v29.i37.5268 PMid:37899784.
» http://doi.org/10.3748/wjg.v29.i37.5268 -
HUANG, R., MENG, X., ZHANG, X., LUO, Z., CAO, L., FENG, Q., MA, G., DONG, D. and WANG, Y., 2025. Artificial intelligence‐driven change redefining radiology through interdisciplinary innovation. Interdisciplinary Medicine, vol. 3, no. 1, pp. e20240063. https://doi.org/10.1002/INMD.20240063
» https://doi.org/10.1002/INMD.20240063 -
IANNUZZI, J.P., KING, J.A., LEONG, J.H., QUAN, J., WINDSOR, J.W., TANYINGOH, D., COWARD, S., FORBES, N., HEITMAN, S.J., SHAHEEN, A.A., SWAIN, M., BUIE, M., UNDERWOOD, F.E. and KAPLAN, G.G., 2022. Global incidence of acute pancreatitis is increasing over time: a systematic review and meta-analysis. Gastroenterology, vol. 162, no. 1, pp. 122-134. http://doi.org/10.1053/j.gastro.2021.09.043 PMid:34571026.
» http://doi.org/10.1053/j.gastro.2021.09.043 -
IRIZATO, M., MINAMIGUCHI, K., UCHIYAMA, T., KUNICHIKA, H., TACHIIRI, T., TAIJI, R., KITAO, A., MARUGAMI, N., INABA, Y. and TANAKA, T., 2025. Hepatobiliary and pancreatic neoplasms: essential predictive imaging features for personalized therapy. Radiographics, vol. 45, no. 3, pp. e240068. http://doi.org/10.1148/rg.240068 PMid:39913319.
» http://doi.org/10.1148/rg.240068 -
JIN, D., KHAN, N.U., GU, G., LEI, H., GOEL, A. and CHEN, T., 2025. Informatics strategies for early detection and risk mitigation in pancreatic cancer patients. Neoplasia, vol. 60, pp. 101129. https://doi.org/10.1016/j.neo.2025.101129 PMid:39842383.
» https://doi.org/10.1016/j.neo.2025.101129 -
KEHINDE, A.O., 2025. Leveraging machine learning for predictive models in healthcare to enhance patient outcome management. International Research Journal of Modernization in Engineering Technology and Science, vol. 7, no. 1, pp. 1465-1482. https://www.doi.org/10.56726/IRJMETS66198.
» https://doi.org/https://www.doi.org/10.56726/IRJMETS66198 - KHAN, M., 2025. A Framework for Automated Insights: Exploring AI-Driven Data Science Techniques. Intelligent Data Science and Analytics, vol. 1, no. 1, pp. 10-22.
-
KIM, M.K., ROUPHAEL, C., MCMICHAEL, J., WELCH, N. and DASARATHY, S., 2024. Challenges in and opportunities for electronic health record-based data analysis and interpretation. Gut and Liver, vol. 18, no. 2, pp. 201-208. http://doi.org/10.5009/gnl230272 PMid:37905424.
» http://doi.org/10.5009/gnl230272 -
KITTRELL, H.D., SHAIKH, A., ADINTORI, P.A., MCCARTHY, P., KOHLI‐SETH, R., NADKARNI, G.N. and SAKHUJA, A., 2024. Role of artificial intelligence in critical care nutrition support and research. Nutrition in Clinical Practice, vol. 39, no. 5, pp. 1069-1080. http://doi.org/10.1002/ncp.11194 PMid:39073166.
» http://doi.org/10.1002/ncp.11194 - KUMAR, V., IQBAL, M.I. and RATHORE, R., 2025. Natural Language Processing (NLP) in disease detection — A discussion of how NLP Techniques can be used to analyze and classify medical text data for disease diagnosis. In: R. SINGH, A. GEHLOT, N. RATHOUR and S.V. AKRAM, eds. AI in disease detection: advancements and applications Nova Jersey: Wiley-IEEE Press, pp. 53-75.
-
LI, F., WANG, S., GAO, Z., QING, M., PAN, S., LIU, Y. and HU, C., 2025. Harnessing artificial intelligence in sepsis care: advances in early detection, personalized treatment, and real-time monitoring. Frontiers in Medicine, vol. 11, pp. 1510792. http://doi.org/10.3389/fmed.2024.1510792 PMid:39835096.
» http://doi.org/10.3389/fmed.2024.1510792 -
LIU, L., LI, J., HU, L., CAI, X., LI, X. and BAI, Y., 2025. Development and validation of a prediction model for enteral feeding intolerance in critical ill patients: a retrospective cohort study. Journal of Clinical Nursing, vol. 34, no. 6, pp. 2336-2347. http://doi.org/10.1111/jocn.17660 PMid:39888094.
» http://doi.org/10.1111/jocn.17660 -
NASARIAN, E., ALIZADEHSANI, R., ACHARYA, U.R. and TSUI, K.L., 2024. Designing interpretable ML system to enhance trust in healthcare: A systematic review to proposed responsible clinician-AI-collaboration framework. Information Fusion, vol. 108, pp. 102412. http://doi.org/10.1016/j.inffus.2024.102412
» http://doi.org/10.1016/j.inffus.2024.102412 -
ÖZDEDE, M., BATUR, A. and AKSOY, A.E., 2025. Improved outcome prediction in acute pancreatitis with generated data and advanced machine learning algorithms. Turkish Journal of Emergency Medicine, vol. 25, no. 1, pp. 32-40. http://doi.org/10.4103/tjem.tjem_161_24 PMid:39882088.
» http://doi.org/10.4103/tjem.tjem_161_24 -
QUAZI, S., 2022. Artificial intelligence and machine learning in precision and genomic medicine. Medical Oncology, vol. 39, no. 8, pp. 120. http://doi.org/10.1007/s12032-022-01711-1 PMid:35704152.
» http://doi.org/10.1007/s12032-022-01711-1 - RAMÍREZ-MALDONADO, E., GORDO, S.L. and JORBA, R., 2025. Emerging Innovations in the Management of Acute Pancreatitis. In: L. RODRIGO, ed. Acute and chronic pancreatitis Rijeka: IntechOpen, pp. 1-23.
-
RANE, N., CHOUDHARY, S.P. and RANE, J., 2024. Acceptance of artificial intelligence: key factors, challenges, and implementation strategies. Journal of Applied Artificial Intelligence, vol. 5, no. 2, pp. 50-70. http://doi.org/10.48185/jaai.v5i2.1017
» http://doi.org/10.48185/jaai.v5i2.1017 -
RASHID, A.B. and KAUSIK, A.K., 2024. AI revolutionizing industries worldwide: A comprehensive overview of its diverse applications. Hybrid Advances, vol. 7, pp. 100277. https://doi.org/10.1016/j.hybadv.2024.100277
» https://doi.org/10.1016/j.hybadv.2024.100277 -
RÊGO, A.C.M. and ARAÚJO-FILHO, I., 2024. Decision-making in severe acute pancreatitis: the role of artificial intelligence and severity scales. World Journal of Advanced Research and Reviews, vol. 23, no. 1, pp. 2899-2908. http://doi.org/10.30574/wjarr.2024.23.1.2255
» http://doi.org/10.30574/wjarr.2024.23.1.2255 -
REHMAN, S. U., OSMONALIEV, K., MAKAMBAEV, A. and AKNAZAROV, S., 2024. The Role of Artificial Intelligence in Genetic: Current and Future Perspective. South Eastern European Journal of Public Health, vol. 25, pp. 1759-1772. https://doi.org/10.70135/seejph.vi.2666
» https://doi.org/10.70135/seejph.vi.2666 -
SEZGIN, E. and KOCABALLI, A.B., 2025. Era of generalist conversational artificial intelligence to support public health communications. Journal of Medical Internet Research, vol. 27, pp. e69007. http://doi.org/10.2196/69007 PMid:39832358.
» http://doi.org/10.2196/69007 -
TAN, M.J.T., KASIREDDY, H.R., SATRIYA, A.B., ABDUL KARIM, H. and ALDAHOUL, N., 2025. Health is beyond genetics: on the integration of lifestyle and environment in real-time for hyper-personalized medicine. Frontiers in Public Health, vol. 12, pp. 1522673. http://doi.org/10.3389/fpubh.2024.1522673 PMid:39839379.
» http://doi.org/10.3389/fpubh.2024.1522673 -
TOLU‐AKINNAWO, O.Z., EZEKWUEME, F., OMOLAYO, O., BATHEJA, S. and AWOYEMI, T., 2025. Advancements in artificial intelligence in noninvasive cardiac imaging: a comprehensive review. Clinical Cardiology, vol. 48, no. 1, pp. e70087. http://doi.org/10.1002/clc.70087 PMid:39871619.
» http://doi.org/10.1002/clc.70087 -
TRIKUDANATHAN, G., YAZICI, C., PHILLIPS, A.E. and FORSMARK, C.E., 2024. Diagnosis and management of acute pancreatitis. Gastroenterology, vol. 167, no. 4, pp. 673-688. http://doi.org/10.1053/j.gastro.2024.02.052 PMid:38759844.
» http://doi.org/10.1053/j.gastro.2024.02.052 -
TRIPATHI, S., TABARI, A., MANSUR, A., DABBARA, H., BRIDGE, C.P. and DAYE, D., 2024. From machine learning to patient outcomes: a comprehensive review of ai in pancreatic cancer. Diagnostics, vol. 14, no. 2, pp. 174. http://doi.org/10.3390/diagnostics14020174 PMid:38248051.
» http://doi.org/10.3390/diagnostics14020174 -
UDEGBE, F.C., EBULUE, O.R., EBULUE, C.C. and EKESIOBI, C.S., 2024. AI’s impact on personalized medicine: tailoring treatments for improved health outcomes. Engineering Science & Technology Journal, vol. 5, no. 4, pp. 1386-1394. http://doi.org/10.51594/estj.v5i4.1040
» http://doi.org/10.51594/estj.v5i4.1040 -
VELASTEGUI, R., POLER, R. and DÍAZ-MADROÑERO, M., 2025. Revolutionising industrial operations: the synergy of multiagent robotic systems and blockchain technology in operations planning and control. Expert Systems with Applications, vol. 269, pp. 126460. http://doi.org/10.1016/j.eswa.2025.126460
» http://doi.org/10.1016/j.eswa.2025.126460 -
VILLASANTE, S., FERNANDES, N., PEREZ, M., CORDOBÉS, M.A., PIELLA, G., MARTINEZ, M., GOMEZ-GAVARA, C., BLANCO, L., ALBERTI, P., CHARCO, R., PANDO, E. and Pancreatia Study Collaborators, 2024. Prediction of severe acute pancreatitis at a very early stage of the disease using artificial intelligence techniques, without laboratory data or imaging tests: the PANCREATIA study. Annals of Surgery, In press, pp. 1-30. http://doi.org/10.1097/SLA.0000000000006579 PMid:39498559.
» http://doi.org/10.1097/SLA.0000000000006579 - WANG, C., ZHU, W., GAO, B.B., GAN, Z., ZHANG, J., GU, Z., QIAN, S., CHEN, M. and MA, L. 2024. Real-iad: A real-world multi-view dataset for benchmarking versatile industrial anomaly detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 16-22 June 2024, Seattle, WA, USA. Seattle: IEEE, pp. 22883-22892.
-
WU, B., LUO, H., LI, J., CHEN, Y., LIU, J., YU, P., YAN, Z., WANG, A., XIAN, H., KE, J., CHENG, R., WANG, X., YI, C., HAN, W., LIAO, H., WU, Y., JIA, W., HAN, M. and YI, Y., 2024. The relationship between the Barthel Index and stroke-associated pneumonia in elderly patients and factors of SAP. BMC Geriatrics, vol. 24, no. 1, pp. 829. http://doi.org/10.1186/s12877-024-05400-8 PMid:39395978.
» http://doi.org/10.1186/s12877-024-05400-8 -
WU, Y. and XIE, L., 2025. AI-driven multi-omics integration for multi-scale predictive modeling of genotype-environment-phenotype relationships. Computational and Structural Biotechnology Journal, vol. 27, pp. 265-277. http://doi.org/10.1016/j.csbj.2024.12.030
» http://doi.org/10.1016/j.csbj.2024.12.030 -
YOUNESI, A., ANSARI, M., FAZLI, M., EJLALI, A., SHAFIQUE, M. and HENKEL, J., 2024. A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends. IEEE Access, vol. 12, pp. 41180-41218. http://doi.org/10.1109/ACCESS.2024.3376441
» http://doi.org/10.1109/ACCESS.2024.3376441 -
ZHANG, C., PENG, J., WANG, L., WANG, Y., CHEN, W., SUN, M.W. and JIANG, H., 2024. A deep learning-powered diagnostic model for acute pancreatitis. BMC Medical Imaging, vol. 24, no. 1, pp. 154. http://doi.org/10.1186/s12880-024-01339-9 PMid:38902660.
» http://doi.org/10.1186/s12880-024-01339-9
Edited by
-
Editor:
Marcelo A.M. Esquisatto
