Medical Decision-making Process Research Articles

Unlocking Optimal Glycemic Interpretation: Redefining HbA1c Analysis in Female Patients With Diabetes and Iron-Deficiency Anemia Using Machine Learning Algorithms.

In response to the nuanced glycemic challenges faced by women with iron deficiency anemia (IDA) associated with diabetes, this study uses advanced machine learning algorithms to redefine hemoglobin (Hb)A1c measurement values. We aimed to improve the accuracy of glycemic interpretation by recognizing the critical interaction between erythrocytes, iron, and glycemic levels in this specific demographic group. This retrospective observational study included 17,526 adult women with HbA1c levels recorded from 2017 to 2022. Samples were classified as diabetic, prediabetic, or non-diabetic based on HbA1c and fasting blood glucose (FBG) levels for distribution analysis without impacting model training. Support Vector Machines, Linear Regression, Random Forest, and K-Nearest Neighbor algorithms as machine learning (ML) methods were used to predict HbA1c levels. Following the training of the model, HbA1c values were predicted for the IDA samples using the trained model. According to our results, there has been a 0.1 unit change in HbA1c values, which has resulted in a clinical decision change in some patients. Using ML to analyze HbA1c results in women with IDA may unveil distinctions among patients whose HbA1c values hover near critical medical decision thresholds. This intersection of technology and laboratory science holds promise for enhancing precision in medical decision-making processes.

Severe Hyperthermia in Mountaineering: Coincidence of Heat Stroke and Infection.

Heat illness is a condition that is sometimes seen in those undertaking physical activities. This case report focuses on a female hiker who developed heat stroke during a trek in the Dachstein region of Upper Austria. The patient's presentation was initially unclear and could only be confirmed by the use of a thermometer. This had a significant impact on the medical decision-making process during a complex rescue operation.

Implementation and Execution of Big Data-based Studies in Ophthalmology within the Framework of the GDPR.

The processing of the retrospective data pool for ophthalmology holds huge potential, especially for the research sector. "Big Data" enables medical science to draw conclusions for the future from historical data. Based on the evaluation of such data, algorithms could be trained, for instance, that are capable of making decisions with the help of artificial intelligence. As a result, the medical decision-making process on certain issues could be accelerated, enriched in qualitative and quantitative terms, or even completely be taken over. Ophthalmology is a rapidly evolving field. Due to the multitude of partly automated medical imaging technologies and the predestined accessibility of the eye for such technologies, ophthalmology, similarly to radiology or dermatology, is well suited for artificial intelligence-assisted image data analysis and the frequently associated initiation of diagnosis and therapy. Meanwhile, numerous studies exist based on AI-assisted image data analysis of ophthalmological image data. To the extent that the algorithms filter out results from the data pools by means of calculation rules and are even capable of making independent decisions on the basis of decision trees, the enormous benefit and, simultaneously, the profit for scientific research is quite obvious. Accordingly, it would be desirable to have unrestricted and comprehensive possibility of corresponding data processing of these health data for ophthalmological research. In spite of the potential for ophthalmology, for which there is only fragmentary evidence, the question of practical feasibility arises. In particular, the legal requirements and limits of European and national data protection law must be taken into account, prior to any unreflected processing of personal (health) data. Only by doing so can we circumvent existing obstacles and pitfalls, which can lead to severe fines. Most important are to date the requirements of two legal texts: The General Data Protection Regulation (GDPR) and the Federal Data Protection Act (BDSG). This article provides an overview of the relevant legal requirements applicable in the field of ophthalmology and highlights the major pitfalls and implementation requirements.

Leveraging graph neural networks for supporting automatic triage of patients

Patient triage is crucial in emergency departments, ensuring timely and appropriate care based on correctly evaluating the emergency grade of patient conditions. Triage methods are generally performed by human operator based on her own experience and information that are gathered from the patient management process. Thus, it is a process that can generate errors in emergency-level associations. Recently, Traditional triage methods heavily rely on human decisions, which can be subjective and prone to errors. A growing interest has recently been focused on leveraging artificial intelligence (AI) to develop algorithms to maximize information gathering and minimize errors in patient triage processing. We define and implement an AI-based module to manage patients’ emergency code assignments in emergency departments. It uses historical data from the emergency department to train the medical decision-making process. Data containing relevant patient information, such as vital signs, symptoms, and medical history, accurately classify patients into triage categories. Experimental results demonstrate that the proposed algorithm achieved high accuracy outperforming traditional triage methods. By using the proposed method, we claim that healthcare professionals can predict severity index to guide patient management processing and resource allocation.

Establishing Healthcare Discrimination: An Analysis of Scandinavian Equality Boards

Discrimination in healthcare is a pervasive issue faced by patients, affecting their access to treatment and overall well-being. This article examines the forms of healthcare discrimination recognised by Scandinavian equality boards through a comparative analysis of their decisions. While social science studies have established the existence of discrimination based on ethnicity, race, gender, sexuality, and age, proving such discrimination in legal terms poses significant challenges. An analysis of board decisions reveals that patients face barriers in establishing legally actionable discrimination, as perceived discriminatory conduct may not meet the criteria for legal claims. Additionally, equality boards are often hesitant to intervene in medical decision-making processes, further complicating the path to legal recourse. Lack of evidentiary support, especially in cases of unconscious bias, makes it difficult for some patients to substantiate claims of discrimination. The findings underscore the complexities of addressing healthcare discrimination through legal means. To effectively combat discrimination, there is a need to clarify the goals of discrimination law in the healthcare context and consider its future application within the broader context of human rights and equality.

Rethinking Human-AI Collaboration in Complex Medical Decision Making: A Case Study in Sepsis Diagnosis.

Today's AI systems for medical decision support often succeed on benchmark datasets in research papers but fail in real-world deployment. This work focuses on the decision making of sepsis, an acute life-threatening systematic infection that requires an early diagnosis with high uncertainty from the clinician. Our aim is to explore the design requirements for AI systems that can support clinical experts in making better decisions for the early diagnosis of sepsis. The study begins with a formative study investigating why clinical experts abandon an existing AI-powered Sepsis predictive module in their electrical health record (EHR) system. We argue that a human-centered AI system needs to support human experts in the intermediate stages of a medical decision-making process (e.g., generating hypotheses or gathering data), instead of focusing only on the final decision. Therefore, we build SepsisLab based on a state-of-the-art AI algorithm and extend it to predict the future projection of sepsis development, visualize the prediction uncertainty, and propose actionable suggestions (i.e., which additional laboratory tests can be collected) to reduce such uncertainty. Through heuristic evaluation with six clinicians using our prototype system, we demonstrate that SepsisLab enables a promising human-AI collaboration paradigm for the future of AI-assisted sepsis diagnosis and other high-stakes medical decision making.

Validation of utstein-based score to predict return of spontaneous circulation (UB-ROSC) in patients with out-of-hospital cardiac arrest

Abstract Funding Acknowledgements None. Background and aims The Utstein Based-ROSC (UB-ROSC) score has been developed to predict ROSC in OHCA victims. Aim of the study was to validate the UB-ROSC score using two Utstein-based OHCA registries: the SWiss REgistry of Cardiac Arrest (SWISSRECA) and the Lombardia Cardiac Arrest Registry (Lombardia CARe), northern Italy. Methods Consecutive patients with OHCA of any etiology occurring between January 1st, 2019 and December 31st 2021 were included in a prospectively designed validation study. UB-ROSC score was computed for each patient and categorized in one of 3 subgroups:low, medium or high likelihood of ROSC according to the UB-ROSC cut-offs (≤-19; -18 to 12; ≥13). To assess the performance of the UB-ROSC score in this new cohort, we assessed both discrimination and calibration. The score was plotted against the survival to hospital admission. Results A total of 12,577 patients were included in the study. A sustained ROSC was obtained in 2,719 patients (22%). The UB-ROSC model resulted well calibrated and showed a good discrimination (AUC 0.71, 95% CI 0.70-0.72). In the low likelihood subgroup of UB-ROSC, only 9% of patients achieved ROSC, whereas the proportion raised to 36% for a score between -18 and 12 (OR 5.0, 95% CI 2.9-8.6, P<0.001) and to 85% for a score ≥ 13 (OR 49.4, 95%CI 14.3-170.6, P <0.001). Conclusions UB-ROSC score represents a reliable tool to predict ROSC probability in OHCA patients. Its application may help the medical decision-making process, providing a realistic stratification of the probability for ROSC.

의료진과의 커뮤니케이션이 장애인 삶의 만족에 미치는 영향: 가족건강성의 매개효과

The purpose of this study is to examine the relationship between communication with healthcare professionals and life satisfaction among individuals with disabilities, and to verify the mediating effect of family strength in this relationship. For this purpose, data from the 3rd wave (2020) Disability and Life Dynamics Panel conducted by the Korea Disabled People’s Development Institute in 2020 were utilized, with a sample of 3,937 individuals with disabilities aged 19 and above. The analysis employed Process Macro to verify the mediating effects. The main findings of the study are as follows. Firstly, higher communication with healthcare professionals had a significant positive effect on life satisfaction. Secondly, increased communication with healthcare professionals also had a significant positive effect on family strength. Thirdly, family strength demonstrated a complete mediating effect in the relationship between communication with healthcare professionals and life satisfaction. Based on the research results and discussions, there is a suggested need for services that guarantee and support the participation of disabled individuals and their families in the medical decision-making process.

Evaluating the accuracy of ChatGPT-4 in predicting ASA scores: A prospective multicentric study ChatGPT-4 in ASA score prediction

BackgroundThis study investigates the potential of ChatGPT-4, developed by OpenAI, in enhancing medical decision-making processes, particularly in preoperative assessments using the American Society of Anesthesiologists (ASA) scoring system. The ASA score, a critical tool in evaluating patients' health status and anesthesia risks before surgery, categorizes patients from I to VI based on their overall health and risk factors. Despite its widespread use, determining accurate ASA scores remains a subjective process that may benefit from AI-supported assessments. This research aims to evaluate ChatGPT-4's capability to predict ASA scores accurately compared to expert anesthesiologists' assessments. MethodsIn this prospective multicentric study, ethical board approval was obtained, and the study was registered with clinicaltrials.gov (NCT06321445). We included 2851 patients from anesthesiology outpatient clinics, spanning neonates to all age groups and genders, with ASA scores between I-IV. Exclusion criteria were set for ASA V and VI scores, emergency operations, and insufficient information for ASA score determination. Data on patients' demographics, health conditions, and ASA scores by anesthesiologists were collected and anonymized. ChatGPT-4 was then tasked with assigning ASA scores based on the standardized patient data. ResultsOur results indicate a high level of concordance between ChatGPT-4 predictions and anesthesiologists' evaluations, with Cohen's kappa analysis showing a kappa value of 0.858 (p = 0.000). While the model demonstrated over 90% accuracy in predicting ASA scores I to III, it showed a notable variance in ASA IV scores, suggesting a potential limitation in assessing patients with more complex health conditions. DiscussionThe findings suggest that ChatGPT-4 can significantly contribute to the medical field by supporting anesthesiologists in preoperative assessments. This study not only demonstrates ChatGPT-4's efficacy in medical data analysis and decision-making but also opens new avenues for AI applications in healthcare, particularly in enhancing patient safety and optimizing surgical outcomes. Further research is needed to refine AI models for complex case assessments and integrate them seamlessly into clinical workflows.

Cancer Risk Identification using Machine Learning

In this comprehensive study, we explore the SEER (Surveillance, Epidemiology, and End Result) dataset to meticulously craft a predictive model aimed at understanding patient survivability, focusing keenly on outcomes like patient survival diagnosis and treatments. Employing a good approach involving rigorous data cleaning, intricate feature extraction, and detailed correlation analysis, we identify the dominant attributes that significantly influence patient outcomes. Our methodology integrates classical machine learning models, including decision trees and random forests, with modern techniques such as neural networks. This mix of methodologies allows us to accurately predict patient survivability. Furthermore, our study delves into the intricate relationships between attributes, models, and algorithms, aiming to identify the dominant factors that influence the outcomes. Our groundbreaking findings underscore the enormous potential of integrating these dominant attributes, paving the way for the creation of exceptionally robust predictive models. These models will substantially enhance medical decision-making processes and, in turn, elevate the overall quality of patient care. Keywords - SEER dataset, patient survivability, machine learning, decision trees, random forests, neural networks, data cleaning, feature extraction, clinical data, medical decision-making.

ResNet50-Boosted UNet for Improved Liver Segmentation Accuracy

Segmentation of the liver from abdominal CT images is difficult due to changes in form, density, and the presence of malignancies. This research describes a novel strategy to improve segmentation accuracy that uses UNet as a foundation architecture and ResNet50 as a backbone architecture. This integrated design automates feature selection and spatial awareness, overcoming limitations in previous models. Experimental evaluations using the LiTS dataset show higher performance. Specifically, using the LiTS dataset, our algorithm achieves a remarkable foreground accuracy of 99.81% in liver segmentation. These results outperform existing approaches, demonstrating UNet and ResNet50's potential as valuable tools for precise liver segmentation in clinical situations. The suggested system shows promise for application in diverse medical imaging tasks other than liver segmentation, demonstrating its versatility and effectiveness in enhancing machine-assisted medical diagnostics and decision-making processes.

Wheel Replacing Pyramid: Better Paradigm Representing Totality of Evidence-Based Medicine.

Evidence-based medicine (EBM), as originally conceived, used all types of peer-reviewed evidence to guide medical practice and decision-making. During the SARS-CoV-2 Coronavirus disease (COVID-19) pandemic, the standard usage of EBM, modeled by the Evidence-Based Medicine Pyramid, undermined EBM by incorrectly using pyramid levels to assign relative quality. The resulting pyramid-based thinking is biased against reports both in levels beneath randomized control trials (RCTs) and those omitted from the pyramid entirely. Thus, much of the evidence was ignored. Our desire for a more encompassing and effective medical decision-making process to apply to repurposed drugs led us to develop an alternative to the EBM Pyramid for EBM. Herein, we propose the totality of evidence (T-EBM) wheel. To create an easily understood graphic that models EBM by incorporating all peer-reviewed evidence that applies to both new and repurposed medicines, and to demonstrate its potential utility using ivermectin as a case study. The graphics were produced using Microsoft Office Visio Professional 2003 except for part of the T-EBM wheel sunburst chart, which was produced using Microsoft 365 Excel. For the case study, PubMed® was used by searching for peer-reviewed reports containing "ivermectin" and either "covid" or "sars" in the title. Reports were filtered for those using ivermectin-based protocols in the treatment of COVID-19. The resulting 265 reports were evaluated for their study design types and treatment outcomes. The three-ringed graphical T-EBM wheel was composed of two inner rings showing all types of reports and an outer ring showing outcomes for each type. The T-EBM wheel avoids the biases of the EBM Pyramid and includes all types of reports in the pyramid along with reports such as population and mechanistic studies. In both early and late stages of medical emergencies, pyramid-based thinking may overlook indications of efficacy in regions of the T-EBM wheel beyond RCTs. This is especially true when searching for ways to prevent and treat a novel disease with repurposed therapeutics before RCTs, safety assessments, and mechanisms of action of novel therapeutics are established. As such, T-EBM Wheels should replace the EBM Pyramids in medical decision-making and education. T-EBM Wheels can be expanded upon by implementing multiple outer rings, one for each different kind of outcome (efficacy, safety, etc.). A T-EBM Wheel can be created for any proprietary or generic medicine. The ivermectin (IVM) T-EBM Wheel displays the efficacy of IVM-based treatments of COVID-19 in a color-coded graphic, visualizing each type of evidence and the proportions of each of their outcomes (positive, inconclusive, negative).

Merging Ontologies and Data from Electronic Health Records

The Electronic Health Record (EHR) is a system for collecting and storing patient medical records as data that can be mechanically accessed, hence facilitating and assisting the medical decision-making process. EHRs exist in several formats, and each format lists thousands of keywords to classify patients data. The keywords are specific and are medical jargon; hence, data classification is very accurate. As the keywords constituting the formats of medical records express concepts by means of specific jargon without definitions or references, their proper use is left to clinicians and could be affected by their background, hence the interpretation of data could become slow or less accurate than that desired. This article presents an approach that accurately relates data in EHRs to ontologies in the medical realm. Thanks to ontologies, clinicians can be assisted when writing or analysing health records, e.g., our solution promptly suggests rigorous definitions for scientific terms, and automatically connects data spread over several parts of EHRs. The first step of our approach consists of converting selected data and keywords from several EHR formats into a format easier to parse, then the second step is merging the extracted data with specialised medical ontologies. Finally, enriched versions of the medical data are made available to professionals. The proposed approach was validated by taking samples of medical records and ontologies in the real world. The results have shown both versatility on handling data, precision of query results, and appropriate suggestions for relations among medical records.

Is continuous chemotherapy necessary for elderly patients with chemosensitive bone-metastatic non-small cell lung cancer?

Background: Bone metastases from non-small cell lung cancer pose a significant threat to elderly patients, with a certain number succumbing to this condition annually. For patients who have experienced tumor reduction post-chemotherapy, the dilemma of whether to continue chemotherapy or not becomes a confounding factor in the medical decision-making process for their families, considering the ability of elderly patients to tolerate further chemotherapy.

Validation of Utstein-Based score to predict return of spontaneous circulation (UB-ROSC) in patients with out-of-hospital cardiac arrest

Background and aimsThe Utstein Based-ROSC (UB-ROSC) score has been developed to predict ROSC in OHCA victims. Aim of the study was to validate the UB-ROSC score using two Utstein-based OHCA registries: the SWiss REgistry of Cardiac Arrest (SWISSRECA) and the Lombardia Cardiac Arrest Registry (Lombardia CARe), northern Italy. MethodsConsecutive patients with OHCA of any etiology occurring between January 1st, 2019 and December 31st 2021 were included in this retrospective validation study. UB-ROSC score was computed for each patient and categorized in one of three subgroups: low, medium or high likelihood of ROSC according to the UB-ROSC cut-offs (≤−19; −18 to 12; ≥13). To assess the performance of the UB-ROSC score in this new cohort, we assessed both discrimination and calibration. The score was plotted against the survival to hospital admission. ResultsA total of 12.577 patients were included in the study. A sustained ROSC was obtained in 2.719 patients (22%). The UB-ROSC model resulted well calibrated and showed a good discrimination (AUC 0.71, 95% CI 0.70–0.72). In the low likelihood subgroup of UB-ROSC, only 10% of patients achieved ROSC, whereas the proportion raised to 36% for a score between −18 and 12 (OR 5.0, 95% CI 2.9–8.6, p < 0.001) and to 85% for a score ≥13 (OR 49.4, 95% CI 14.3–170.6, p < 0.001). ConclusionsUB-ROSC score represents a reliable tool to predict ROSC probability in OHCA patients. Its application may help the medical decision-making process, providing a realistic stratification of the probability for ROSC.

Factors Affecting Treatment Selection Among Patients With Hidradenitis Suppurativa

Despite the US Food and Drug Administration's approval of adalimumab for the treatment of hidradenitis suppurativa (HS), prescription rates remain low, indicating a critical gap between evidence-based guidelines and clinical practice. Understanding the medical decision-making process that these patients use when considering biologic agents and other HS therapies may uncover opportunities for improved patient-physician communication and HS disease control. To elucidate factors that affect the medical decision-making process for patients with HS, with an emphasis on biologic therapies. Open-ended semistructured interviews were conducted with English-speaking adults with HS (aged ≥18 years) recruited from 2 dermatology clinics that are part of Emory University School of Medicine in Atlanta, Georgia. All participants had an average 7-day pain score of 1 or higher on a 0- to 10-point numeric rating scale. Surveys were conducted between November 2019 and March 2020, and data were analyzed from December 2021 to August 2022. Data collection continued until thematic saturation was reached at 21 interviews. A total of 21 participants (median [IQR] age, 38.5 [27.9-43.4] years; 16 females [76%]) were included in the analysis. Almost all participants (96%) had Hurley stage II or III disease, and 15 (71%) had a history of adalimumab use. Suffering threshold, perceptions of treatment risk, treatment fatigue, disease understanding, and sources of information (included dermatologists, the internet, advertisements, and friends and loved ones) were identified as factors affecting participants' decisions to initiate new treatments for HS. Results of this qualitative study suggest that mitigating misconceptions about treatment risk, identifying gaps in disease knowledge, and emphasizing early treatment to prevent scarring and disease progression may empower patients with HS to engage in treatment planning and to try new therapies.

Understanding Social, Cultural, and Religious Factors Influencing Medical Decision-Making on BRCA1/2 Genetic Testing in the Orthodox Jewish Community

Introduction: Although the prevalence of a pathogenic variant in the BRCA1 and BRCA2 genes is about 1:400 (0.25%) in the general population, the prevalence is as high as 1:40 (2.5%) among the Ashkenazi Jewish population. Despite cost-effective preventive measures for mutation carriers, Orthodox Jews constitute a cultural and religious group that requires different approaches to BRCA1 and BRCA2 genetic testing relative to other groups. This study analyzed a dialog of key stakeholders and community members to explore factors that influence decision-making about BRCA1 and BRCA2 genetic testing in the New York Orthodox Jewish community. Methods: Qualitative research methods, based on Grounded Theory and Narrative Research, were utilized to analyze the narrative data collected from 49 key stakeholders and community members. A content analysis was conducted to identify themes; inter-rater reliability was 71%. Results: Facilitators of genetic testing were a desire for preventive interventions and education, while barriers to genetic testing included negative emotions, feared impact on family/romantic relationships, cost, and stigma. Views differed on the role of religious leaders and healthcare professionals in medical decision-making. Education, health, and community were discussed as influential factors, and concerns were expressed about disclosure, implementation, and information needs. Conclusion: This study elicited the opinions of Orthodox Jewish women (decision-makers) and key stakeholders (influencers) who play critical roles in the medical decision-making process. The findings have broad implications for engaging community stakeholders within faith-based or culturally distinct groups to ensure better utilization of healthcare services for cancer screening and prevention designed to improve population health.

Opportunities, challenges and implications of medical tourism development in Hong Kong

AbstractThis study revealed two different sets of push and pull factors affecting the medical travel decision process of two groups of mainland Chinese to Hong Kong, including potential and experienced medical tourists. The relations between identified factors and their willingness of personal visit and recommendation were also investigated. Regarding the recommendation intention, interpersonal acquisition and personal needs satisfaction are mostly considered by travelers in psychological level while recognized high medical reception capacity and quality are also prioritized in the pull aspect. However, local medical service constraints, perceived quality of medical experience shaped by healthcare suppliers, and destination attributes determine the two groups' responses to personal visit intention. Besides, the advantages of developing medical tourism in Hong Kong are implicated as can‐be‐perceived unique cultural attribute, mass tourism fame as medical tourism development basis, and reputation for high‐quality care formed with unintentional or deliberate promotion from third parties and various marketing channels.

Fuzzy-Based Bioengineering System for Predicting and Diagnosing Diseases of the Nervous System Triggered by the Interaction of Industrial Frequency Electromagnetic Fields.

The study aims to enhance the standard of medical care for individuals working in the electric power industry who are exposed to industrial frequency electromagnetic fields and other relevant risk factors. This enhancement is sought through the integration of fuzzy mathematical models with contemporary information and intellectual technologies. The study addresses the challenges of forecasting and diagnosing illnesses within a specific demographic characterized by a combination of poorly formalized issues with interconnected conditions. To tackle this complexity, a methodological framework was developed for synthesizing hybrid fuzzy decision rules. This approach combines clinical expertise with artificial intelligence methodologies to promote innovative problem-solving strategies. Additionally, the researchers devised an original method to evaluate the body's protective capacity, which was integrated into these decision rules to enhance the precision and efficacy of medical decision-making processes. The research findings indicate that industrial frequency electromagnetic fields contribute to illnesses of societal significance. Additionally, it highlights that these effects are worsened by other risk factors such as adverse microclimates, noise, vibration, chemical exposure, and psychological stress. Diseases of the neurological, immunological, cardiovascular, genitourinary, respiratory, and digestive systems are caused by these variables in conjunction with unique physical traits. The development of mathematical models in this study makes it possible to detect and diagnose disorders in workers exposed to electromagnetic fields early on, especially those pertaining to the autonomic nervous system and heart rhythm regulation. The results can be used in clinical practice to treat personnel in the electric power industry since expert evaluation and modeling showed high confidence levels in decision-making accuracy.

A Guide to an Iterative Approach to Model-Based Decision Making in Health and Medicine: An Iterative Decision-Making Framework.

Decision makers frequently face decisions about optimal resource allocation. A model-based economic evaluation can be used to guide decision makers in their choices by systematically evaluating the magnitude of expected health effects and costs of decision options and by making trade-offs explicit. We provide a guide to an iterative approach to the medical decision-making process by following a coherent framework, and outline the overarching iterative steps of model-based decision making. We systematized the framework by performing three steps. First, we compiled the existing guidelines provided by the ISPOR-SMDM Modeling Good Research Practices Task Force, and the ISPOR ValueofInformation Task Force. Second, we identified other previous work related to frameworks and guidelines for model-based decision analyses through a literature search in PubMed. Third, we assessed the role of the evidence and iterative process in decision making and formalized key steps in a model-based decision-making framework. We provide guidance on an iterative approach to medical decision making by applying the compiled iterative model-based decision-making framework. The framework formally combines the decision problem conceptualization (Part I), the model conceptualization and development (Part II), and the process of model-based decision analysis (Part III). Following the overarching steps of the framework ensures compliance to the principles of evidence-based medicine and regular updates of the evidence, given that valueofinformation analysis represents an essential component of model-based decision analysis in the framework. Following the provided guide and the steps outlined in the framework can help inform various health care decisions, and therefore it has the potential to improve decision making.