Inigo Bermejo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Inigo Bermejo has a total of 91 co-authors. Here are the top co-authors by number of shared publications:
- Andre Dekker
Department of Radiation Oncology (Maastro), GROW Research Institute for Oncology and Reproduction, Maastricht University Medical Centre+, Maastricht, The Netherlands
9 shared publications - Anke Bruninx
Department of Radiation Oncology (Maastro), GROW Research Institute for Oncology and Reproduction, Maastricht University Medical Centre+, Maastricht, The Netherlands
6 shared publications - Bart Scheenstra
Department of Cardiothoracic Surgery, Heart and Vascular Center, Maastricht University Medical Center , Maastricht, Netherlands
4 shared publications Andre Dekker
Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre+, Maastricht, The Netherlands
3 shared publications- Arnoud W. J. van 'T Hof
Department of Cardiology, Maastricht University Medical Center, Maastricht, The Netherlands
3 shared publications - Catharina M. L. Zegers
Department of Radiation Oncology (MAASTRO), GROW Research Institute for Oncology and Reproduction, Maastricht University Medical Centre , Maastricht
3 shared publications
Latest Publications
- Open Access
- 8 August 2025
- Published by JMIR Publications Inc. in JMIR Research Protocols
- Vol. 14, e66068
Optimizing Cardiovascular Risk Management in Primary Care Using a Personalized eCoach Solution Enhanced by an Artificial Intelligence–Driven Clinical Prediction Model: Protocol from the Coronary Artery Disease Risk Estimation and Early Detection Consortium
Background: Atherosclerotic cardiovascular disease poses a heavy burden on the population’s health and health care costs. Identifying apparently healthy individuals at risk of developing cardiovascular diseases using clinical prediction models raises awareness, facilitates shared decision-making, and supports tailored management of disease prevention. In the CARRIER project, a personalized cardiovascular risk management (CVRM) eCoach approach is cocreated, in which identified individuals receive education, guidance, and monitoring to prevent atherosclerotic cardiovascular disease through existing interventions. In this approach, an artificial intelligence–driven clinical prediction model calculates the 10-year risk for atherosclerotic cardiovascular disease, which supports informed decision-making. Objective: This study aims to assess the effectiveness of our CVRM eCoach approach through a 10-year risk calculation of atherosclerotic cardiovascular disease, including risk factors contributing to this risk. Methods: This pretest-posttest interventional study provides the CVRM eCoach approach for 6 months to 100 apparently healthy individuals eligible for CVRM. The CVRM eCoach approach is a multicomponent eHealth solution, including a clinical prediction under intervention model that not only calculates the 10-year risk of cardiovascular disease through conventional risk factors (smoking, blood pressure, and lipid profile) and individual characteristics (age, gender, socioeconomic status, physical activity, and diet) but also calculates how the risk changes after hypothetical lifestyle or medical interventions. The CVRM eCoach approach includes features that encourage behavior change. Most of these features include goal setting, decision cards to help decide on an intervention, intervention monitoring, remote communication, and education, all accessible from one dashboard. A practice nurse or physician consults the individuals after risk calculation with the clinical prediction model and uses behavior change features, such as the decision cards, to support shared decision-making. Data are primarily collected via the eCoach, after which the 10-year risk for atherosclerotic cardiovascular disease and its components are analyzed using paired-sample analyses. Results: Recruitment began in March 2024 and will continue until 100 participants have been recruited, which is expected in 2025. Conclusions: We anticipate that our CVRM eCoach approach will be valuable in the primary prevention setting. During the crucial initial first months of habit formation, factors such as education, regular check-ups via the eCoach, and clear risk communication could support individuals in sustaining their medical or lifestyle interventions. We hypothesize that there will be a slight to moderate reduction in the 10-year risk of atherosclerotic cardiovascular disease, which over time will lead to significant health improvements on a larger scale. Trial Registration: CCMO NL84584.096.23; https://onderzoekmetmensen.nl/nl/trial/56578
- 8 August 2025
- Published by JMIR Publications Inc. in JMIR Research Protocols
- Vol. 14, e66068
Open AccessOptimizing Cardiovascular Risk Management in Primary Care Using a Personalized eCoach Solution Enhanced by an Artificial Intelligence–Driven Clinical Prediction Model: Protocol from the Coronary Artery Disease Risk Estimation and Early Detection Consortium
Background: Atherosclerotic cardiovascular disease poses a heavy burden on the population’s health and health care costs. Identifying apparently healthy individuals at risk of developing cardiovascular diseases using clinical prediction models raises awareness, facilitates shared decision-making, and supports tailored management of disease prevention. In the CARRIER project, a personalized cardiovascular risk management (CVRM) eCoach approach is cocreated, in which identified individuals receive education, guidance, and monitoring to prevent atherosclerotic cardiovascular disease through existing interventions. In this approach, an artificial intelligence–driven clinical prediction model calculates the 10-year risk for atherosclerotic cardiovascular disease, which supports informed decision-making. Objective: This study aims to assess the effectiveness of our CVRM eCoach approach through a 10-year risk calculation of atherosclerotic cardiovascular disease, including risk factors contributing to this risk. Methods: This pretest-posttest interventional study provides the CVRM eCoach approach for 6 months to 100 apparently healthy individuals eligible for CVRM. The CVRM eCoach approach is a multicomponent eHealth solution, including a clinical prediction under intervention model that not only calculates the 10-year risk of cardiovascular disease through conventional risk factors (smoking, blood pressure, and lipid profile) and individual characteristics (age, gender, socioeconomic status, physical activity, and diet) but also calculates how the risk changes after hypothetical lifestyle or medical interventions. The CVRM eCoach approach includes features that encourage behavior change. Most of these features include goal setting, decision cards to help decide on an intervention, intervention monitoring, remote communication, and education, all accessible from one dashboard. A practice nurse or physician consults the individuals after risk calculation with the clinical prediction model and uses behavior change features, such as the decision cards, to support shared decision-making. Data are primarily collected via the eCoach, after which the 10-year risk for atherosclerotic cardiovascular disease and its components are analyzed using paired-sample analyses. Results: Recruitment began in March 2024 and will continue until 100 participants have been recruited, which is expected in 2025. Conclusions: We anticipate that our CVRM eCoach approach will be valuable in the primary prevention setting. During the crucial initial first months of habit formation, factors such as education, regular check-ups via the eCoach, and clear risk communication could support individuals in sustaining their medical or lifestyle interventions. We hypothesize that there will be a slight to moderate reduction in the 10-year risk of atherosclerotic cardiovascular disease, which over time will lead to significant health improvements on a larger scale. Trial Registration: CCMO NL84584.096.23; https://onderzoekmetmensen.nl/nl/trial/56578
- Open Access
- 2 July 2025
- Published by Oxford University Press (OUP) in European Journal of Heart Failure
- Vol. 27 (8) , 1393-1399
Exploring Safety of Down-Titrating Diuretics in Heart Failure Management
Aims: Loop diuretics are widely used in heart failure (HF) for symptom relief. Guidelines advise treating patients with the lowest possible dose of loop diuretics to maintain euvolaemia, based on expert opinion only. However, data on the safety of this practice are scarce. This analysis aims to investigate the clinical course after changing loop diuretics in stable HF patients. Methods and results: A post-hoc analysis from the TIME-CHF study was conducted in 622 patients. Daily loop diuretic doses were meticulously recorded, resulting in 11 035 dose evaluations assessed. The frequency of relevant events within 30 days (hospitalization, death, dose change) following an up-titration, down-titration, or no change in diuretic therapy was calculated. Risk of hospitalization and deaths 30 days after down-titration was estimated after adjusting for congestion level. At baseline the cohort consisted mostly of males (59%), with a mean age of 77 years. Patients were highly symptomatic with 76% classified as New York Heart Association class III or IV. Within 30 days after a down-titration, diuretic dose necessitated an increase in 30.4% of cases, compared with 20.7% following up-titration and 8.0% on a stable dose. Hospitalization and death were significantly more frequent following down-titration (3.4% and 2% within 30 days, respectively) than with a stable dose (1% and 0.6%, p < 0.001). Similar hospitalization rates were observed after up-titration. The risk of hospitalization doubled and of death tripled after down-titration in patients with similar congestion levels. Conclusions: There is a significant risk that reduction in diuretic dose requires restart or increase of diuretics within a short period. Additionally, there may be a significant risk associated with diuretic dose reduction. Therefore, HF patients need to be closely monitored after down-titration of loop diuretic therapy.
- 2 July 2025
- Published by Oxford University Press (OUP) in European Journal of Heart Failure
- Vol. 27 (8) , 1393-1399
Open AccessExploring Safety of Down-Titrating Diuretics in Heart Failure Management
Aims: Loop diuretics are widely used in heart failure (HF) for symptom relief. Guidelines advise treating patients with the lowest possible dose of loop diuretics to maintain euvolaemia, based on expert opinion only. However, data on the safety of this practice are scarce. This analysis aims to investigate the clinical course after changing loop diuretics in stable HF patients. Methods and results: A post-hoc analysis from the TIME-CHF study was conducted in 622 patients. Daily loop diuretic doses were meticulously recorded, resulting in 11 035 dose evaluations assessed. The frequency of relevant events within 30 days (hospitalization, death, dose change) following an up-titration, down-titration, or no change in diuretic therapy was calculated. Risk of hospitalization and deaths 30 days after down-titration was estimated after adjusting for congestion level. At baseline the cohort consisted mostly of males (59%), with a mean age of 77 years. Patients were highly symptomatic with 76% classified as New York Heart Association class III or IV. Within 30 days after a down-titration, diuretic dose necessitated an increase in 30.4% of cases, compared with 20.7% following up-titration and 8.0% on a stable dose. Hospitalization and death were significantly more frequent following down-titration (3.4% and 2% within 30 days, respectively) than with a stable dose (1% and 0.6%, p < 0.001). Similar hospitalization rates were observed after up-titration. The risk of hospitalization doubled and of death tripled after down-titration in patients with similar congestion levels. Conclusions: There is a significant risk that reduction in diuretic dose requires restart or increase of diuretics within a short period. Additionally, there may be a significant risk associated with diuretic dose reduction. Therefore, HF patients need to be closely monitored after down-titration of loop diuretic therapy.
- Open Access
- 2 July 2025
- Published by Springer Nature in Diagnostic and Prognostic Research
- Vol. 9 (1) , 1-9
Development and temporal evaluation of sex-specific models to predict 4-year atherosclerotic cardiovascular disease risk based on age and neighbourhood characteristics in South Limburg, the Netherlands
Background: To improve screening for atherosclerotic cardiovascular disease (ASCVD), we aimed to develop and temporally evaluate sex-specific models to predict 4-year ASCVD risk in South Limburg based on age and neighbourhood characteristics concerning home address. Methods: We included 40- to 70-year-olds living in South Limburg on 1 January 2015 for model development, and 40- to 70-year-olds living in South Limburg on 1 January 2016 for model evaluation. We randomly sampled people selected in 1 year and in both years to create development and evaluation data sets. Follow-up of ASCVD and competing events (overall mortality excluding ASCVD) lasted until 31 December 2020. Candidate predictors were the individual’s age, the neighbourhood’s socio-economic status, and the neighbourhood’s particulate matter concentration. Using the evaluation data sets, we compared two model types, subdistribution and cause-specific hazard models, and eight model structures. Discrimination was assessed by the area under the receiver operating characteristic curve (AUROC). Calibration was assessed by calculating overall expected-observed ratios (E/O). For the final models, calibration plots were made additionally. Results: The development data sets consisted of 67,549 males (4-year cumulative ASCVD incidence: 3.08%) and 67,947 females (4-year cumulative ASCVD incidence: 1.50%). The evaluation data sets consisted of 66,068 males (4-year cumulative ASCVD incidence: 3.22%) and 66,231 females (4-year cumulative ASCVD incidence: 1.49%). For males, the AUROC of the final model equalled 0.6548. The E/O equalled 0.9466. For females, the AUROC equalled 0.6744. The E/O equalled 0.9838. Conclusions: The resulting model shows promise for further research. These models may be used for ASCVD screening in the future.
- 2 July 2025
- Published by Springer Nature in Diagnostic and Prognostic Research
- Vol. 9 (1) , 1-9
Open AccessDevelopment and temporal evaluation of sex-specific models to predict 4-year atherosclerotic cardiovascular disease risk based on age and neighbourhood characteristics in South Limburg, the Netherlands
Background: To improve screening for atherosclerotic cardiovascular disease (ASCVD), we aimed to develop and temporally evaluate sex-specific models to predict 4-year ASCVD risk in South Limburg based on age and neighbourhood characteristics concerning home address. Methods: We included 40- to 70-year-olds living in South Limburg on 1 January 2015 for model development, and 40- to 70-year-olds living in South Limburg on 1 January 2016 for model evaluation. We randomly sampled people selected in 1 year and in both years to create development and evaluation data sets. Follow-up of ASCVD and competing events (overall mortality excluding ASCVD) lasted until 31 December 2020. Candidate predictors were the individual’s age, the neighbourhood’s socio-economic status, and the neighbourhood’s particulate matter concentration. Using the evaluation data sets, we compared two model types, subdistribution and cause-specific hazard models, and eight model structures. Discrimination was assessed by the area under the receiver operating characteristic curve (AUROC). Calibration was assessed by calculating overall expected-observed ratios (E/O). For the final models, calibration plots were made additionally. Results: The development data sets consisted of 67,549 males (4-year cumulative ASCVD incidence: 3.08%) and 67,947 females (4-year cumulative ASCVD incidence: 1.50%). The evaluation data sets consisted of 66,068 males (4-year cumulative ASCVD incidence: 3.22%) and 66,231 females (4-year cumulative ASCVD incidence: 1.49%). For males, the AUROC of the final model equalled 0.6548. The E/O equalled 0.9466. For females, the AUROC equalled 0.6744. The E/O equalled 0.9838. Conclusions: The resulting model shows promise for further research. These models may be used for ASCVD screening in the future.
- Open Access
- 11 February 2025
- Published by JMIR Publications Inc. in JMIR Formative Research
- Vol. 9 (1) , e60095
Developing an ICD-10 Coding Assistant: Pilot Study Using RoBERTa and GPT-4 for Term Extraction and Description-Based Code Selection
Background: The International Classification of Diseases (ICD), developed by the World Health Organization, standardizes health condition coding to support health care policy, research, and billing, but artificial intelligence automation, while promising, still underperforms compared with human accuracy and lacks the explainability needed for adoption in medical settings. Objective: The potential of large language models for assisting medical coders in the ICD-10 coding was explored through the development of a computer-assisted coding system. This study aimed to augment human coding by initially identifying lead terms and using retrieval-augmented generation (RAG)–based methods for computer-assisted coding enhancement. Methods: The explainability dataset from the CodiEsp challenge (CodiEsp-X) was used, featuring 1000 Spanish clinical cases annotated with ICD-10 codes. A new dataset, CodiEsp-X-lead, was generated using GPT-4 to replace full-textual evidence annotations with lead term annotations. A Robustly Optimized BERT (Bidirectional Encoder Representations from Transformers) Pretraining Approach transformer model was fine-tuned for named entity recognition to extract lead terms. GPT-4 was subsequently employed to generate code descriptions from the extracted textual evidence. Using a RAG approach, ICD codes were assigned to the lead terms by querying a vector database of ICD code descriptions with OpenAI’s text-embedding-ada-002 model. Results: The fine-tuned Robustly Optimized BERT Pretraining Approach achieved an overall F1-score of 0.80 for ICD lead term extraction on the new CodiEsp-X-lead dataset. GPT-4-generated code descriptions reduced retrieval failures in the RAG approach by approximately 5% for both diagnoses and procedures. However, the overall explainability F1-score for the CodiEsp-X task was limited to 0.305, significantly lower than the state-of-the-art F1-score of 0.633. The diminished performance was partly due to the reliance on code descriptions, as some ICD codes lacked descriptions, and the approach did not fully align with the medical coder’s workflow. Conclusions: While lead term extraction showed promising results, the subsequent RAG-based code assignment using GPT-4 and code descriptions was less effective. Future research should focus on refining the approach to more closely mimic the medical coder’s workflow, potentially integrating the alphabetic index and official coding guidelines, rather than relying solely on code descriptions. This alignment may enhance system accuracy and better support medical coders in practice.
- 11 February 2025
- Published by JMIR Publications Inc. in JMIR Formative Research
- Vol. 9 (1) , e60095
Open AccessDeveloping an ICD-10 Coding Assistant: Pilot Study Using RoBERTa and GPT-4 for Term Extraction and Description-Based Code Selection
Background: The International Classification of Diseases (ICD), developed by the World Health Organization, standardizes health condition coding to support health care policy, research, and billing, but artificial intelligence automation, while promising, still underperforms compared with human accuracy and lacks the explainability needed for adoption in medical settings. Objective: The potential of large language models for assisting medical coders in the ICD-10 coding was explored through the development of a computer-assisted coding system. This study aimed to augment human coding by initially identifying lead terms and using retrieval-augmented generation (RAG)–based methods for computer-assisted coding enhancement. Methods: The explainability dataset from the CodiEsp challenge (CodiEsp-X) was used, featuring 1000 Spanish clinical cases annotated with ICD-10 codes. A new dataset, CodiEsp-X-lead, was generated using GPT-4 to replace full-textual evidence annotations with lead term annotations. A Robustly Optimized BERT (Bidirectional Encoder Representations from Transformers) Pretraining Approach transformer model was fine-tuned for named entity recognition to extract lead terms. GPT-4 was subsequently employed to generate code descriptions from the extracted textual evidence. Using a RAG approach, ICD codes were assigned to the lead terms by querying a vector database of ICD code descriptions with OpenAI’s text-embedding-ada-002 model. Results: The fine-tuned Robustly Optimized BERT Pretraining Approach achieved an overall F1-score of 0.80 for ICD lead term extraction on the new CodiEsp-X-lead dataset. GPT-4-generated code descriptions reduced retrieval failures in the RAG approach by approximately 5% for both diagnoses and procedures. However, the overall explainability F1-score for the CodiEsp-X task was limited to 0.305, significantly lower than the state-of-the-art F1-score of 0.633. The diminished performance was partly due to the reliance on code descriptions, as some ICD codes lacked descriptions, and the approach did not fully align with the medical coder’s workflow. Conclusions: While lead term extraction showed promising results, the subsequent RAG-based code assignment using GPT-4 and code descriptions was less effective. Future research should focus on refining the approach to more closely mimic the medical coder’s workflow, potentially integrating the alphabetic index and official coding guidelines, rather than relying solely on code descriptions. This alignment may enhance system accuracy and better support medical coders in practice.
- Open Access
- 31 January 2025
- Published by Wiley in Cancer Medicine
- Vol. 14 (3) , e70458
Lung Cancer Detection Using Bayesian Networks: A Retrospective Development and Validation Study on a Danish Population of High‐Risk Individuals
Background: Lung cancer (LC) is the top cause of cancer deaths globally, prompting many countries to adopt LC screening programs. While screening typically relies on age and smoking intensity, more efficient risk models exist. We devised a Bayesian network (BN) for LC detection, testing its resilience with varying degrees of missing data and comparing it to a prior machine learning (ML) model.Methods: We analyzed data from 9940 patients referred for LC assessment in Southern Denmark from 2009 to 2018. Variables included age, sex, smoking, and lab results. Our experiments varied missing data (0%–30%), BN structure (expert‐based vs. data‐driven), and discretization method (standard vs. data‐driven).Results: Across all missing data levels, area under the curve (AUC) remained steady, ranging from 0.737 to 0.757, compared to the ML model's AUC of 0.77. BN structure and discretization method had minimal impact on performance. BNs were well calibrated overall, with a net benefit in decision curve analysis when predicted risk exceeded 5%.Conclusion: BN models showed resilience with up to 30% missing values. Moreover, these BNs exhibited similar performance, calibration, and clinical utility compared to the machine learning model developed using the same dataset. Considering their effectiveness in handling missing data, BNs emerge as a relevant method for the development of future lung cancer detection models.
- 31 January 2025
- Published by Wiley in Cancer Medicine
- Vol. 14 (3) , e70458
Open AccessLung Cancer Detection Using Bayesian Networks: A Retrospective Development and Validation Study on a Danish Population of High‐Risk Individuals
Background: Lung cancer (LC) is the top cause of cancer deaths globally, prompting many countries to adopt LC screening programs. While screening typically relies on age and smoking intensity, more efficient risk models exist. We devised a Bayesian network (BN) for LC detection, testing its resilience with varying degrees of missing data and comparing it to a prior machine learning (ML) model.Methods: We analyzed data from 9940 patients referred for LC assessment in Southern Denmark from 2009 to 2018. Variables included age, sex, smoking, and lab results. Our experiments varied missing data (0%–30%), BN structure (expert‐based vs. data‐driven), and discretization method (standard vs. data‐driven).Results: Across all missing data levels, area under the curve (AUC) remained steady, ranging from 0.737 to 0.757, compared to the ML model's AUC of 0.77. BN structure and discretization method had minimal impact on performance. BNs were well calibrated overall, with a net benefit in decision curve analysis when predicted risk exceeded 5%.Conclusion: BN models showed resilience with up to 30% missing values. Moreover, these BNs exhibited similar performance, calibration, and clinical utility compared to the machine learning model developed using the same dataset. Considering their effectiveness in handling missing data, BNs emerge as a relevant method for the development of future lung cancer detection models.
- Open Access
A Bayesian Network Approach to Lung Cancer Screening: Assessing the Impact of Data Quantity, Quality, and the Combination of Data from Danish Electronic Health Records
Background/Objectives: Lung cancer (LC) is the leading cause of cancer mortality, making early diagnosis essential. While LC screening trials are underway globally, optimal prediction models and inclusion criteria are still lacking. This study aimed to develop and evaluate Bayesian Network (BN) models for LC risk prediction using a decade of data from Denmark. The primary goal was to assess BN performance on datasets varying in size and completeness, simulate real-world screening scenarios, and identify the most valuable data sources for LC screening. Methods: The study included 38,944 patients evaluated for LC, with 11,284 (29%) diagnosed. Data on comorbidities, medications, and general practice were available for the entire cohort, while laboratory results, smoking habits, and other variables were only available for subsets. The cohort was divided into four subsets based on data availability, and BNs were trained and validated across these subsets using cross-validation and external validation. To determine the optimal combination of variables, all possible data combinations were evaluated on the samples that contained all the variables (n = 5587). Results: A model trained on the small, complete dataset (AUC 0.78) performed similarly on a larger dataset with 21% missing data (AUC 0.78). Performance dropped when 39% of data were missing (AUC 0.67), resulting in informative variables missing completely in the dataset. Laboratory results and smoking data were the most informative, significantly outperforming models based only on age and smoking status (AUC 0.70). Conclusions: BN models demonstrated moderate to strong predictive performance, even with incomplete data, highlighting the potential value of incorporating laboratory results in LC screening programs.
Open AccessA Bayesian Network Approach to Lung Cancer Screening: Assessing the Impact of Data Quantity, Quality, and the Combination of Data from Danish Electronic Health Records
Background/Objectives: Lung cancer (LC) is the leading cause of cancer mortality, making early diagnosis essential. While LC screening trials are underway globally, optimal prediction models and inclusion criteria are still lacking. This study aimed to develop and evaluate Bayesian Network (BN) models for LC risk prediction using a decade of data from Denmark. The primary goal was to assess BN performance on datasets varying in size and completeness, simulate real-world screening scenarios, and identify the most valuable data sources for LC screening. Methods: The study included 38,944 patients evaluated for LC, with 11,284 (29%) diagnosed. Data on comorbidities, medications, and general practice were available for the entire cohort, while laboratory results, smoking habits, and other variables were only available for subsets. The cohort was divided into four subsets based on data availability, and BNs were trained and validated across these subsets using cross-validation and external validation. To determine the optimal combination of variables, all possible data combinations were evaluated on the samples that contained all the variables (n = 5587). Results: A model trained on the small, complete dataset (AUC 0.78) performed similarly on a larger dataset with 21% missing data (AUC 0.78). Performance dropped when 39% of data were missing (AUC 0.67), resulting in informative variables missing completely in the dataset. Laboratory results and smoking data were the most informative, significantly outperforming models based only on age and smoking status (AUC 0.70). Conclusions: BN models demonstrated moderate to strong predictive performance, even with incomplete data, highlighting the potential value of incorporating laboratory results in LC screening programs.
- Open Access
- 3 September 2024
- Published by JMIR Publications Inc. in JMIR Preprints
Optimizing Cardiovascular Risk Management in Primary Care Using a Personalized eCoach Solution Enhanced by an Artificial Intelligence–Driven Clinical Prediction Model: Protocol from the Coronary Artery Disease Risk Estimation and Early Detection Consortium (Preprint)
BACKGROUND Atherosclerotic cardiovascular disease poses a heavy burden on the population’s health and health care costs. Identifying apparently healthy individuals at risk of developing cardiovascular diseases using clinical prediction models raises awareness, facilitates shared decision-making, and supports tailored management of disease prevention. In the CARRIER project, a personalized cardiovascular risk management (CVRM) eCoach approach is cocreated, in which identified individuals receive education, guidance, and monitoring to prevent atherosclerotic cardiovascular disease through existing interventions. In this approach, an artificial intelligence–driven clinical prediction model calculates the 10-year risk for atherosclerotic cardiovascular disease, which supports informed decision-making. OBJECTIVE This study aims to assess the effectiveness of our CVRM eCoach approach through a 10-year risk calculation of atherosclerotic cardiovascular disease, including risk factors contributing to this risk. METHODS This pretest-posttest interventional study provides the CVRM eCoach approach for 6 months to 100 apparently healthy individuals eligible for CVRM. The CVRM eCoach approach is a multicomponent eHealth solution, including a clinical prediction under intervention model that not only calculates the 10-year risk of cardiovascular disease through conventional risk factors (smoking, blood pressure, and lipid profile) and individual characteristics (age, gender, socioeconomic status, physical activity, and diet) but also calculates how the risk changes after hypothetical lifestyle or medical interventions. The CVRM eCoach approach includes features that encourage behavior change. Most of these features include goal setting, decision cards to help decide on an intervention, intervention monitoring, remote communication, and education, all accessible from one dashboard. A practice nurse or physician consults the individuals after risk calculation with the clinical prediction model and uses behavior change features, such as the decision cards, to support shared decision-making. Data are primarily collected via the eCoach, after which the 10-year risk for atherosclerotic cardiovascular disease and its components are analyzed using paired-sample analyses. RESULTS Recruitment began in March 2024 and will continue until 100 participants have been recruited, which is expected in 2025. CONCLUSIONS We anticipate that our CVRM eCoach approach will be valuable in the primary prevention setting. During the crucial initial first months of habit formation, factors such as education, regular check-ups via the eCoach, and clear risk communication could support individuals in sustaining their medical or lifestyle interventions. We hypothesize that there will be a slight to moderate reduction in the 10-year risk of atherosclerotic cardiovascular disease, which over time will lead to significant health improvements on a larger scale. CLINICALTRIAL CCMO NL84584.096.23; https://onderzoekmetmensen.nl/nl/trial/56578
- 3 September 2024
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessOptimizing Cardiovascular Risk Management in Primary Care Using a Personalized eCoach Solution Enhanced by an Artificial Intelligence–Driven Clinical Prediction Model: Protocol from the Coronary Artery Disease Risk Estimation and Early Detection Consortium (Preprint)
BACKGROUND Atherosclerotic cardiovascular disease poses a heavy burden on the population’s health and health care costs. Identifying apparently healthy individuals at risk of developing cardiovascular diseases using clinical prediction models raises awareness, facilitates shared decision-making, and supports tailored management of disease prevention. In the CARRIER project, a personalized cardiovascular risk management (CVRM) eCoach approach is cocreated, in which identified individuals receive education, guidance, and monitoring to prevent atherosclerotic cardiovascular disease through existing interventions. In this approach, an artificial intelligence–driven clinical prediction model calculates the 10-year risk for atherosclerotic cardiovascular disease, which supports informed decision-making. OBJECTIVE This study aims to assess the effectiveness of our CVRM eCoach approach through a 10-year risk calculation of atherosclerotic cardiovascular disease, including risk factors contributing to this risk. METHODS This pretest-posttest interventional study provides the CVRM eCoach approach for 6 months to 100 apparently healthy individuals eligible for CVRM. The CVRM eCoach approach is a multicomponent eHealth solution, including a clinical prediction under intervention model that not only calculates the 10-year risk of cardiovascular disease through conventional risk factors (smoking, blood pressure, and lipid profile) and individual characteristics (age, gender, socioeconomic status, physical activity, and diet) but also calculates how the risk changes after hypothetical lifestyle or medical interventions. The CVRM eCoach approach includes features that encourage behavior change. Most of these features include goal setting, decision cards to help decide on an intervention, intervention monitoring, remote communication, and education, all accessible from one dashboard. A practice nurse or physician consults the individuals after risk calculation with the clinical prediction model and uses behavior change features, such as the decision cards, to support shared decision-making. Data are primarily collected via the eCoach, after which the 10-year risk for atherosclerotic cardiovascular disease and its components are analyzed using paired-sample analyses. RESULTS Recruitment began in March 2024 and will continue until 100 participants have been recruited, which is expected in 2025. CONCLUSIONS We anticipate that our CVRM eCoach approach will be valuable in the primary prevention setting. During the crucial initial first months of habit formation, factors such as education, regular check-ups via the eCoach, and clear risk communication could support individuals in sustaining their medical or lifestyle interventions. We hypothesize that there will be a slight to moderate reduction in the 10-year risk of atherosclerotic cardiovascular disease, which over time will lead to significant health improvements on a larger scale. CLINICALTRIAL CCMO NL84584.096.23; https://onderzoekmetmensen.nl/nl/trial/56578
- Open Access
- 22 March 2023
- Published by JMIR Publications Inc. in JMIR Formative Research
- Vol. 7 (1) , e38125
How Natural Language Processing Can Aid With Pulmonary Oncology Tumor Node Metastasis Staging From Free-Text Radiology Reports: Algorithm Development and Validation
Background: Natural language processing (NLP) is thought to be a promising solution to extract and store concepts from free text in a structured manner for data mining purposes. This is also true for radiology reports, which still consist mostly of free text. Accurate and complete reports are very important for clinical decision support, for instance, in oncological staging. As such, NLP can be a tool to structure the content of the radiology report, thereby increasing the report’s value. Objective: This study describes the implementation and validation of an N-stage classifier for pulmonary oncology. It is based on free-text radiological chest computed tomography reports according to the tumor, node, and metastasis (TNM) classification, which has been added to the already existing T-stage classifier to create a combined TN-stage classifier. Methods: SpaCy, PyContextNLP, and regular expressions were used for proper information extraction, after additional rules were set to accurately extract N-stage. Results: The overall TN-stage classifier accuracy scores were 0.84 and 0.85, respectively, for the training (N=95) and validation (N=97) sets. This is comparable to the outcomes of the T-stage classifier (0.87-0.92). Conclusions: This study shows that NLP has potential in classifying pulmonary oncology from free-text radiological reports according to the TNM classification system as both the T- and N-stages can be extracted with high accuracy.
- 22 March 2023
- Published by JMIR Publications Inc. in JMIR Formative Research
- Vol. 7 (1) , e38125
Open AccessHow Natural Language Processing Can Aid With Pulmonary Oncology Tumor Node Metastasis Staging From Free-Text Radiology Reports: Algorithm Development and Validation
Background: Natural language processing (NLP) is thought to be a promising solution to extract and store concepts from free text in a structured manner for data mining purposes. This is also true for radiology reports, which still consist mostly of free text. Accurate and complete reports are very important for clinical decision support, for instance, in oncological staging. As such, NLP can be a tool to structure the content of the radiology report, thereby increasing the report’s value. Objective: This study describes the implementation and validation of an N-stage classifier for pulmonary oncology. It is based on free-text radiological chest computed tomography reports according to the tumor, node, and metastasis (TNM) classification, which has been added to the already existing T-stage classifier to create a combined TN-stage classifier. Methods: SpaCy, PyContextNLP, and regular expressions were used for proper information extraction, after additional rules were set to accurately extract N-stage. Results: The overall TN-stage classifier accuracy scores were 0.84 and 0.85, respectively, for the training (N=95) and validation (N=97) sets. This is comparable to the outcomes of the T-stage classifier (0.87-0.92). Conclusions: This study shows that NLP has potential in classifying pulmonary oncology from free-text radiological reports according to the TNM classification system as both the T- and N-stages can be extracted with high accuracy.
- Open Access
Prediction of Radiotherapy Compliance in Elderly Cancer Patients Using an Internally Validated Decision Tree
This study aims to analyze the relationship between the available variables and treatment compliance in elderly cancer patients treated with radiotherapy and to establish a decision tree model to guide caregivers in their decision-making process. For this purpose, 456 patients over 74 years of age who received radiotherapy between 2005 and 2017 were included in this retrospective analysis. The outcome of interest was radiotherapy compliance, determined by whether patients completed their scheduled radiotherapy treatment (compliance means they completed their treatment and noncompliance means they did not). A bootstrap (B = 400) technique was implemented to select the best tuning parameters to establish the decision tree. The developed decision tree uses patient status, the Charlson comorbidity index, the Eastern Cooperative Oncology Group Performance scale, age, sex, cancer type, health insurance status, radiotherapy aim, and fractionation type (conventional fractionation versus hypofractionation) to distinguish between compliant and noncompliant patients. The decision tree’s mean area under the curve and 95% confidence interval was 0.71 (0.66–0.77). Although external validation is needed to determine the decision tree’s clinical usefulness, its discriminating ability was moderate and it could serve as an aid for caregivers to select the optimal treatment for elderly cancer patients.
Open AccessPrediction of Radiotherapy Compliance in Elderly Cancer Patients Using an Internally Validated Decision Tree
This study aims to analyze the relationship between the available variables and treatment compliance in elderly cancer patients treated with radiotherapy and to establish a decision tree model to guide caregivers in their decision-making process. For this purpose, 456 patients over 74 years of age who received radiotherapy between 2005 and 2017 were included in this retrospective analysis. The outcome of interest was radiotherapy compliance, determined by whether patients completed their scheduled radiotherapy treatment (compliance means they completed their treatment and noncompliance means they did not). A bootstrap (B = 400) technique was implemented to select the best tuning parameters to establish the decision tree. The developed decision tree uses patient status, the Charlson comorbidity index, the Eastern Cooperative Oncology Group Performance scale, age, sex, cancer type, health insurance status, radiotherapy aim, and fractionation type (conventional fractionation versus hypofractionation) to distinguish between compliant and noncompliant patients. The decision tree’s mean area under the curve and 95% confidence interval was 0.71 (0.66–0.77). Although external validation is needed to determine the decision tree’s clinical usefulness, its discriminating ability was moderate and it could serve as an aid for caregivers to select the optimal treatment for elderly cancer patients.
- Open Access
- 17 October 2022
- Published by JMIR Publications Inc. in JMIR Cardio
- Vol. 6 (2) , e37437
Digital Health Solutions to Reduce the Burden of Atherosclerotic Cardiovascular Disease Proposed by the CARRIER Consortium
Digital health is a promising tool to support people with an elevated risk for atherosclerotic cardiovascular disease (ASCVD) and patients with an established disease to improve cardiovascular outcomes. Many digital health initiatives have been developed and employed. However, barriers to their large-scale implementation have remained. This paper focuses on these barriers and presents solutions as proposed by the Dutch CARRIER (ie, Coronary ARtery disease: Risk estimations and Interventions for prevention and EaRly detection) consortium. We will focus in 4 sections on the following: (1) the development process of an eHealth solution that will include design thinking and cocreation with relevant stakeholders; (2) the modeling approach for two clinical prediction models (CPMs) to identify people at risk of developing ASCVD and to guide interventions; (3) description of a federated data infrastructure to train the CPMs and to provide the eHealth solution with relevant data; and (4) discussion of an ethical and legal framework for responsible data handling in health care. The Dutch CARRIER consortium consists of a collaboration between experts in the fields of eHealth development, ASCVD, public health, big data, as well as ethics and law. The consortium focuses on reducing the burden of ASCVD. We believe the future of health care is data driven and supported by digital health. Therefore, we hope that our research will not only facilitate CARRIER consortium but may also facilitate other future health care initiatives.
- 17 October 2022
- Published by JMIR Publications Inc. in JMIR Cardio
- Vol. 6 (2) , e37437
Open AccessDigital Health Solutions to Reduce the Burden of Atherosclerotic Cardiovascular Disease Proposed by the CARRIER Consortium
Digital health is a promising tool to support people with an elevated risk for atherosclerotic cardiovascular disease (ASCVD) and patients with an established disease to improve cardiovascular outcomes. Many digital health initiatives have been developed and employed. However, barriers to their large-scale implementation have remained. This paper focuses on these barriers and presents solutions as proposed by the Dutch CARRIER (ie, Coronary ARtery disease: Risk estimations and Interventions for prevention and EaRly detection) consortium. We will focus in 4 sections on the following: (1) the development process of an eHealth solution that will include design thinking and cocreation with relevant stakeholders; (2) the modeling approach for two clinical prediction models (CPMs) to identify people at risk of developing ASCVD and to guide interventions; (3) description of a federated data infrastructure to train the CPMs and to provide the eHealth solution with relevant data; and (4) discussion of an ethical and legal framework for responsible data handling in health care. The Dutch CARRIER consortium consists of a collaboration between experts in the fields of eHealth development, ASCVD, public health, big data, as well as ethics and law. The consortium focuses on reducing the burden of ASCVD. We believe the future of health care is data driven and supported by digital health. Therefore, we hope that our research will not only facilitate CARRIER consortium but may also facilitate other future health care initiatives.