Oriol Estrada
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Oriol Estrada has a total of 199 co-authors. Here are the top co-authors by number of shared publications:
- Francesc López Seguí
Department of Epidemiology and Evaluation, Hospital del Mar, Barcelona, Catalonia; Center for Research in Health and Economics, Pompeu Fabra University, Barcelona, Catalonia; Chair in ICT and Health, Centre for Health and Social Care Research (CESS), University of Vic-Central University of Catalonia (UVic-UCC), Vic, Catalonia
17 shared publications - Guillem Hernández Guillamet
XiT Research Group, Universitat de Girona (UdG), EPS - Edifici P-IV, Carrer Universitat de Girona, 6, Girona, 17003, Catalunya, Spain; Assistance strategy management. Hospital Germans Trias i Pujol, (ICS), Carretera de Canyet, Badalona, 08916, Catalunya, Spain; Research Group on Innovation, Health Economics and Digital Transformation, Institut Germans Trias i Pujol (IGTP), Cami de les Escoles, Badalona, 08916, Catalunya, Spain
10 shared publications - Laura Miró Mezquita
Servei Psiquiatria. Hospital Universitari Germans Trias i Pujol
8 shared publications - Miquel Àngel Mas
Direcció Clínica Territorial de Cronicitat Metropolitana Nord, Institut Català de la Salut, Catalonia, Spain
8 shared publications - Ramón Miralles
Direcció Clínica Territorial de Cronicitat Metropolitana Nord, Institut Català de la Salut, Catalonia, Spain
8 shared publications - Jordi Ara
North Metropolitan Primary Care Directorate, Catalan Institute of Health, 08916 Badalona, Spain
6 shared publications
Latest Publications
- Open Access
- 18 November 2026
- Published by JMIR Publications Inc. in JMIR Preprints
Longitudinal Electronic Health Record Models for Short-Horizon Prediction of In-Hospital Mortality: Retrospective Development, Internal Validation, and Data-Completeness Study (Preprint)
BACKGROUND Longitudinal electronic health record models may support early recognition of clinical deterioration, but incomplete measurements and imprecise outcome times complicate comparisons with clinical early warning scores. OBJECTIVE This study aimed to compare longitudinal prediction models and clinical early warning scores within a model-agnostic evaluation framework that examines data completeness and outcome timing. METHODS This retrospective, single-center study used an outcome-enriched cohort comprising 264,523 eight-hour windows from 7638 episodes (7078 patients) from years 2022 to 2025. Day-discretized terminal discharge served as a death-time proxy; 24 hours was primary, 48 and 72 hours complementary, and 8 hours exploratory. Using patient-disjoint partitions and time-available predictors, we compared penalized logistic regression, gradient boosting (GBM), and random forest using engineered temporal features, a sequence Transformer, and a Transformer–GBM ensemble against adapted Modified Early Warning Score (MEWS), National Early Warning Score (NEWS), and the local VIDA early warning score. Evaluation covered discrimination, calibration, data provenance, common-support comparisons, and alert budgets. RESULTS At 24 hours, area under the receiver operating characteristic curve (AUROC) ranged from 0.852 to 0.885 across longitudinal models and from 0.607 to 0.705 for MEWS, NEWS, and VIDA; average precision (AP) ranged from 0.256 to 0.338 and from 0.073 to 0.094, respectively. GBM and the ensemble had the highest point estimates (AUROC 0.884, 95% CI 0.874-0.895, and 0.885, 95% CI 0.874-0.896; AP 0.333, 95% CI 0.304-0.366, and 0.338, 95% CI 0.309-0.371, respectively). The ensemble showed no clear gain in discrimination over GBM. Prespecified VIDA reconstruction increased episode-level availability from 4889 to 6881 without establishing equivalence to recorded scores. A phase-only 8-hour control achieved AUROC 0.833, demonstrating an endpoint-discretization artifact. CONCLUSIONS These comparisons highlight the relevance of temporal representation, measurement availability, and endpoint definition when assessing predictive performance. Representative temporal/external validation, prevalence-aware recalibration, and prospective clinical evaluation are required before clinical use.
- 18 November 2026
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessLongitudinal Electronic Health Record Models for Short-Horizon Prediction of In-Hospital Mortality: Retrospective Development, Internal Validation, and Data-Completeness Study (Preprint)
BACKGROUND Longitudinal electronic health record models may support early recognition of clinical deterioration, but incomplete measurements and imprecise outcome times complicate comparisons with clinical early warning scores. OBJECTIVE This study aimed to compare longitudinal prediction models and clinical early warning scores within a model-agnostic evaluation framework that examines data completeness and outcome timing. METHODS This retrospective, single-center study used an outcome-enriched cohort comprising 264,523 eight-hour windows from 7638 episodes (7078 patients) from years 2022 to 2025. Day-discretized terminal discharge served as a death-time proxy; 24 hours was primary, 48 and 72 hours complementary, and 8 hours exploratory. Using patient-disjoint partitions and time-available predictors, we compared penalized logistic regression, gradient boosting (GBM), and random forest using engineered temporal features, a sequence Transformer, and a Transformer–GBM ensemble against adapted Modified Early Warning Score (MEWS), National Early Warning Score (NEWS), and the local VIDA early warning score. Evaluation covered discrimination, calibration, data provenance, common-support comparisons, and alert budgets. RESULTS At 24 hours, area under the receiver operating characteristic curve (AUROC) ranged from 0.852 to 0.885 across longitudinal models and from 0.607 to 0.705 for MEWS, NEWS, and VIDA; average precision (AP) ranged from 0.256 to 0.338 and from 0.073 to 0.094, respectively. GBM and the ensemble had the highest point estimates (AUROC 0.884, 95% CI 0.874-0.895, and 0.885, 95% CI 0.874-0.896; AP 0.333, 95% CI 0.304-0.366, and 0.338, 95% CI 0.309-0.371, respectively). The ensemble showed no clear gain in discrimination over GBM. Prespecified VIDA reconstruction increased episode-level availability from 4889 to 6881 without establishing equivalence to recorded scores. A phase-only 8-hour control achieved AUROC 0.833, demonstrating an endpoint-discretization artifact. CONCLUSIONS These comparisons highlight the relevance of temporal representation, measurement availability, and endpoint definition when assessing predictive performance. Representative temporal/external validation, prevalence-aware recalibration, and prospective clinical evaluation are required before clinical use.
- Open Access
- 22 May 2026
- Published by JMIR Publications Inc. in JMIR Preprints
The Value-Based Framework DHRIVE: A Digital Health Roadmap for Implementation, Validation, and Expansion (Preprint)
BACKGROUND Contemporary healthcare systems remain challenged by fragmented, reactive, and volume-based models of care, despite growing pressure to deliver more integrated, patient-centred, and sustainable services. In this context, Value-Based Healthcare (VBHC) has emerged as a key paradigm for reorienting care towards outcomes that matter to patients in relation to the resources used, and digital health solutions can help translate this approach into practice through redesigned care pathways, improved access and continuity, and the routine use of longitudinal patient-centred data. However, many digital solutions still remain isolated pilots with limited structural integration or scalability, and existing frameworks provide only limited operational guidance on how to address the organisational and implementation challenges involved in integrating and scaling value-based digital health solutions in complex healthcare settings. OBJECTIVE This study aims to develop and describe a structured implementation framework designed to guide healthcare organizations in designing, implementing, validating, and scaling digital health programs while operationalizing VBHC principles. METHODS DHRIVE (Digital Health Roadmap for Implementation, Validation and Expansion) was developed in line with Medical Research Council guidance for complex interventions through an iterative, inductive, and person-centred approach. The framework emerged through a four-phase process conducted at Hospital Universitari Germans Trias i Pujol (Catalonia, Spain), which also informed the development of the hospital’s eSalut digital health programme: (1) a co-design phase involving a focus group with healthcare professionals (n=10), semi-structured interviews with patients (n=8), and a focus group with senior managers (n=6); (2) an organisational and technological set-up phase focused on platform selection, interoperability, and governance; (3) prototype development, pilot implementation, and evaluation across three use cases; and (4) a refinement phase in which findings from implementation and patient interviews informed the final framework. RESULTS The final DHRIVE framework comprises four integrated components: (1) a value-oriented core anchoring decisions to clinical outcomes, patient and professional experience, and organisational efficiency; (2) three operational pillars: monitoring, patient empowerment, and structured communication; (3) five enabling dimensions: governance, clinical workflows, technology, adoption, training and cultural change, and evaluation; and (4) an iterative implementation structure. Applied within the eSalut programme, DHRIVE supported organisation-wide implementation across approximately 80% of clinical services, with over 100 active use cases and more than 5,000 patients enrolled. CONCLUSIONS DHRIVE provides a pragmatic framework for operationalising VBHC as part of digital health solutions in real-world healthcare settings. By integrating governance, clinical workflows, technological capabilities, and evaluation systems into a coherent model, it may help address structural barriers that limit the scalability of digital health. Further research should assess its effectiveness, cost-effectiveness, and transferability across diverse healthcare contexts.
- 22 May 2026
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessThe Value-Based Framework DHRIVE: A Digital Health Roadmap for Implementation, Validation, and Expansion (Preprint)
BACKGROUND Contemporary healthcare systems remain challenged by fragmented, reactive, and volume-based models of care, despite growing pressure to deliver more integrated, patient-centred, and sustainable services. In this context, Value-Based Healthcare (VBHC) has emerged as a key paradigm for reorienting care towards outcomes that matter to patients in relation to the resources used, and digital health solutions can help translate this approach into practice through redesigned care pathways, improved access and continuity, and the routine use of longitudinal patient-centred data. However, many digital solutions still remain isolated pilots with limited structural integration or scalability, and existing frameworks provide only limited operational guidance on how to address the organisational and implementation challenges involved in integrating and scaling value-based digital health solutions in complex healthcare settings. OBJECTIVE This study aims to develop and describe a structured implementation framework designed to guide healthcare organizations in designing, implementing, validating, and scaling digital health programs while operationalizing VBHC principles. METHODS DHRIVE (Digital Health Roadmap for Implementation, Validation and Expansion) was developed in line with Medical Research Council guidance for complex interventions through an iterative, inductive, and person-centred approach. The framework emerged through a four-phase process conducted at Hospital Universitari Germans Trias i Pujol (Catalonia, Spain), which also informed the development of the hospital’s eSalut digital health programme: (1) a co-design phase involving a focus group with healthcare professionals (n=10), semi-structured interviews with patients (n=8), and a focus group with senior managers (n=6); (2) an organisational and technological set-up phase focused on platform selection, interoperability, and governance; (3) prototype development, pilot implementation, and evaluation across three use cases; and (4) a refinement phase in which findings from implementation and patient interviews informed the final framework. RESULTS The final DHRIVE framework comprises four integrated components: (1) a value-oriented core anchoring decisions to clinical outcomes, patient and professional experience, and organisational efficiency; (2) three operational pillars: monitoring, patient empowerment, and structured communication; (3) five enabling dimensions: governance, clinical workflows, technology, adoption, training and cultural change, and evaluation; and (4) an iterative implementation structure. Applied within the eSalut programme, DHRIVE supported organisation-wide implementation across approximately 80% of clinical services, with over 100 active use cases and more than 5,000 patients enrolled. CONCLUSIONS DHRIVE provides a pragmatic framework for operationalising VBHC as part of digital health solutions in real-world healthcare settings. By integrating governance, clinical workflows, technological capabilities, and evaluation systems into a coherent model, it may help address structural barriers that limit the scalability of digital health. Further research should assess its effectiveness, cost-effectiveness, and transferability across diverse healthcare contexts.
- Open Access
- 12 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. PP (21682194) , 1-14
Contactless Acquisition and Decoupling of Respiratory and Cardiac Signals using a 122 GHz FMCW Radar
This paper presents a contactless method for the simultaneous monitoring of heart rate (HR) and respiratory rate (RR) using a Frequency Modulated Continuous Wave (FMCW) radar operating at 122.5 GHz. To address the challenges posed by spectral overlap and interference between cardiac and respiratory components, we introduce a signal separation and estimation framework based on Maximum Likelihood Estimation (MLE) combined with an orthogonal projection technique. The approach models the thoracic displacement captured by the radar as the superposition of periodic sources and applies spectral projection to isolate the fundamental frequencies and their harmonics. Theoretical performance is assessed through the derivation of the Cramér-Rao Lower Bound (CRLB) and extensive Monte Carlo simulations under varying SNR and sample size conditions. Experimental validation was conducted on 23 healthy volunteers, each providing two 20 second recordings, using a clinical-grade reference monitor. The method achieves high estimation accuracy, with a mean absolute error of 0.69 bpm for HR and 0.33 bpm for RR. The algorithm is capable of reconstructing the cardiac pulse waveform while preserving key morphological features such as the systolic peak and dicrotic notch. Furthermore, the use of the projection technique further enhanced estimation accuracy under nonphysiological conditions, including both elevated and reduced rates. These findings demonstrate the potential of the proposed method as a reliable tool for contactless monitoring of vital signs and support its future integration into biomedical applications.
- 12 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. PP (21682194) , 1-14
Open AccessContactless Acquisition and Decoupling of Respiratory and Cardiac Signals using a 122 GHz FMCW Radar
This paper presents a contactless method for the simultaneous monitoring of heart rate (HR) and respiratory rate (RR) using a Frequency Modulated Continuous Wave (FMCW) radar operating at 122.5 GHz. To address the challenges posed by spectral overlap and interference between cardiac and respiratory components, we introduce a signal separation and estimation framework based on Maximum Likelihood Estimation (MLE) combined with an orthogonal projection technique. The approach models the thoracic displacement captured by the radar as the superposition of periodic sources and applies spectral projection to isolate the fundamental frequencies and their harmonics. Theoretical performance is assessed through the derivation of the Cramér-Rao Lower Bound (CRLB) and extensive Monte Carlo simulations under varying SNR and sample size conditions. Experimental validation was conducted on 23 healthy volunteers, each providing two 20 second recordings, using a clinical-grade reference monitor. The method achieves high estimation accuracy, with a mean absolute error of 0.69 bpm for HR and 0.33 bpm for RR. The algorithm is capable of reconstructing the cardiac pulse waveform while preserving key morphological features such as the systolic peak and dicrotic notch. Furthermore, the use of the projection technique further enhanced estimation accuracy under nonphysiological conditions, including both elevated and reduced rates. These findings demonstrate the potential of the proposed method as a reliable tool for contactless monitoring of vital signs and support its future integration into biomedical applications.
- Open Access
- 18 July 2025
- Published by Springer Nature in BMC Health Services Research
- Vol. 25 (1) , 958
Analysis of the current status and future vision of innovation in a tertiary hospital in Catalonia: a cross-sectional study
Innovation in healthcare is a complex process involving the creation or modification of products, services, or processes, and their successful implementation in clinical settings. University Hospital Germans Trias i Pujol (HUGTP) implemented a new innovation management model in 2018, to achieve greater impact. However, there is still a knowledge gap regarding how healthcare organizations understand and experience innovation activities. This exploratory study aims to analyze the current state and future vision of innovation at HUGTP, using the novel Innovation Map methodology to capture the perceptions of professionals engaged in innovation. A cross-sectional study was conducted at HUGTP using the Innovation Map approach, which combines quantitative and qualitative data. Professionals with roles connected to innovation were recruited via email and intranet. Data were collected through an ad hoc-developed questionnaire and focus groups. Quantitative data were analyzed using Jamovi software (95% confidence interval,p≤0.05), and qualitative data were analyzed with ATLAS.ti to identify attributes and cluster emerging themes. A total of 152 participants completed the quantitative survey and 33 participated in focus groups. The results show a high level of awareness and positive perception of the Innovation Department's activities, particularly among professionals in high-responsibility roles. While the areas of work received strong overall ratings, some statistical differences between professional categories and departments highlight the need for tailored future strategies. Participants also recognized the significant impact of emerging technologies, although perceptions varied by group. Key improvement areas were identified, particularly regarding internal communication and better integration of innovation practices across all departments. This study presents the first implementation of the Innovation Map, a novel mixed-methods tool to holistically assess innovation awareness, perceptions, and needs within a hospital. The findings provide a meaningful initial overview of the innovation landscape at HUGTP and underscore the importance of strategic, inclusive innovation management. These results offer a valuable starting point for future longitudinal and multicenter studies.
- 18 July 2025
- Published by Springer Nature in BMC Health Services Research
- Vol. 25 (1) , 958
Open AccessAnalysis of the current status and future vision of innovation in a tertiary hospital in Catalonia: a cross-sectional study
Innovation in healthcare is a complex process involving the creation or modification of products, services, or processes, and their successful implementation in clinical settings. University Hospital Germans Trias i Pujol (HUGTP) implemented a new innovation management model in 2018, to achieve greater impact. However, there is still a knowledge gap regarding how healthcare organizations understand and experience innovation activities. This exploratory study aims to analyze the current state and future vision of innovation at HUGTP, using the novel Innovation Map methodology to capture the perceptions of professionals engaged in innovation. A cross-sectional study was conducted at HUGTP using the Innovation Map approach, which combines quantitative and qualitative data. Professionals with roles connected to innovation were recruited via email and intranet. Data were collected through an ad hoc-developed questionnaire and focus groups. Quantitative data were analyzed using Jamovi software (95% confidence interval,p≤0.05), and qualitative data were analyzed with ATLAS.ti to identify attributes and cluster emerging themes. A total of 152 participants completed the quantitative survey and 33 participated in focus groups. The results show a high level of awareness and positive perception of the Innovation Department's activities, particularly among professionals in high-responsibility roles. While the areas of work received strong overall ratings, some statistical differences between professional categories and departments highlight the need for tailored future strategies. Participants also recognized the significant impact of emerging technologies, although perceptions varied by group. Key improvement areas were identified, particularly regarding internal communication and better integration of innovation practices across all departments. This study presents the first implementation of the Innovation Map, a novel mixed-methods tool to holistically assess innovation awareness, perceptions, and needs within a hospital. The findings provide a meaningful initial overview of the innovation landscape at HUGTP and underscore the importance of strategic, inclusive innovation management. These results offer a valuable starting point for future longitudinal and multicenter studies.
- Open Access
- 19 March 2025
- Published by Ubiquity Press, Ltd. in International Journal of Integrated Care
- Vol. 25 (1) , 11
What Can We Learn for Future Integrated Care Models in Long Term Care Facilities After the COVID-19 Emergency? Lessons From an Observational Study in Catalonia
Introduction: The healthcare response to the COVID-19 pandemic in long term care facilities (LTCF), constitutes one of the challenges faced by governments and institutions worldwide. Our aim was to analyze the facilitators and barriers of this response, for the future integrated care model in these facilities. Methods: From a retrospective observational study, we present the experience and lessons learned of the implementation of an integrated response at the meso level in LTCF for older people and for people with physical and mental conditions in the North Metropolitan area of Barcelona, in Catalonia, during the COVID-19 pandemic. Results: We analyzed the care provided to 13,369 institutionalized people. The major facilitating points were: the adaptation of proactive care teams, the creation of a tool to improve communication with institutions, and the management of epidemiological data for planning collaboration between different actors. Main barriers were not including users and family members views in the response adaptation, and the lack of LTCF resources to respond to changing needs. Conclusions: Increasing proactivity and adapting interventions based on updated information were key to minimize infections and mortality. Improving the communication and the collaboration between actors, and people involvement in the response planning, need to be considered for the future.
- 19 March 2025
- Published by Ubiquity Press, Ltd. in International Journal of Integrated Care
- Vol. 25 (1) , 11
Open AccessWhat Can We Learn for Future Integrated Care Models in Long Term Care Facilities After the COVID-19 Emergency? Lessons From an Observational Study in Catalonia
Introduction: The healthcare response to the COVID-19 pandemic in long term care facilities (LTCF), constitutes one of the challenges faced by governments and institutions worldwide. Our aim was to analyze the facilitators and barriers of this response, for the future integrated care model in these facilities. Methods: From a retrospective observational study, we present the experience and lessons learned of the implementation of an integrated response at the meso level in LTCF for older people and for people with physical and mental conditions in the North Metropolitan area of Barcelona, in Catalonia, during the COVID-19 pandemic. Results: We analyzed the care provided to 13,369 institutionalized people. The major facilitating points were: the adaptation of proactive care teams, the creation of a tool to improve communication with institutions, and the management of epidemiological data for planning collaboration between different actors. Main barriers were not including users and family members views in the response adaptation, and the lack of LTCF resources to respond to changing needs. Conclusions: Increasing proactivity and adapting interventions based on updated information were key to minimize infections and mortality. Improving the communication and the collaboration between actors, and people involvement in the response planning, need to be considered for the future.
- Open Access
- 21 March 2024
- Published by JMIR Publications Inc. in Online Journal of Public Health Informatics
- Vol. 16 (1) , e58453
Correction: Machine Learning Model for Predicting Mortality Risk in Patients With Complex Chronic Conditions: Retrospective Analysis
[This corrects the article DOI: 10.2196/52782.].
- 21 March 2024
- Published by JMIR Publications Inc. in Online Journal of Public Health Informatics
- Vol. 16 (1) , e58453
Open AccessCorrection: Machine Learning Model for Predicting Mortality Risk in Patients With Complex Chronic Conditions: Retrospective Analysis
[This corrects the article DOI: 10.2196/52782.].
- Open Access
- 18 March 2024
- Published by Oxford University Press (OUP) in ESC Heart Failure
- Vol. 11 (4) , 1955-1962
Assessing the Impact of Haemodynamic Monitoring with CardioMEMS on Heart Failure Patients: A Cost–Benefit Analysis
Aims: The objective of this study was to perform a cost–benefit analysis of the CardioMEMS HF System (Abbott Laboratories, Abbott Park, IL, USA) in a heart failure (HF) clinic in Spain by evaluating the real-time remote monitoring of pulmonary artery pressures, which has been shown to reduce HF-related hospitalizations and improve the quality of life for selected HF patients. Particularly, the study aimed to determine the value of CardioMEMS in Southern Europe, where healthcare costs are significantly lower and its effectiveness remains uncertain. Methods and results: This single-centre study enrolled all consecutive HF patients (N = 43) who had been implanted with a pulmonary artery pressure sensor (CardioMEMS HF System); 48.8% were females, aged 75.5 ± 7.0 years, with both reduced and preserved left ventricular ejection fraction; 67.4% of them were in New York Heart Association Class III. The number of HF hospitalizations in the year before and the year after the sensor implantation was compared. Quality-adjusted life years gained based on a literature review of previous studies were calculated. The rate of HF hospitalizations was significantly lower at 1 year compared with the year before CardioMEMS implantation (0.25 vs. 1.10 events/patient-year, hazard ratio 0.22, P = 0.001). At the end of the first year, the usual management outperformed the CardioMEMS HF System. By the end of the second year, the CardioMEMS system is estimated to reduce costs compared with usual management (net benefits of €346). Conclusions: Based on the results, we suggest that remote monitoring of pulmonary artery pressure with the CardioMEMS HF System represents a midterm and long-term efficient strategy in a healthcare setting in Southern Europe.
- 18 March 2024
- Published by Oxford University Press (OUP) in ESC Heart Failure
- Vol. 11 (4) , 1955-1962
Open AccessAssessing the Impact of Haemodynamic Monitoring with CardioMEMS on Heart Failure Patients: A Cost–Benefit Analysis
Aims: The objective of this study was to perform a cost–benefit analysis of the CardioMEMS HF System (Abbott Laboratories, Abbott Park, IL, USA) in a heart failure (HF) clinic in Spain by evaluating the real-time remote monitoring of pulmonary artery pressures, which has been shown to reduce HF-related hospitalizations and improve the quality of life for selected HF patients. Particularly, the study aimed to determine the value of CardioMEMS in Southern Europe, where healthcare costs are significantly lower and its effectiveness remains uncertain. Methods and results: This single-centre study enrolled all consecutive HF patients (N = 43) who had been implanted with a pulmonary artery pressure sensor (CardioMEMS HF System); 48.8% were females, aged 75.5 ± 7.0 years, with both reduced and preserved left ventricular ejection fraction; 67.4% of them were in New York Heart Association Class III. The number of HF hospitalizations in the year before and the year after the sensor implantation was compared. Quality-adjusted life years gained based on a literature review of previous studies were calculated. The rate of HF hospitalizations was significantly lower at 1 year compared with the year before CardioMEMS implantation (0.25 vs. 1.10 events/patient-year, hazard ratio 0.22, P = 0.001). At the end of the first year, the usual management outperformed the CardioMEMS HF System. By the end of the second year, the CardioMEMS system is estimated to reduce costs compared with usual management (net benefits of €346). Conclusions: Based on the results, we suggest that remote monitoring of pulmonary artery pressure with the CardioMEMS HF System represents a midterm and long-term efficient strategy in a healthcare setting in Southern Europe.
- Open Access
- 15 March 2024
- Published by JMIR Publications Inc. in JMIR Preprints
Correction: Machine Learning Model for Predicting Mortality Risk in Patients With Complex Chronic Conditions: Retrospective Analysis (Preprint)
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author).
- 15 March 2024
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessCorrection: Machine Learning Model for Predicting Mortality Risk in Patients With Complex Chronic Conditions: Retrospective Analysis (Preprint)
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author).
- Open Access
- 4 March 2024
- Published by Oxford University Press (OUP) in Journal of Travel Medicine
- Vol. 31 (6)
Female genitourinary schistosomiasis-related symptoms in long-term sub-Saharan African migrants in Europe: a prospective population-based study
Schistosomiasis can involve the genital tract in up to 75% of women with urinary Schistosoma haematobium infection in endemic countries, a phenomenon known as female genital schistosomiasis (FGS). 1, 2 It is characterized by an amalgamation of gynaecological signs and symptoms, mainly including menstrual disturbances and vulvovaginal discomfort. The observation of eggs in the genitourinary tract or the characteristic lesions at colposcopy examination is not the rule. 1, 2 The burden of FGS in African migrant women in non-endemic countries, carrying long-term or chronic S. haematobium infections, is unknown.
- 4 March 2024
- Published by Oxford University Press (OUP) in Journal of Travel Medicine
- Vol. 31 (6)
Open AccessFemale genitourinary schistosomiasis-related symptoms in long-term sub-Saharan African migrants in Europe: a prospective population-based study
Schistosomiasis can involve the genital tract in up to 75% of women with urinary Schistosoma haematobium infection in endemic countries, a phenomenon known as female genital schistosomiasis (FGS). 1, 2 It is characterized by an amalgamation of gynaecological signs and symptoms, mainly including menstrual disturbances and vulvovaginal discomfort. The observation of eggs in the genitourinary tract or the characteristic lesions at colposcopy examination is not the rule. 1, 2 The burden of FGS in African migrant women in non-endemic countries, carrying long-term or chronic S. haematobium infections, is unknown.
- Open Access
- 28 December 2023
- Published by JMIR Publications Inc. in Online Journal of Public Health Informatics
- Vol. 15 (1) , e52782
Machine Learning Model for Predicting Mortality Risk in Patients With Complex Chronic Conditions: Retrospective Analysis
Background: The health care system is undergoing a shift toward a more patient-centered approach for individuals with chronic and complex conditions, which presents a series of challenges, such as predicting hospital needs and optimizing resources. At the same time, the exponential increase in health data availability has made it possible to apply advanced statistics and artificial intelligence techniques to develop decision-support systems and improve resource planning, diagnosis, and patient screening. These methods are key to automating the analysis of large volumes of medical data and reducing professional workloads. Objective: This article aims to present a machine learning model and a case study in a cohort of patients with highly complex conditions. The object was to predict mortality within the following 4 years and early mortality over 6 months following diagnosis. The method used easily accessible variables and health care resource utilization information. Methods: A classification algorithm was selected among 6 models implemented and evaluated using a stratified cross-validation strategy with k=10 and a 70/30 train-test split. The evaluation metrics used included accuracy, recall, precision, F1-score, and area under the receiver operating characteristic (AUROC) curve. Results: The model predicted patient death with an 87% accuracy, recall of 87%, precision of 82%, F1-score of 84%, and area under the curve (AUC) of 0.88 using the best model, the Extreme Gradient Boosting (XGBoost) classifier. The results were worse when predicting premature deaths (following 6 months) with an 83% accuracy (recall=55%, precision=64% F1-score=57%, and AUC=0.88) using the Gradient Boosting (GRBoost) classifier. Conclusions: This study showcases encouraging outcomes in forecasting mortality among patients with intricate and persistent health conditions. The employed variables are conveniently accessible, and the incorporation of health care resource utilization information of the patient, which has not been employed by current state-of-the-art approaches, displays promising predictive power. The proposed prediction model is designed to efficiently identify cases that need customized care and proactively anticipate the demand for critical resources by health care providers.
- 28 December 2023
- Published by JMIR Publications Inc. in Online Journal of Public Health Informatics
- Vol. 15 (1) , e52782
Open AccessMachine Learning Model for Predicting Mortality Risk in Patients With Complex Chronic Conditions: Retrospective Analysis
Background: The health care system is undergoing a shift toward a more patient-centered approach for individuals with chronic and complex conditions, which presents a series of challenges, such as predicting hospital needs and optimizing resources. At the same time, the exponential increase in health data availability has made it possible to apply advanced statistics and artificial intelligence techniques to develop decision-support systems and improve resource planning, diagnosis, and patient screening. These methods are key to automating the analysis of large volumes of medical data and reducing professional workloads. Objective: This article aims to present a machine learning model and a case study in a cohort of patients with highly complex conditions. The object was to predict mortality within the following 4 years and early mortality over 6 months following diagnosis. The method used easily accessible variables and health care resource utilization information. Methods: A classification algorithm was selected among 6 models implemented and evaluated using a stratified cross-validation strategy with k=10 and a 70/30 train-test split. The evaluation metrics used included accuracy, recall, precision, F1-score, and area under the receiver operating characteristic (AUROC) curve. Results: The model predicted patient death with an 87% accuracy, recall of 87%, precision of 82%, F1-score of 84%, and area under the curve (AUC) of 0.88 using the best model, the Extreme Gradient Boosting (XGBoost) classifier. The results were worse when predicting premature deaths (following 6 months) with an 83% accuracy (recall=55%, precision=64% F1-score=57%, and AUC=0.88) using the Gradient Boosting (GRBoost) classifier. Conclusions: This study showcases encouraging outcomes in forecasting mortality among patients with intricate and persistent health conditions. The employed variables are conveniently accessible, and the incorporation of health care resource utilization information of the patient, which has not been employed by current state-of-the-art approaches, displays promising predictive power. The proposed prediction model is designed to efficiently identify cases that need customized care and proactively anticipate the demand for critical resources by health care providers.