Salvador Tortajada
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
Salvador Tortajada has a total of 134 co-authors. Here are the top co-authors by number of shared publications:
- Juan Miguel Garcia Gomez
Biomedical Data Science Laboratory (BDSLab), Instituto de Aplicaciones de las Tecnologías de la Información y de las Comunicaciones Avanzadas (ITACA), Universitat Politècnica de València (UPV), Valencia, Spain
16 shared publications - Montserrat Robles
Universitat Politècnica de València
9 shared publications - Elies Fuster-Garcia
Instituto Universitario de Tecnologías de la Información y Comunicaciones (ITACA), Universitat Politècnica de València , Valencia
8 shared publications - Javier Vicente
Universidad Politécnica de Valencia
8 shared publications - Carlos Sáez
Biomedical Data Science Laboratory (BDSLab), Instituto de Aplicaciones de las Tecnologías de la Información y de las Comunicaciones Avanzadas (ITACA), Universitat Politècnica de València (UPV), Valencia, Spain
6 shared publications - Margarida Julià-Sapé
Departament de Bioquimica i Biologia Molecular and Institut de Biotecnologia i Biomedicina (IBB), Universitat Autonoma de Barcelona (UAB), Spain
6 shared publications
Latest Publications
- Open Access
- 20 October 2022
- Published by Springer Nature in Insights into Imaging
- Vol. 13 (1) , 1
Correction: A comparison of Covid-19 early detection between convolutional neural networks and radiologists
- 20 October 2022
- Published by Springer Nature in Insights into Imaging
- Vol. 13 (1) , 1
Open AccessCorrection: A comparison of Covid-19 early detection between convolutional neural networks and radiologists
- Open Access
Predicting morbidity by Local Similarities in Multi-Scale Patient Trajectories
Healthcare predictive models generally rely on static snapshots of patient information. Patient Trajectories (PTs) model the evolution of patient conditions over time and are a promising source of information for predicting future morbidities. However, PTs are highly heterogeneous among patients in terms of length and content, so only aggregated versions that include the most frequent events have been studied. Further, the use of longitudinal multiscale data such as integrating EHR coded data and laboratory results in PT models is yet to be explored. Our hypothesis is that local similarities on small chunks of PTs can identify similar patients with respect to their future morbidities. The objectives of this work are (1) to develop a methodology to identify local similarities between PTs prior to the occurrence of morbidities to predict these on new query individuals; and (2) to validate this methodology to impute risk of cardiovascular diseases (CVD) in patients with diabetes. We have proposed a novel formal definition of PTs based on sequences of multi-scale data over time, so each patient has their own PT including every data available in their EHR. Thus, patients do not need to follow partly or completely one pre-defined trajectory built by the most frequent events in a population but having common events with any another patient. A dynamic programming methodology to identify local alignments on PTs for predicting future morbidities is proposed. The proposed methodology for PT definition and the alignment algorithm are generic to be applied on any additional clinical domain. We tested this solution for predicting CVD in patients with diabetes and we achieved a positive predictive value of 0.33, a recall of 0.72 and a specificity of 0.38. Therefore, the proposed solution in the diabetes use case can result of utmost utility to patient screening. Highlights: Local similarities between patient trajectories can potentially be used to predict morbid conditions. A formal definition of patient trajectories comprising heterogeneous clinical observations, biomedical tests and time gaps is proposed. A novel dynamic programming methodology is proposed to find similar patients based on the Smith-Waterman alignment algorithm and a set of customized scoring matrices.
Open AccessPredicting morbidity by Local Similarities in Multi-Scale Patient Trajectories
Healthcare predictive models generally rely on static snapshots of patient information. Patient Trajectories (PTs) model the evolution of patient conditions over time and are a promising source of information for predicting future morbidities. However, PTs are highly heterogeneous among patients in terms of length and content, so only aggregated versions that include the most frequent events have been studied. Further, the use of longitudinal multiscale data such as integrating EHR coded data and laboratory results in PT models is yet to be explored. Our hypothesis is that local similarities on small chunks of PTs can identify similar patients with respect to their future morbidities. The objectives of this work are (1) to develop a methodology to identify local similarities between PTs prior to the occurrence of morbidities to predict these on new query individuals; and (2) to validate this methodology to impute risk of cardiovascular diseases (CVD) in patients with diabetes. We have proposed a novel formal definition of PTs based on sequences of multi-scale data over time, so each patient has their own PT including every data available in their EHR. Thus, patients do not need to follow partly or completely one pre-defined trajectory built by the most frequent events in a population but having common events with any another patient. A dynamic programming methodology to identify local alignments on PTs for predicting future morbidities is proposed. The proposed methodology for PT definition and the alignment algorithm are generic to be applied on any additional clinical domain. We tested this solution for predicting CVD in patients with diabetes and we achieved a positive predictive value of 0.33, a recall of 0.72 and a specificity of 0.38. Therefore, the proposed solution in the diabetes use case can result of utmost utility to patient screening. Highlights: Local similarities between patient trajectories can potentially be used to predict morbid conditions. A formal definition of patient trajectories comprising heterogeneous clinical observations, biomedical tests and time gaps is proposed. A novel dynamic programming methodology is proposed to find similar patients based on the Smith-Waterman alignment algorithm and a set of customized scoring matrices.
- Open Access
- 7 August 2019
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 14 (8) , e0220369
Temporal variability analysis reveals biases in electronic health records due to hospital process reengineering interventions over seven years
To evaluate the effects of Process-Reengineering interventions on the Electronic Health Records (EHR) of a hospital over 7 years. Temporal Variability Assessment (TVA) based on probabilistic data quality assessment was applied to the historic monthly-batched admission data of Hospital La Fe Valencia, Spain from 2010 to 2016. Routine healthcare data with a complete EHR was expanded by processed variables such as the Charlson Comorbidity Index. Four Process-Reengineering interventions were detected by quantifiable effects on the EHR: (1) the hospital relocation in 2011 involved progressive reduction of admissions during the next four months, (2) the hospital services re-configuration incremented the number of inter-services transfers, (3) the care-services re-distribution led to transfers between facilities (4) the assignment to the hospital of a new area with 80,000 patients in 2015 inspired the discharge to home for follow up and the update of the pre-surgery planned admissions protocol that produced a significant decrease of the patient length of stay. TVA provides an indicator of the effect of process re-engineering interventions on healthcare practice. Evaluating the effect of facilities’ relocation and increment of citizens (findings 1, 3–4), the impact of strategies (findings 2–3), and gradual changes in protocols (finding 4) may help on the hospital management by optimizing interventions based on their effect on EHRs or on data reuse. The effects on hospitals EHR due to process re-engineering interventions can be evaluated using the TVA methodology. Being aware of conditioned variations in EHR is of the utmost importance for the reliable reuse of routine hospitalization data.
- 7 August 2019
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 14 (8) , e0220369
Open AccessTemporal variability analysis reveals biases in electronic health records due to hospital process reengineering interventions over seven years
To evaluate the effects of Process-Reengineering interventions on the Electronic Health Records (EHR) of a hospital over 7 years. Temporal Variability Assessment (TVA) based on probabilistic data quality assessment was applied to the historic monthly-batched admission data of Hospital La Fe Valencia, Spain from 2010 to 2016. Routine healthcare data with a complete EHR was expanded by processed variables such as the Charlson Comorbidity Index. Four Process-Reengineering interventions were detected by quantifiable effects on the EHR: (1) the hospital relocation in 2011 involved progressive reduction of admissions during the next four months, (2) the hospital services re-configuration incremented the number of inter-services transfers, (3) the care-services re-distribution led to transfers between facilities (4) the assignment to the hospital of a new area with 80,000 patients in 2015 inspired the discharge to home for follow up and the update of the pre-surgery planned admissions protocol that produced a significant decrease of the patient length of stay. TVA provides an indicator of the effect of process re-engineering interventions on healthcare practice. Evaluating the effect of facilities’ relocation and increment of citizens (findings 1, 3–4), the impact of strategies (findings 2–3), and gradual changes in protocols (finding 4) may help on the hospital management by optimizing interventions based on their effect on EHRs or on data reuse. The effects on hospitals EHR due to process re-engineering interventions can be evaluated using the TVA methodology. Being aware of conditioned variations in EHR is of the utmost importance for the reliable reuse of routine hospitalization data.
- Open Access
- 20 June 2017
- Published by Ubiquity Press, Ltd. in International Journal of Integrated Care
- Vol. 17 (2) , 4
Case Management for Patients with Complex Multimorbidity: Development and Validation of a Coordinated Intervention between Primary and Hospital Care
In the past few years, healthcare systems have been facing a growing demand related to the high prevalence of chronic diseases. Case management programs have emerged as an integrated care approach for the management of chronic disease. Nevertheless, there is little scientific evidence on the impact of using a case management program for patients with complex multimorbidity regarding hospital resource utilisation. We evaluated an integrated case management intervention set up by community-based care at outpatient clinics with nurse case managers from a telemedicine unit. The hypothesis to be tested was whether improved continuity of care resulting from the integration of community-based and hospital services reduced the use of hospital resources amongst patients with complex multimorbidity. A retrospective cohort study was performed using a sample of 714 adult patients admitted to the program between January 2012 and January 2015. We found a significant decrease in the number of emergency room visits, unplanned hospitalizations, and length of stay, and an expected increase in the home care hospital-based episodes. These results support the hypothesis that case management interventions can reduce the use of unplanned hospital admissions when applied to patients with complex multimorbidity.
- 20 June 2017
- Published by Ubiquity Press, Ltd. in International Journal of Integrated Care
- Vol. 17 (2) , 4
Open AccessCase Management for Patients with Complex Multimorbidity: Development and Validation of a Coordinated Intervention between Primary and Hospital Care
In the past few years, healthcare systems have been facing a growing demand related to the high prevalence of chronic diseases. Case management programs have emerged as an integrated care approach for the management of chronic disease. Nevertheless, there is little scientific evidence on the impact of using a case management program for patients with complex multimorbidity regarding hospital resource utilisation. We evaluated an integrated case management intervention set up by community-based care at outpatient clinics with nurse case managers from a telemedicine unit. The hypothesis to be tested was whether improved continuity of care resulting from the integration of community-based and hospital services reduced the use of hospital resources amongst patients with complex multimorbidity. A retrospective cohort study was performed using a sample of 714 adult patients admitted to the program between January 2012 and January 2015. We found a significant decrease in the number of emergency room visits, unplanned hospitalizations, and length of stay, and an expected increase in the home care hospital-based episodes. These results support the hypothesis that case management interventions can reduce the use of unplanned hospital admissions when applied to patients with complex multimorbidity.
- Open Access
- 1 January 2017
- Published by IOS Press
- Vol. 235, 539-543
A Standardized and Data Quality Assessed Maternal-Child Care Integrated Data Repository for Research and Monitoring of Best Practices: A Pilot Project in Spain
We present the results of a pilot project of the Spanish Ministry of Health, Social Services and Equality, envisaged to the development of a national integrated data repository of maternal-child care information. Based on health information standards and data quality assessment procedures, the developed repository is aimed to a reliable data reuse for (1) population research and (2) the monitoring of healthcare best practices. Data standardization was provided by means of two main ISO 13606 archetypes (composed of 43 sub-archetypes), the first dedicated to the delivery and birth information and the second about the infant feeding information from delivery up to two years. Data quality was assessed by means of a dedicated procedure on seven dimensions including completeness, consistency, uniqueness, multi-source variability, temporal variability, correctness and predictive value. A set of 127 best practice indicators was defined according to international recommendations and mapped to the archetypes, allowing their calculus using XQuery programs. As a result, a standardized and data quality assessed integrated data respository was generated, including 7857 records from two Spanish hospitals: Hospital Virgen del Castillo, Yecla, and Hospital 12 de Octubre, Madrid. This pilot project establishes the basis for a reliable maternal-child care data reuse and standardized monitoring of best practices based on the developed information and data quality standards.
- 1 January 2017
- Published by IOS Press
- Vol. 235, 539-543
Open AccessA Standardized and Data Quality Assessed Maternal-Child Care Integrated Data Repository for Research and Monitoring of Best Practices: A Pilot Project in Spain
We present the results of a pilot project of the Spanish Ministry of Health, Social Services and Equality, envisaged to the development of a national integrated data repository of maternal-child care information. Based on health information standards and data quality assessment procedures, the developed repository is aimed to a reliable data reuse for (1) population research and (2) the monitoring of healthcare best practices. Data standardization was provided by means of two main ISO 13606 archetypes (composed of 43 sub-archetypes), the first dedicated to the delivery and birth information and the second about the infant feeding information from delivery up to two years. Data quality was assessed by means of a dedicated procedure on seven dimensions including completeness, consistency, uniqueness, multi-source variability, temporal variability, correctness and predictive value. A set of 127 best practice indicators was defined according to international recommendations and mapped to the archetypes, allowing their calculus using XQuery programs. As a result, a standardized and data quality assessed integrated data respository was generated, including 7857 records from two Spanish hospitals: Hospital Virgen del Castillo, Yecla, and Hospital 12 de Octubre, Madrid. This pilot project establishes the basis for a reliable maternal-child care data reuse and standardized monitoring of best practices based on the developed information and data quality standards.
- 1 July 2015
- Published by SAGE Publications in Telemedicine and e-Health
- Vol. 21 (7) , 567-574
A Mobile Health Application to Predict Postpartum Depression Based on Machine Learning
Background: Postpartum depression (PPD) is a disorder that often goes undiagnosed. The development of a screening program requires considerable and careful effort, where evidence-based decisions have to be taken in order to obtain an effective test with a high level of sensitivity and an acceptable specificity that is quick to perform, easy to interpret, culturally sensitive, and cost-effective. The purpose of this article is twofold: first, to develop classification models for detecting the risk of PPD during the first week after childbirth, thus enabling early intervention; and second, to develop a mobile health (m-health) application (app) for the Android ® (Google, Mountain View, CA) platform based on the model with best performance for both mothers who have just given birth and clinicians who want to monitor their patient's test. Materials and Methods: A set of predictive models for estimating the risk of PPD was trained using machine learning techniques and data about postpartum women collected from seven Spanish hospitals. An internal evaluation was carried out using a hold-out strategy. An easy flowchart and architecture for designing the graphical user interface of the m-health app was followed. Results: Naive Bayes showed the best balance between sensitivity and specificity as a predictive model for PPD during the first week after delivery. It was integrated into the clinical decision support system for Android mobile apps. Conclusions: This approach can enable the early prediction and detection of PPD because it fulfills the conditions of an effective screening test with a high level of sensitivity and specificity that is quick to perform, easy to interpret, culturally sensitive, and cost-effective.
- 1 July 2015
- Published by SAGE Publications in Telemedicine and e-Health
- Vol. 21 (7) , 567-574
A Mobile Health Application to Predict Postpartum Depression Based on Machine Learning
Background: Postpartum depression (PPD) is a disorder that often goes undiagnosed. The development of a screening program requires considerable and careful effort, where evidence-based decisions have to be taken in order to obtain an effective test with a high level of sensitivity and an acceptable specificity that is quick to perform, easy to interpret, culturally sensitive, and cost-effective. The purpose of this article is twofold: first, to develop classification models for detecting the risk of PPD during the first week after childbirth, thus enabling early intervention; and second, to develop a mobile health (m-health) application (app) for the Android ® (Google, Mountain View, CA) platform based on the model with best performance for both mothers who have just given birth and clinicians who want to monitor their patient's test. Materials and Methods: A set of predictive models for estimating the risk of PPD was trained using machine learning techniques and data about postpartum women collected from seven Spanish hospitals. An internal evaluation was carried out using a hold-out strategy. An easy flowchart and architecture for designing the graphical user interface of the m-health app was followed. Results: Naive Bayes showed the best balance between sensitivity and specificity as a predictive model for PPD during the first week after delivery. It was integrated into the clinical decision support system for Android mobile apps. Conclusions: This approach can enable the early prediction and detection of PPD because it fulfills the conditions of an effective screening test with a high level of sensitivity and specificity that is quick to perform, easy to interpret, culturally sensitive, and cost-effective.
- 29 May 2015
- Published by Springer Nature
- p. 363-371
A Multiagent System Proposal for 30 Day Readmission Problem Management
- 29 May 2015
- Published by Springer Nature
- p. 363-371
A Multiagent System Proposal for 30 Day Readmission Problem Management
- 5 November 2014
- Published by Springer Nature
- Vol. 1246, 57-78
Incremental Logistic Regression for Customizing Automatic Diagnostic Models
In the last decades, and following the new trends in medicine, statistical learning techniques have been used for developing automatic diagnostic models for aiding the clinical experts throughout the use of Clinical Decision Support Systems. The development of these models requires a large, representative amount of data, which is commonly obtained from one hospital or a group of hospitals after an expensive and time-consuming gathering, preprocess, and validation of cases. After the model development, it has to overcome an external validation that is often carried out in a different hospital or health center. The experience is that the models show underperformed expectations. Furthermore, patient data needs ethical approval and patient consent to send and store data. For these reasons, we introduce an incremental learning algorithm base on the Bayesian inference approach that may allow us to build an initial model with a smaller number of cases and update it incrementally when new data are collected or even perform a new calibration of a model from a different center by using a reduced number of cases. The performance of our algorithm is demonstrated by employing different benchmark datasets and a real brain tumor dataset; and we compare its performance to a previous incremental algorithm and a non-incremental Bayesian model, showing that the algorithm is independent of the data model, iterative, and has a good convergence.
- 5 November 2014
- Published by Springer Nature
- Vol. 1246, 57-78
Incremental Logistic Regression for Customizing Automatic Diagnostic Models
In the last decades, and following the new trends in medicine, statistical learning techniques have been used for developing automatic diagnostic models for aiding the clinical experts throughout the use of Clinical Decision Support Systems. The development of these models requires a large, representative amount of data, which is commonly obtained from one hospital or a group of hospitals after an expensive and time-consuming gathering, preprocess, and validation of cases. After the model development, it has to overcome an external validation that is often carried out in a different hospital or health center. The experience is that the models show underperformed expectations. Furthermore, patient data needs ethical approval and patient consent to send and store data. For these reasons, we introduce an incremental learning algorithm base on the Bayesian inference approach that may allow us to build an initial model with a smaller number of cases and update it incrementally when new data are collected or even perform a new calibration of a model from a different center by using a reduced number of cases. The performance of our algorithm is demonstrated by employing different benchmark datasets and a real brain tumor dataset; and we compare its performance to a previous incremental algorithm and a non-incremental Bayesian model, showing that the algorithm is independent of the data model, iterative, and has a good convergence.
- 5 November 2014
- Published by Springer Nature
- Vol. 1246, 19-37
Definition of Loss Functions for Learning from Imbalanced Data to Minimize Evaluation Metrics
Most learning algorithms for classification use objective functions based on regularized and/or continuous versions of the 0-1 loss function. Moreover, the performance of the classification models is usually measured by means of the empirical error or misclassification rate. Nevertheless, neither those loss functions nor the empirical error is adequate for learning from imbalanced data. In these problems, the empirical error is uninformative about the performance of the classifier and the loss functions usually produce models that are shifted to the majority class. This study defines the loss function L BER whose associated empirical risk is equal to the BER. Our results show that classifiers based on our L BER loss function are optimal in terms of the BER evaluation metric. Furthermore, the boundaries of the classifiers were invariant to the imbalance ratio of the training dataset. The L BER-based models outperformed the 0-1-based models and other algorithms for imbalanced data in terms of BER, regardless of the prevalence of the positive class. Finally, we demonstrate the equivalence of the loss function to the method of inverted prior probabilities, and we define the family of loss functions L WER that is associated with any WER evaluation metric by the generalization of L BER.
- 5 November 2014
- Published by Springer Nature
- Vol. 1246, 19-37
Definition of Loss Functions for Learning from Imbalanced Data to Minimize Evaluation Metrics
Most learning algorithms for classification use objective functions based on regularized and/or continuous versions of the 0-1 loss function. Moreover, the performance of the classification models is usually measured by means of the empirical error or misclassification rate. Nevertheless, neither those loss functions nor the empirical error is adequate for learning from imbalanced data. In these problems, the empirical error is uninformative about the performance of the classifier and the loss functions usually produce models that are shifted to the majority class. This study defines the loss function L BER whose associated empirical risk is equal to the BER. Our results show that classifiers based on our L BER loss function are optimal in terms of the BER evaluation metric. Furthermore, the boundaries of the classifiers were invariant to the imbalance ratio of the training dataset. The L BER-based models outperformed the 0-1-based models and other algorithms for imbalanced data in terms of BER, regardless of the prevalence of the positive class. Finally, we demonstrate the equivalence of the loss function to the method of inverted prior probabilities, and we define the family of loss functions L WER that is associated with any WER evaluation metric by the generalization of L BER.
- 1 September 2014
- Published by Elsevier in International Journal of Radiation Oncology - Biology - Physics (IJROBP)
- Vol. 90 (1) , S593-S594
Computerized Decision Support System and Naïve Bayes Models for Predicting the Risk of Relapse in Breast Cancer
- 1 September 2014
- Published by Elsevier in International Journal of Radiation Oncology - Biology - Physics (IJROBP)
- Vol. 90 (1) , S593-S594
Computerized Decision Support System and Naïve Bayes Models for Predicting the Risk of Relapse in Breast Cancer