Fausto Barlocco
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Fausto Barlocco has a total of 55 co-authors. Here are the top co-authors by number of shared publications:
- Iacopo Olivotto
University of Florence
5 shared publications - Dejana Popovic
Department of Cardiology, Clinical Center of Serbia, 11000 Belgrade, Serbia
3 shared publications - Djordje G. Jakovljevic
Cardiovascular and Translational Medicine, Coventry University, Coventry, UK
3 shared publications - Guy A. MacGowan
Department of Cardiology, Freeman Hospital, Newcastle upon Tyne, UK
3 shared publications - Lars Siegfried Maier
Department of Internal Medicine II University Hospital Regensburg Regensburg Germany
3 shared publications - Lazar Velicki
Faculty of Medicine, University of Novi Sad, 21000 Novi Sad, Serbia
3 shared publications
Latest Publications
- Open Access
- 25 June 2026
- Published by MDPI AG in International Journal of Environmental Research and Public Health
- Vol. 23 (7) , 833
Assessing Quality of Life in Genetic Cardiomyopathies: A Scoping Review
Genetic cardiomyopathies (GCMs) are chronic heart muscle disorders requiring lifelong monitoring and treatment. Although quality of life (QoL) and health-related quality of life (HRQoL) are increasingly recognized as important outcomes in cardiomyopathy care, their conceptualization and measurement remain inconsistent. This scoping review aims to (a) identify the tools most commonly used to assess QoL and HRQoL in adults with genetic cardiomyopathies and (b) map the thematic areas of existing studies, including symptom burden, psychological distress, diagnostic challenges, and the impact of medical and psychological interventions. PubMed, Scopus, and PsycINFO were systematically searched, and the final search was completed in November 2025. Seventeen peer-reviewed studies met the inclusion criteria and were included in this scoping review. The review followed the PRISMA extension for Scoping Reviews and included both quantitative, qualitative and mixed-methods designs. Most studies employed standardized tools such as EQ-5D (N = 5), SF-36/SF36v2 (N = 5), and the Kansas City Cardiomyopathy Questionnaire (N = 3), while others included the Minnesota Living with Heart Failure Questionnaire (N = 2) and disease-specific or ad hoc measures. The most frequently investigated themes included impairments in physical functioning, emotional well-being, symptom burden, psychological distress, and social participation. Several studies showed that patients’ perceived QoL was more closely associated with symptom burden and psychological adjustment than with objective clinical indicators alone. Clinical interventions showed mixed or limited effects on QoL and HRQoL outcomes, even when clinical parameters improved. Qualitative research further emphasized the lived experiences of patients and families, highlighting unmet needs in care. Less commonly addressed findings concerned caregiver perspectives, patient–provider communication, treatment adherence, socioeconomic disadvantage, healthcare costs, productivity loss, and the experiences of patients with rarer cardiomyopathy-related conditions. The results highlight how QoL and HRQoL are central but still inconsistently assessed outcomes in cardiomyopathy research. This review calls for greater conceptual clarity between QoL and HRQoL, greater standardization in measurement tools, broader inclusion of psychosocial variables, and more patient-centred research approaches to better support individuals living with cardiomyopathies.
- 25 June 2026
- Published by MDPI AG in International Journal of Environmental Research and Public Health
- Vol. 23 (7) , 833
Open AccessAssessing Quality of Life in Genetic Cardiomyopathies: A Scoping Review
Genetic cardiomyopathies (GCMs) are chronic heart muscle disorders requiring lifelong monitoring and treatment. Although quality of life (QoL) and health-related quality of life (HRQoL) are increasingly recognized as important outcomes in cardiomyopathy care, their conceptualization and measurement remain inconsistent. This scoping review aims to (a) identify the tools most commonly used to assess QoL and HRQoL in adults with genetic cardiomyopathies and (b) map the thematic areas of existing studies, including symptom burden, psychological distress, diagnostic challenges, and the impact of medical and psychological interventions. PubMed, Scopus, and PsycINFO were systematically searched, and the final search was completed in November 2025. Seventeen peer-reviewed studies met the inclusion criteria and were included in this scoping review. The review followed the PRISMA extension for Scoping Reviews and included both quantitative, qualitative and mixed-methods designs. Most studies employed standardized tools such as EQ-5D (N = 5), SF-36/SF36v2 (N = 5), and the Kansas City Cardiomyopathy Questionnaire (N = 3), while others included the Minnesota Living with Heart Failure Questionnaire (N = 2) and disease-specific or ad hoc measures. The most frequently investigated themes included impairments in physical functioning, emotional well-being, symptom burden, psychological distress, and social participation. Several studies showed that patients’ perceived QoL was more closely associated with symptom burden and psychological adjustment than with objective clinical indicators alone. Clinical interventions showed mixed or limited effects on QoL and HRQoL outcomes, even when clinical parameters improved. Qualitative research further emphasized the lived experiences of patients and families, highlighting unmet needs in care. Less commonly addressed findings concerned caregiver perspectives, patient–provider communication, treatment adherence, socioeconomic disadvantage, healthcare costs, productivity loss, and the experiences of patients with rarer cardiomyopathy-related conditions. The results highlight how QoL and HRQoL are central but still inconsistently assessed outcomes in cardiomyopathy research. This review calls for greater conceptual clarity between QoL and HRQoL, greater standardization in measurement tools, broader inclusion of psychosocial variables, and more patient-centred research approaches to better support individuals living with cardiomyopathies.
- Open Access
- 1 October 2022
- Published by Oxford University Press (OUP) in European Heart Journal
- Vol. 43 (Supplement)
ECG as a storytelling of cardiac involvement evolution in Anderson Fabry disease
Background: Cardiac involvement in Anderson-Fabry disease (AFD) is related to a progressive glycosphingolipid storage over time and is characterized by left ventricular hypertrophy (LVH), conduction abnormalities and myocardial fibrosis. ECG is useful for early recognition of AFD, however evidence is limited on the association between ECG alterations and disease stage. Purpose: To assess the relationship between ECG characteristics and progressive cardiac involvement, from the pre-hypertrophic phase to phenotypes with increasing degree of LVH. Methods: In a multicenter cohort, 183 AFD patients (40% male, age 47±12 years, 60% affected by “classical AFD”) underwent ECG and transthoracic echocardiography. Patients were divided into 4 groups according to the different degree of LV thickness measured in parasternal short axis view: group A ≤9 mm (N=46, 25%), group B 10–14 mm (N=77, 42%), group C 15–19 mm (N=45, 25%) and group D ≥20 mm (N=15, 8%). Patients with pacemaker and under 18 years of age were excluded. Results: A normal ECG was present in 89% in group A, 59% in group B, 11% in group C and it was absent in group D. Short PR (<120 ms) was more frequent in group A, whereas with LVH increasing, median PR interval duration significantly prolonged among the 4 groups (136 [125–150]vs 141 [130–160] vs 160 [130–180] vs 170 [130–180] ms, p=0.002 respectively). Median P-wave duration was shorter in group A and B compared to group C and D (80 m vs 100 ms, p<0.001), while both QRS and QTc gradually increased. Median Sokolow-Lyon voltage criteria statistically augmented among the groups (22 [18–26] vs 27 [20–33] vs 32 [25–45] vs 35 [18–40] mm, p<0.001 respectively), along with right ventricular hypertrophy (0%, 1%, 11%, 8%, p=0.02). Right bundle branch block (RBBB) had a higher frequency in advanced stages (0%, 34%, 34%, 40%, p<0.001), with a prevalence of complete RBBB of 46% in group D. Similarly, left anterior fascicular block (0%, 7%, 18%, 46%, p<0.001) and QRS fragmentation (2%, 11%, 25%, 23%, p=0.009) were more common in advanced stages. No differences were found in left bundle branch block (LBBB), in low QRS voltages or in LV pre-excitation prevalence. According with the wall thickness increase, negative T waves were more frequent in lateral (4%, 21%, 70%, 77%, p<0.001) and inferior leads (6%, 15%, 32%, 46%, p 0.001), as well as their association with ST-T depression (4%, 17%, 64%, 46%, p<0.001). Giant negative T waves were present only in group C and D (16% and 31%) mainly representing a LVH distribution toward the apex. Conclusions: ECG is a very useful tool to stage cardiac involvement evolution in AFD. Peculiar ECG characteristics evolve together with LV wall thickness: incomplete and progressively complete RBBB usually associated (preceding or following) LVH and/or typical repolarization abnormalities in inferior or lateral leads and giant negative T waves in the more advanced stages are the most frequent and typical ECG patterns. Funding Acknowledgement: Type of funding sources: None.
- 1 October 2022
- Published by Oxford University Press (OUP) in European Heart Journal
- Vol. 43 (Supplement)
Open AccessECG as a storytelling of cardiac involvement evolution in Anderson Fabry disease
Background: Cardiac involvement in Anderson-Fabry disease (AFD) is related to a progressive glycosphingolipid storage over time and is characterized by left ventricular hypertrophy (LVH), conduction abnormalities and myocardial fibrosis. ECG is useful for early recognition of AFD, however evidence is limited on the association between ECG alterations and disease stage. Purpose: To assess the relationship between ECG characteristics and progressive cardiac involvement, from the pre-hypertrophic phase to phenotypes with increasing degree of LVH. Methods: In a multicenter cohort, 183 AFD patients (40% male, age 47±12 years, 60% affected by “classical AFD”) underwent ECG and transthoracic echocardiography. Patients were divided into 4 groups according to the different degree of LV thickness measured in parasternal short axis view: group A ≤9 mm (N=46, 25%), group B 10–14 mm (N=77, 42%), group C 15–19 mm (N=45, 25%) and group D ≥20 mm (N=15, 8%). Patients with pacemaker and under 18 years of age were excluded. Results: A normal ECG was present in 89% in group A, 59% in group B, 11% in group C and it was absent in group D. Short PR (<120 ms) was more frequent in group A, whereas with LVH increasing, median PR interval duration significantly prolonged among the 4 groups (136 [125–150]vs 141 [130–160] vs 160 [130–180] vs 170 [130–180] ms, p=0.002 respectively). Median P-wave duration was shorter in group A and B compared to group C and D (80 m vs 100 ms, p<0.001), while both QRS and QTc gradually increased. Median Sokolow-Lyon voltage criteria statistically augmented among the groups (22 [18–26] vs 27 [20–33] vs 32 [25–45] vs 35 [18–40] mm, p<0.001 respectively), along with right ventricular hypertrophy (0%, 1%, 11%, 8%, p=0.02). Right bundle branch block (RBBB) had a higher frequency in advanced stages (0%, 34%, 34%, 40%, p<0.001), with a prevalence of complete RBBB of 46% in group D. Similarly, left anterior fascicular block (0%, 7%, 18%, 46%, p<0.001) and QRS fragmentation (2%, 11%, 25%, 23%, p=0.009) were more common in advanced stages. No differences were found in left bundle branch block (LBBB), in low QRS voltages or in LV pre-excitation prevalence. According with the wall thickness increase, negative T waves were more frequent in lateral (4%, 21%, 70%, 77%, p<0.001) and inferior leads (6%, 15%, 32%, 46%, p 0.001), as well as their association with ST-T depression (4%, 17%, 64%, 46%, p<0.001). Giant negative T waves were present only in group C and D (16% and 31%) mainly representing a LVH distribution toward the apex. Conclusions: ECG is a very useful tool to stage cardiac involvement evolution in AFD. Peculiar ECG characteristics evolve together with LV wall thickness: incomplete and progressively complete RBBB usually associated (preceding or following) LVH and/or typical repolarization abnormalities in inferior or lateral leads and giant negative T waves in the more advanced stages are the most frequent and typical ECG patterns. Funding Acknowledgement: Type of funding sources: None.
- Open Access
- 1 October 2022
- Published by Oxford University Press (OUP) in European Heart Journal
- Vol. 43 (Supplement)
Electrocardiographic evolution in Anderson-Fabry disease patients on and off specific therapy: a potential marker to study the therapeutic cardiac goal
Background: Anderson Fabry disease (AFD) is an X-linked lysosomal storage disorder leading to a deficiency in α-galactosidase A and globotriasylceramide (Gb3) deposition in different organs, including the heart. In AFD patients electrocardiogram (ECG) represents an important tool to detect cardiac involvement. AFD specific therapy (enzyme replacement or chaperon therapy) has shown to modify the natural history of the disease and to decrease Gb3 levels, but so far there are no data on its influence on ECG evolution. Purpose: To assess the progression of ECG features in AFD patients on and off specific disease therapy and to evaluate the potential role of ECG in studying the cardiac specific response to therapy. Methods: We recruited 170 patients with an established AFD diagnosis, ≥18 years old (64 males 38%, median age 46±15 years) in a multicentre study cohort. We analysed their ECG evolution for a median follow-up of 64±48 months in patients off (group A, N=63) and on (group B, N=107) specific therapy. Results: AFD patients off specific disease therapy (group A) had similar age at baseline compared to those on therapy (47±14 vs 44±12 years; p=0,171), however significantly differed for males prevalence [13 (21%) vs 51 (48%); p≤0,001], classic phenotype [36 (57%) vs 82 (77%); p<0,001)] and maximal wall thickness [11±3 vs 13±4 mm; p≤0,0001]. As regards ECG features at baseline, group A showed a lower prevalence of repolarization anomalies [16 (25%) vs 51 (48%), p=0,005], left ventricular hypertrophy [14 (22%) vs 51 (48%), p=0,001], pseudo necrosis [4 (6%) vs 18 (17%) vs, p≤0,060] and short PR [2 (3%) vs 12 (11%), p=0.0845]. During the follow-up ECG progression was observed in 9 patients in group A (14%), characterized by the development of repolarization anomalies (N=5; 8%), incomplete right bundle block (N=4; 6%), shortening of PR interval (N=2; 3%), left ventricular hypertrophy (N=2; 3%), left atrial enlargement (N=2; 3%) and complete right bundle block (N=1; 2%). Differently, in group B an ECG evolution was observed in 31 patients (29%) characterized by the development of repolarization anomalies (N=19; 18%), left atrial enlargement (N=12; 12%), complete right bundle block (N=8; 8%), left anterior fascicular hemiblock (N=4; 4%), left bundle block (N=4, 4%) and left ventricular hypertrophy (N=3; 3%). Among patients off therapy we observed an improvement of ECG in 1 patient characterized by regression of repolarization anomalies, which could be explained with the presence of transient overload anomalies. Conclusion: In AFD patients off and on specific disease therapy, ECG evolution was detected in 14% and 29% respectively, consistently with the more advanced cardiac involvement in patients on therapy (higher prevalence of male sex, classic phenotype and higher maximum wall thickness). The fact that one third of the patients showed ECG changes progression despite being on specific disease therapy could be relevant to better defined the therapeutic cardiac goal. Funding Acknowledgement: Type of funding sources: None.
- 1 October 2022
- Published by Oxford University Press (OUP) in European Heart Journal
- Vol. 43 (Supplement)
Open AccessElectrocardiographic evolution in Anderson-Fabry disease patients on and off specific therapy: a potential marker to study the therapeutic cardiac goal
Background: Anderson Fabry disease (AFD) is an X-linked lysosomal storage disorder leading to a deficiency in α-galactosidase A and globotriasylceramide (Gb3) deposition in different organs, including the heart. In AFD patients electrocardiogram (ECG) represents an important tool to detect cardiac involvement. AFD specific therapy (enzyme replacement or chaperon therapy) has shown to modify the natural history of the disease and to decrease Gb3 levels, but so far there are no data on its influence on ECG evolution. Purpose: To assess the progression of ECG features in AFD patients on and off specific disease therapy and to evaluate the potential role of ECG in studying the cardiac specific response to therapy. Methods: We recruited 170 patients with an established AFD diagnosis, ≥18 years old (64 males 38%, median age 46±15 years) in a multicentre study cohort. We analysed their ECG evolution for a median follow-up of 64±48 months in patients off (group A, N=63) and on (group B, N=107) specific therapy. Results: AFD patients off specific disease therapy (group A) had similar age at baseline compared to those on therapy (47±14 vs 44±12 years; p=0,171), however significantly differed for males prevalence [13 (21%) vs 51 (48%); p≤0,001], classic phenotype [36 (57%) vs 82 (77%); p<0,001)] and maximal wall thickness [11±3 vs 13±4 mm; p≤0,0001]. As regards ECG features at baseline, group A showed a lower prevalence of repolarization anomalies [16 (25%) vs 51 (48%), p=0,005], left ventricular hypertrophy [14 (22%) vs 51 (48%), p=0,001], pseudo necrosis [4 (6%) vs 18 (17%) vs, p≤0,060] and short PR [2 (3%) vs 12 (11%), p=0.0845]. During the follow-up ECG progression was observed in 9 patients in group A (14%), characterized by the development of repolarization anomalies (N=5; 8%), incomplete right bundle block (N=4; 6%), shortening of PR interval (N=2; 3%), left ventricular hypertrophy (N=2; 3%), left atrial enlargement (N=2; 3%) and complete right bundle block (N=1; 2%). Differently, in group B an ECG evolution was observed in 31 patients (29%) characterized by the development of repolarization anomalies (N=19; 18%), left atrial enlargement (N=12; 12%), complete right bundle block (N=8; 8%), left anterior fascicular hemiblock (N=4; 4%), left bundle block (N=4, 4%) and left ventricular hypertrophy (N=3; 3%). Among patients off therapy we observed an improvement of ECG in 1 patient characterized by regression of repolarization anomalies, which could be explained with the presence of transient overload anomalies. Conclusion: In AFD patients off and on specific disease therapy, ECG evolution was detected in 14% and 29% respectively, consistently with the more advanced cardiac involvement in patients on therapy (higher prevalence of male sex, classic phenotype and higher maximum wall thickness). The fact that one third of the patients showed ECG changes progression despite being on specific disease therapy could be relevant to better defined the therapeutic cardiac goal. Funding Acknowledgement: Type of funding sources: None.
- Open Access
Gender Related Differences in the Clinical Presentation of Hypertrophic Cardiomyopathy—An Analysis from the SILICOFCM Database
Background and Objectives: Hypertrophic cardiomyopathy (HCM) is the most common inherited cardiac disease that affects approximately 1 in 500 people. Due to an incomplete disease penetrance associated with numerous factors, HCM is not manifested in all carriers of genetic mutation. Although about two-thirds of patients are male, it seems that female gender is associated with more severe disease phenotype and worse prognosis. The objective of this study was to evaluate the gender related differences in HCM presentation. Materials and Methods: This study was conducted as a part of the international multidisciplinary SILICOFCM project. Clinical information, laboratory analyses, electrocardiography, echocardiography, and genetic testing data were collected for 362 HCM patients from four clinical centers (Florence, Newcastle, Novi Sad, and Regensburg). There were 33% female patients, and 67% male patients. Results: Female patients were older than males (64.5 vs. 53.5 years, p < 0.0005). The male predominance was present across all age groups until the age of 70, when gender distribution became comparable. Females had higher number of symptomatic individuals then males (69% vs. 52%, p = 0.003), most frequently complaining of dyspnea (50% vs. 30%), followed by chest pain (30% vs. 17%), fatigue (26% vs. 13%), palpitations (22% vs. 13%), and syncope (13% vs. 8%). The most common rhythm disorder was atrial fibrillation which was present in a similar number of females and males (19% vs. 13%, p = 0.218). Levels of N-terminal pro-brain natriuretic peptide were comparable between the genders (571 vs. 794 ng/L, p = 0.244). Echocardiography showed similar thickness of interventricular septum (18 vs. 16 mm, p = 0.121) and posterolateral wall (13 vs. 12 mm, p = 0.656), however, females had a lower number of systolic anterior motion (8% vs. 16%, p = 0.020) and other mitral valve abnormalities. Conclusions: Female patients are underrepresented but seem to have a more pronounced clinical presentation of HCM. Therefore, establishing gender specific diagnostic criteria for HCM should be considered.
Open AccessGender Related Differences in the Clinical Presentation of Hypertrophic Cardiomyopathy—An Analysis from the SILICOFCM Database
Background and Objectives: Hypertrophic cardiomyopathy (HCM) is the most common inherited cardiac disease that affects approximately 1 in 500 people. Due to an incomplete disease penetrance associated with numerous factors, HCM is not manifested in all carriers of genetic mutation. Although about two-thirds of patients are male, it seems that female gender is associated with more severe disease phenotype and worse prognosis. The objective of this study was to evaluate the gender related differences in HCM presentation. Materials and Methods: This study was conducted as a part of the international multidisciplinary SILICOFCM project. Clinical information, laboratory analyses, electrocardiography, echocardiography, and genetic testing data were collected for 362 HCM patients from four clinical centers (Florence, Newcastle, Novi Sad, and Regensburg). There were 33% female patients, and 67% male patients. Results: Female patients were older than males (64.5 vs. 53.5 years, p < 0.0005). The male predominance was present across all age groups until the age of 70, when gender distribution became comparable. Females had higher number of symptomatic individuals then males (69% vs. 52%, p = 0.003), most frequently complaining of dyspnea (50% vs. 30%), followed by chest pain (30% vs. 17%), fatigue (26% vs. 13%), palpitations (22% vs. 13%), and syncope (13% vs. 8%). The most common rhythm disorder was atrial fibrillation which was present in a similar number of females and males (19% vs. 13%, p = 0.218). Levels of N-terminal pro-brain natriuretic peptide were comparable between the genders (571 vs. 794 ng/L, p = 0.244). Echocardiography showed similar thickness of interventricular septum (18 vs. 16 mm, p = 0.121) and posterolateral wall (13 vs. 12 mm, p = 0.656), however, females had a lower number of systolic anterior motion (8% vs. 16%, p = 0.020) and other mitral valve abnormalities. Conclusions: Female patients are underrepresented but seem to have a more pronounced clinical presentation of HCM. Therefore, establishing gender specific diagnostic criteria for HCM should be considered.
- Open Access
- 2 February 2022
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 10 (2) , e30483
Disease Progression of Hypertrophic Cardiomyopathy: Modeling Using Machine Learning
Background: Cardiovascular disorders in general are responsible for 30% of deaths worldwide. Among them, hypertrophic cardiomyopathy (HCM) is a genetic cardiac disease that is present in about 1 of 500 young adults and can cause sudden cardiac death (SCD). Objective: Although the current state-of-the-art methods model the risk of SCD for patients, to the best of our knowledge, no methods are available for modeling the patient's clinical status up to 10 years ahead. In this paper, we propose a novel machine learning (ML)-based tool for predicting disease progression for patients diagnosed with HCM in terms of adverse remodeling of the heart during a 10-year period. Methods: The method consisted of 6 predictive regression models that independently predict future values of 6 clinical characteristics: left atrial size, left atrial volume, left ventricular ejection fraction, New York Heart Association functional classification, left ventricular internal diastolic diameter, and left ventricular internal systolic diameter. We supplemented each prediction with the explanation that is generated using the Shapley additive explanation method. Results: The final experiments showed that predictive error is lower on 5 of the 6 constructed models in comparison to experts (on average, by 0.34) or a consortium of experts (on average, by 0.22). The experiments revealed that semisupervised learning and the artificial data from virtual patients help improve predictive accuracies. The best-performing random forest model improved R2 from 0.3 to 0.6. Conclusions: By engaging medical experts to provide interpretation and validation of the results, we determined the models' favorable performance compared to the performance of experts for 5 of 6 targets.
- 2 February 2022
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 10 (2) , e30483
Open AccessDisease Progression of Hypertrophic Cardiomyopathy: Modeling Using Machine Learning
Background: Cardiovascular disorders in general are responsible for 30% of deaths worldwide. Among them, hypertrophic cardiomyopathy (HCM) is a genetic cardiac disease that is present in about 1 of 500 young adults and can cause sudden cardiac death (SCD). Objective: Although the current state-of-the-art methods model the risk of SCD for patients, to the best of our knowledge, no methods are available for modeling the patient's clinical status up to 10 years ahead. In this paper, we propose a novel machine learning (ML)-based tool for predicting disease progression for patients diagnosed with HCM in terms of adverse remodeling of the heart during a 10-year period. Methods: The method consisted of 6 predictive regression models that independently predict future values of 6 clinical characteristics: left atrial size, left atrial volume, left ventricular ejection fraction, New York Heart Association functional classification, left ventricular internal diastolic diameter, and left ventricular internal systolic diameter. We supplemented each prediction with the explanation that is generated using the Shapley additive explanation method. Results: The final experiments showed that predictive error is lower on 5 of the 6 constructed models in comparison to experts (on average, by 0.34) or a consortium of experts (on average, by 0.22). The experiments revealed that semisupervised learning and the artificial data from virtual patients help improve predictive accuracies. The best-performing random forest model improved R2 from 0.3 to 0.6. Conclusions: By engaging medical experts to provide interpretation and validation of the results, we determined the models' favorable performance compared to the performance of experts for 5 of 6 targets.
- Open Access
- 18 May 2021
- Published by JMIR Publications Inc. in JMIR Preprints
Disease Progression of Hypertrophic Cardiomyopathy: Modeling Using Machine Learning (Preprint)
BACKGROUND Cardiovascular disorders in general are responsible for 30% of deaths worldwide. Among them, hypertrophic cardiomyopathy (HCM) is a genetic cardiac disease that is present in about 1 of 500 young adults and can cause sudden cardiac death (SCD). OBJECTIVE Although the current state-of-the-art methods model the risk of SCD for patients, to the best of our knowledge, no methods are available for modeling the patient's clinical status up to 10 years ahead. In this paper, we propose a novel machine learning (ML)-based tool for predicting disease progression for patients diagnosed with HCM in terms of adverse remodeling of the heart during a 10-year period. METHODS The method consisted of 6 predictive regression models that independently predict future values of 6 clinical characteristics: left atrial size, left atrial volume, left ventricular ejection fraction, New York Heart Association functional classification, left ventricular internal diastolic diameter, and left ventricular internal systolic diameter. We supplemented each prediction with the explanation that is generated using the Shapley additive explanation method. RESULTS The final experiments showed that predictive error is lower on 5 of the 6 constructed models in comparison to experts (on average, by 0.34) or a consortium of experts (on average, by 0.22). The experiments revealed that semisupervised learning and the artificial data from virtual patients help improve predictive accuracies. The best-performing random forest model improved R2 from 0.3 to 0.6. CONCLUSIONS By engaging medical experts to provide interpretation and validation of the results, we determined the models' favorable performance compared to the performance of experts for 5 of 6 targets.
- 18 May 2021
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessDisease Progression of Hypertrophic Cardiomyopathy: Modeling Using Machine Learning (Preprint)
BACKGROUND Cardiovascular disorders in general are responsible for 30% of deaths worldwide. Among them, hypertrophic cardiomyopathy (HCM) is a genetic cardiac disease that is present in about 1 of 500 young adults and can cause sudden cardiac death (SCD). OBJECTIVE Although the current state-of-the-art methods model the risk of SCD for patients, to the best of our knowledge, no methods are available for modeling the patient's clinical status up to 10 years ahead. In this paper, we propose a novel machine learning (ML)-based tool for predicting disease progression for patients diagnosed with HCM in terms of adverse remodeling of the heart during a 10-year period. METHODS The method consisted of 6 predictive regression models that independently predict future values of 6 clinical characteristics: left atrial size, left atrial volume, left ventricular ejection fraction, New York Heart Association functional classification, left ventricular internal diastolic diameter, and left ventricular internal systolic diameter. We supplemented each prediction with the explanation that is generated using the Shapley additive explanation method. RESULTS The final experiments showed that predictive error is lower on 5 of the 6 constructed models in comparison to experts (on average, by 0.34) or a consortium of experts (on average, by 0.22). The experiments revealed that semisupervised learning and the artificial data from virtual patients help improve predictive accuracies. The best-performing random forest model improved R2 from 0.3 to 0.6. CONCLUSIONS By engaging medical experts to provide interpretation and validation of the results, we determined the models' favorable performance compared to the performance of experts for 5 of 6 targets.
- Open Access
- 5 August 2020
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 15 (8) , e0236814
Doctor-patient care relationship in genetic cardiomyopathies: An exploratory study on clinical consultations
The present study aims to explore the setting of consultation and communication between physicians and patients affected by genetic cardiomyopathies, investigating how the two parts of the therapeutic relationship participate and share information. 45 adult patients affected by various cardiomyopathies took part in a prospective case study while attending consultations at a cardiologic outpatient clinic constituting an Italian referral centre for cardiomyopathies. A researcher observed the consultations, which were audio-recorded and transcribed. Transcripts were coded and an analysis of setting, type of communication implemented and participation of doctors and patients in terms of word-count and type of questions/answers was carried out. Overall word-count was significantly higher for physicians than for patients (t(44) = 9,506; pt(44) = -11,90; pt(44) = 5.58; pr = .838; p<0.001). Findings emphasize patients’ need for adequate time and space to share their subjective illness experience with the physician, within an approach informed by the insights and recommendations of Narrative Medicine. These findings are instrumental to improving the specific clinical setting for individuals with genetic cardiomyopathies.
- 5 August 2020
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 15 (8) , e0236814
Open AccessDoctor-patient care relationship in genetic cardiomyopathies: An exploratory study on clinical consultations
The present study aims to explore the setting of consultation and communication between physicians and patients affected by genetic cardiomyopathies, investigating how the two parts of the therapeutic relationship participate and share information. 45 adult patients affected by various cardiomyopathies took part in a prospective case study while attending consultations at a cardiologic outpatient clinic constituting an Italian referral centre for cardiomyopathies. A researcher observed the consultations, which were audio-recorded and transcribed. Transcripts were coded and an analysis of setting, type of communication implemented and participation of doctors and patients in terms of word-count and type of questions/answers was carried out. Overall word-count was significantly higher for physicians than for patients (t(44) = 9,506; pt(44) = -11,90; pt(44) = 5.58; pr = .838; p<0.001). Findings emphasize patients’ need for adequate time and space to share their subjective illness experience with the physician, within an approach informed by the insights and recommendations of Narrative Medicine. These findings are instrumental to improving the specific clinical setting for individuals with genetic cardiomyopathies.