Nuria Pastor

Nuria Pastor

Auto-generated profile, based on publicly available information

Nuria Pastor

Vitalera, FollowHealth S.L.,Barcelona,Spain

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 September 2024 in Journal of the American Medical Informatics Association
Verified
Journal Article
Open access
PDF file
SLSteven Labkoff
Steven Labkoff
BOBilikis Oladimeji
Bilikis Oladimeji
JKJoseph Kannry
Joseph Kannry
ASAnthony Solomonides
Anthony Solomonides
RLRussell Leftwich
Russell Leftwich
YQYuri Quintana
Yuri Quintana
Background: Integrating artificial intelligence (AI) in healthcare settings has the potential to benefit clinical decision-making. Addressing challenges such as ensuring trustworthiness, mitigating bias, and maintaining safety is paramount. The lack of established methodologies for pre- and post-deployment evaluation of AI tools regarding crucial attributes such as transparency, performance monitoring, and adverse event reporting makes this situation challenging. Objectives: This paper aims to make practical suggestions for creating methods, rules, and guidelines to ensure that the development, testing, supervision, and use of AI in clinical decision support (CDS) systems are done well and safely for patients. Materials and Methods: In May 2023, the Division of Clinical Informatics at Beth Israel Deaconess Medical Center and the American Medical Informatics Association co-sponsored a working group on AI in healthcare. In August 2023, there were 4 webinars on AI topics and a 2-day workshop in September 2023 for consensus-building. The event included over 200 industry stakeholders, including clinicians, software developers, academics, ethicists, attorneys, government policy experts, scientists, and patients. The goal was to identify challenges associated with the trusted use of AI-enabled CDS in medical practice. Key issues were identified, and solutions were proposed through qualitative analysis and a 4-month iterative consensus process. Results: Our work culminated in several key recommendations: (1) building safe and trustworthy systems; (2) developing validation, verification, and certification processes for AI-CDS systems; (3) providing a means of safety monitoring and reporting at the national level; and (4) ensuring that appropriate documentation and end-user training are provided. Discussion: AI-enabled Clinical Decision Support (AI-CDS) systems promise to revolutionize healthcare decision-making, necessitating a comprehensive framework for their development, implementation, and regulation that emphasizes trustworthiness, transparency, and safety. This framework encompasses various aspects including model training, explainability, validation, certification, monitoring, and continuous evaluation, while also addressing challenges such as data privacy, fairness, and the need for regulatory oversight to ensure responsible integration of AI into clinical workflow. Conclusions: Achieving responsible AI-CDS systems requires a collective effort from many healthcare stakeholders. This involves implementing robust safety, monitoring, and transparency measures while fostering innovation. Future steps include testing and piloting proposed trust mechanisms, such as safety reporting protocols, and establishing best practice guidelines.

24 April 2023 in JMIR Cardio
Verified
Journal Article
Open access
MCMargarita Calvo-López
Margarita Calvo-López
RTRaquel Arranz Tolós
Raquel Arranz Tolós
JEJosefa Marin Expósito
Josefa Marin Expósito
DGDomenico Gruosso
Domenico Gruosso
RARut Andrea
Rut Andrea
MGMaría Sanz‐De La Garza
María Sanz‐De La Garza
Background: Center-based cardiac rehabilitation programs (CRPs) reduce morbidity and mortality after an ischemic cardiac event; however, they are widely underused. Home-based CRP has emerged as an alternative to improve patient adherence; however, its safety and efficacy remain unclear, especially for older patients and female patients. Objective: This study aimed to develop a holistic home-based CRP for patients with ischemic heart disease and evaluate its safety and impact on functional capacity, adherence to a healthy lifestyle, and quality of life. Methods: The 8-week home-based CRP included patients of both sexes, with no age limit, who had overcome an acute myocardial infarction in the previous 3 months, had a left ventricular ejection fraction of ≥40%, and had access to a tablet or mobile device. The CRP was developed using a dedicated platform designed explicitly for this purpose and included 3 weekly exercise sessions combining tailored aerobic and strength training and 2 weekly educational session focused on lifestyle habits, therapeutic adherence, and patient empowerment. Results: We initially included 62 patients, of whom 1 was excluded for presenting with ventricular arrhythmias during the initial stress test, 5 were excluded because of incompatibility, and 6 dropped out because of a technological barrier. Ultimately, 50 patients completed the program: 85% (42/50) were male, with a mean age of 58.9 (SD 10.3) years, a mean left ventricular ejection fraction of 52.1% (SD 6.72%), and 25 (50%) New York Heart Association functional class I and 25 (50%) New York Heart Association II-III. The CRP significantly improved functional capacity (+1.6 metabolic equivalent tasks), muscle strength (arm curl test +15.5% and sit-to-stand test +19.7%), weekly training volume (+803 metabolic equivalent tasks), adherence to the Mediterranean diet, emotional state (anxiety), and quality of life. No major complications occurred, and adherence was excellent (>80%) in both the exercise and educational sessions. In the subgroup analysis, CRP showed equivalent beneficial effects irrespective of sex and age. In addition, patient preferences for CRP approaches were equally distributed, with one-third (14/50, 29%) of the patients preferring a face-to-face CRP, one-third (17/50, 34%) preferring a telematic CRP, and one-third (18/50, 37%) preferring a hybrid approach. Regarding CRP duration, 63% (31/50) of the patients considered it adequate, whereas the remaining 37% (19/50) preferred a longer program. Conclusions: A holistic telematic CRP dedicated to patients after an ischemic cardiac event, irrespective of sex and age, is safe and, in our population, has achieved positive results in improving maximal aerobic capacity, weekly training volume, muscle strength, quality of life, compliance with diet, and anxiety symptoms. The preference for a center- or home-based CRP approach is diverse among the study population, emphasizing the need for a tailored CRP to improve adherence and completion rates.

31 May 2023 in JMIR Formative Research
Verified
Journal Article
Open access
MPManuel Ramón Castillo Padrós
Manuel Ramón Castillo Padrós
NPNuria Pastor
Nuria Pastor
JPJúlia Altarriba Paracolls
Júlia Altarriba Paracolls
MPMarcelino Mosquera Peña
Marcelino Mosquera Peña
DPDenise Pergolizzi
Denise Pergolizzi
ÀVÀngels Salvador Vergès
Àngels Salvador Vergès
Background: Due to the complexities of advanced illnesses and their treatments, it can be difficult for patients in palliative care to maintain their quality of life. Telemedicine interventions in chronic disease management engage patients in their care, provide continuous follow-up by their health care providers, identify symptoms earlier, and allow a quick response to illness-related decline. Objective: We aimed to detail and reflect on the design of an app and evaluate its feasibility to monitor the clinical situation of patients with advanced illnesses. Methods: This study used a mixed methods design using qualitative methods to inform app development and design and quantitative methods for data collection and analysis of patient evaluations. Palliative care units in 2 Spanish university hospitals (Nuestra Señora de la Candelaria in Santa Cruz de Tenerife and University Hospital Complex of Ferrol in A Coruña) carried out a literature review, designed the study protocol, and obtained approval from the Ethics Committee from June to December 2020. In addition, focus group meetings were held, and the design and technical development of the app were elaborated on and subsequently presented in the participating palliative care units. From January to March 2021, the app was made public on the App Store and Play Store, and a pilot study with patients was carried out in April to September 2021. Results: Six focus group meetings were held that included doctors, nurses, app developers, technology consultants, and sponsors. In addition, the technology consultants presented their results 3 times in the participating palliative care units to obtain feedback. After the app’s final design, it was possible to publish it on the usual servers and begin its evaluation in patients (n=60, median age 72 years). Sixty percent (n=36) of the participants were women and 40% (n=24) were men. The most prevalent advanced pathology was cancer (n=46, 76%), followed by other diseases (n=7, 12%) and amyotrophic lateral sclerosis (n=5, 8%). Seventy percent (n=42) of the patients were already in follow-up prior to the start of the study, while 30% (n=18) were included at the start of their follow-up. The information in the app was collected and entered by relatives or caregivers in 60% (n=36) of the cases. The median follow-up was 52 (IQR 14-104) days. In all, 69% (n=41) had a follow-up >30 days (10 were deceased and 9 were missing data). The use of the different sections of the app ranged from 37% (n=22) for the glycemic record to 90% (n=54) for the constipation scale). Patients and caregivers were delighted with its ease of use and usefulness. Conclusions: Incorporating an intelligent remote patient monitoring system in clinical practice for patients in palliative care can improve access to health services and provide more information to professionals.

24 June 2020 in JMIR Research Protocols
Verified
Journal Article
Open access
NPNúria Pastor
Núria Pastor
EKElizabeth Khalilian
Elizabeth Khalilian
ECElsa Caballeria
Elsa Caballeria
DMDanielle Morrison
Danielle Morrison
ULUnai Sanchez Luque
Unai Sanchez Luque
Hugo Lopez-PelayoHugo Lopez-Pelayo
Hugo Lopez-Pelayo
Background: Monitoring mental health outcomes has traditionally been based on heuristic decisions, often based on scarce, subjective evidence, making the clinical decisions made by professionals, as well as the monitoring of these diseases, subject to flaws. However, the digital phenotype, which refers to the analysis of data collected by measuring human behavior with mobile sensors and smart bracelets, is a promising tool for filling this gap in current clinical practice. Objective: The objectives of this study are to develop the digital phenotyping of patients with alcohol use disorder and anxiety symptoms using data collected from a mobile device (ie, smartphone) and a wearable sensor (ie, Fitbit) and to analyze usability and patient satisfaction with the data collection service provided by the app. Methods: We propose to conduct a study among a group of 60 participants split into two subgroups—experimental and control—of 30 participants each. The experimental group will be recruited by physicians from the Hospital Clínic de Barcelona, and the control group will be recruited on a volunteer basis through fliers and social media. All participants will go through pretraining to ensure technological capability and understanding of tasks, then each participant will download the HumanITcare app and will be given a wearable sensor (ie, Fitbit). Throughout the 4-month period, participants will be monitored on a range of factors, including sleep cycle, heart rate, movement patterns, and sociability. All data from the wearable sensors and the mobile devices will be saved and sent to the HumanITcare server. Participants will be asked to complete weekly questionnaires about anxiety, depression, and alcohol use disorder symptoms. Research assistants will ensure timely responses. The data from both sensors will then be compared to the questionnaire responses to determine how accurately the devices can predict the same symptoms. Results: The recruitment phase was completed in November 2019 and all the data were collected by the end of December 2019. Data are being processed; this process is expected to be completed by October 2020. Conclusions: This study was created and conducted as a pilot study with the Hospital Clínic de Barcelona, with the purpose of exploring the feasibility of our approach. The study is focused on patients diagnosed with anxiety and alcohol use disorder, but participants were also monitored for depressive symptoms throughout the trial, although these were not part of the initial inclusion criteria. A limitation to our study was the exclusive use of Android smartphones over iOS devices; this could result in a potential selection bias, due to the accessibility and affordability of Android phones as opposed to iOS-based phones. Another limitation might be that reviews of usability and satisfaction could be confounded by factors such as age and familiarity. An additional function that we might add in future studies is the ability for patients to manage their own data. International Registered Report Identifier (IRRID): DERR1-10.2196/16964

13 November 2024
Verified
Conference Paper
Closed access
JLJoan Perramon Llussà
Joan Perramon Llussà
JPJúlia Altarriba Paracolls
Júlia Altarriba Paracolls
RARicard Sanjosé Alemany
Ricard Sanjosé Alemany
MBMarina Bataller
Marina Bataller
NHNúria Pastor Hernández
Núria Pastor Hernández
PGPolyxeni Gkontra
Polyxeni Gkontra
Heart failure (HF) poses significant global health challenges, necessitating advanced management strategies. Telemonitoring, coupled with artificial intelligence (AI), offers a promising approach to enhance HF care by remotely monitoring patients and predicting exacerbations. This paper introduces vitalera, a telemonitoring platform integrating AI to optimize patient management through personalized health data analysis and smart alarms. Key to our study is the improvement of vitalera's alarm-based system using machine learning models. An ongoing observational clinical study across hospitals in Spain and Romania provides data for training and validating the system. Initial results using traditional Machine Learning (ML) models evaluated by means of cross-validation show promising performance, achieving high recall rates crucial for timely detection of critical alarms and outperforming the current rule-based system. Challenges include optimizing model performance across varied hospital contexts and managing dataset imbalance. This study underscores AI's potential in revolutionizing HF telemonitoring, aiming for enhanced patient outcomes and quality of care.

9 November 2022 in JMIR Preprints
Verified
Preprint
Open access
MCMargarita Calvo-López
Margarita Calvo-López
RTRaquel Arranz Tolós
Raquel Arranz Tolós
JEJosefa Marin Expósito
Josefa Marin Expósito
DGDomenico Gruosso
Domenico Gruosso
RARut Andrea
Rut Andrea
MGMaría Sanz‐De La Garza
María Sanz‐De La Garza
BACKGROUND Center-based cardiac rehabilitation programs (CRPs) reduce morbidity and mortality after an ischemic cardiac event; however, they are widely underused. Home-based CRP has emerged as an alternative to improve patient adherence; however, its safety and efficacy remain unclear, especially for older patients and female patients. OBJECTIVE This study aimed to develop a holistic home-based CRP for patients with ischemic heart disease and evaluate its safety and impact on functional capacity, adherence to a healthy lifestyle, and quality of life. METHODS The 8-week home-based CRP included patients of both sexes, with no age limit, who had overcome an acute myocardial infarction in the previous 3 months, had a left ventricular ejection fraction of ≥40%, and had access to a tablet or mobile device. The CRP was developed using a dedicated platform designed explicitly for this purpose and included 3 weekly exercise sessions combining tailored aerobic and strength training and 2 weekly educational session focused on lifestyle habits, therapeutic adherence, and patient empowerment. RESULTS We initially included 62 patients, of whom 1 was excluded for presenting with ventricular arrhythmias during the initial stress test, 5 were excluded because of incompatibility, and 6 dropped out because of a technological barrier. Ultimately, 50 patients completed the program: 85% (42/50) were male, with a mean age of 58.9 (SD 10.3) years, a mean left ventricular ejection fraction of 52.1% (SD 6.72%), and 25 (50%) New York Heart Association functional class I and 25 (50%) New York Heart Association II-III. The CRP significantly improved functional capacity (+1.6 metabolic equivalent tasks), muscle strength (arm curl test +15.5% and sit-to-stand test +19.7%), weekly training volume (+803 metabolic equivalent tasks), adherence to the Mediterranean diet, emotional state (anxiety), and quality of life. No major complications occurred, and adherence was excellent (>80%) in both the exercise and educational sessions. In the subgroup analysis, CRP showed equivalent beneficial effects irrespective of sex and age. In addition, patient preferences for CRP approaches were equally distributed, with one-third (14/50, 29%) of the patients preferring a face-to-face CRP, one-third (17/50, 34%) preferring a telematic CRP, and one-third (18/50, 37%) preferring a hybrid approach. Regarding CRP duration, 63% (31/50) of the patients considered it adequate, whereas the remaining 37% (19/50) preferred a longer program. CONCLUSIONS A holistic telematic CRP dedicated to patients after an ischemic cardiac event, irrespective of sex and age, is safe and, in our population, has achieved positive results in improving maximal aerobic capacity, weekly training volume, muscle strength, quality of life, compliance with diet, and anxiety symptoms. The preference for a center- or home-based CRP approach is diverse among the study population, emphasizing the need for a tailored CRP to improve adherence and completion rates.