Francisca Pais Leite
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Francisca Pais Leite has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
- Nuno André da Silva
Hospital da Luz Learning Health
5 shared publications - Bernardo Neves
Learning Health, Hospital da Luz, Lisbon, Portugal
2 shared publications - Daniel Simões Lopes
ITI/LARSyS, Av. Prof. Gama Pinto 2, 1649-003, Lisboa, Portugal; Instituto Superior Técnico, Universidade de Lisboa, Av. Rovisco Pais, 1049-001, Lisboa, Portugal
2 shared publications Joseph B. Mandeville
2 shared publications- Mario J. Silva
University of Lisbon
2 shared publications Anders M. Dale
1 shared publication
Latest Publications
- Open Access
Eye-to-Eye: Gaze detection as a proxy for medical doctor behaviour during virtual and in-person appointments
The gaze direction of the physician during consultations plays an important role in patient satisfaction, with several studies pointing to the positive correlation between the amount of time the physician spends looking at the patient and patient satisfaction. Additionally, the effects of the virtual consultation environment on the gaze behaviour of the doctor have yet to be studied. Therefore, this study aims to assess the impact of the virtual consultation environment by comparing the amount of total time the doctor spends looking at the patient between face-to-face and virtual consultations, as well as the average duration during the consultation and the gaze frequency. The study population consisted of 14 doctors divided between 4 medical specialties: Gynaecology/Obstetrics (4), Neurology (3), Endocrinology (3) and General and Familiar Medicine (4). A low-cost desktop that runs an appearance-based gaze estimation pipeline was implemented in the clinical setup. Each doctor recorded 20 face-to-face consultations and 20 virtual consultations, which were then processed by the pipeline to obtain the percentage of time the doctor spent looking at the patient during the consultation. Overall, we found that doctors look more at the patient in virtual consultations compared to face-to-face consultations, both in total time and average duration during the consultation. Within medical specialties, three out the four specialties involved presented clear tendencies to look more at the patient in virtual consultations when compared to face-to-face consultations.
Open AccessEye-to-Eye: Gaze detection as a proxy for medical doctor behaviour during virtual and in-person appointments
The gaze direction of the physician during consultations plays an important role in patient satisfaction, with several studies pointing to the positive correlation between the amount of time the physician spends looking at the patient and patient satisfaction. Additionally, the effects of the virtual consultation environment on the gaze behaviour of the doctor have yet to be studied. Therefore, this study aims to assess the impact of the virtual consultation environment by comparing the amount of total time the doctor spends looking at the patient between face-to-face and virtual consultations, as well as the average duration during the consultation and the gaze frequency. The study population consisted of 14 doctors divided between 4 medical specialties: Gynaecology/Obstetrics (4), Neurology (3), Endocrinology (3) and General and Familiar Medicine (4). A low-cost desktop that runs an appearance-based gaze estimation pipeline was implemented in the clinical setup. Each doctor recorded 20 face-to-face consultations and 20 virtual consultations, which were then processed by the pipeline to obtain the percentage of time the doctor spent looking at the patient during the consultation. Overall, we found that doctors look more at the patient in virtual consultations compared to face-to-face consultations, both in total time and average duration during the consultation. Within medical specialties, three out the four specialties involved presented clear tendencies to look more at the patient in virtual consultations when compared to face-to-face consultations.
- Open Access
- 23 April 2025
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 192 (Pt A) , 110181
Zero-shot learning for clinical phenotyping: Comparing LLMs and rule-based methods
- 23 April 2025
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 192 (Pt A) , 110181
Open AccessZero-shot learning for clinical phenotyping: Comparing LLMs and rule-based methods
- Open Access
- 15 April 2024
- Published by Springer Nature in BMC Medical Informatics and Decision Making
- Vol. 24 (1) , 1-14
Identifying subgroups in heart failure patients with multimorbidity by clustering and network analysis
This study presents a workflow for identifying and characterizing patients with Heart Failure (HF) and multimorbidity utilizing data from Electronic Health Records. Multimorbidity, the co-occurrence of two or more chronic conditions, poses a significant challenge on healthcare systems. Nonetheless, understanding of patients with multimorbidity, including the most common disease interactions, risk factors, and treatment responses, remains limited, particularly for complex and heterogeneous conditions like HF. We conducted a clustering analysis of 3745 HF patients using demographics, comorbidities, laboratory values, and drug prescriptions. Our analysis revealed four distinct clusters with significant differences in multimorbidity profiles showing differential prognostic implications regarding unplanned hospital admissions. These findings underscore the considerable disease heterogeneity within HF patients and emphasize the potential for improved characterization of patient subgroups for clinical risk stratification through the use of EHR data.
- 15 April 2024
- Published by Springer Nature in BMC Medical Informatics and Decision Making
- Vol. 24 (1) , 1-14
Open AccessIdentifying subgroups in heart failure patients with multimorbidity by clustering and network analysis
This study presents a workflow for identifying and characterizing patients with Heart Failure (HF) and multimorbidity utilizing data from Electronic Health Records. Multimorbidity, the co-occurrence of two or more chronic conditions, poses a significant challenge on healthcare systems. Nonetheless, understanding of patients with multimorbidity, including the most common disease interactions, risk factors, and treatment responses, remains limited, particularly for complex and heterogeneous conditions like HF. We conducted a clustering analysis of 3745 HF patients using demographics, comorbidities, laboratory values, and drug prescriptions. Our analysis revealed four distinct clusters with significant differences in multimorbidity profiles showing differential prognostic implications regarding unplanned hospital admissions. These findings underscore the considerable disease heterogeneity within HF patients and emphasize the potential for improved characterization of patient subgroups for clinical risk stratification through the use of EHR data.
- 21 December 2021
- Published by Taylor & Francis in Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization
- Vol. 10 (3) , 260-265
Augmenting the training space of an epidural needle insertion simulator with HoloLens
The goal of this study is to explore the potential of the Optical See-Through Augmented Reality (OST-AR) in the training of median and paramedian epidural anaesthesia administration. To this end, we propose EpiduralLens, an epidural needle insertion simulator that augments the training space by resorting to a dummy, a HoloLens, an AR target, 3D sound feedback, and voice commands. The proposed system projects relevant 3D anatomical information and visual guides that are placed on and around the dummy, which are complemented with aural feedback that guides the instruction process. EpiduralLens was evaluated by 6 anaesthesiologists. The results of the formal evaluation sessions indicate that our prototype had high acceptability by the experts, verifying that combining an aural interface with 3D visual interface is a useful way to aid immersion and improve the learnability of trainees. Moreover, the participants showed interest in using the application in future sessions as a training aid for median and paramedian epidural anaesthesia administration.
- 21 December 2021
- Published by Taylor & Francis in Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization
- Vol. 10 (3) , 260-265
Augmenting the training space of an epidural needle insertion simulator with HoloLens
The goal of this study is to explore the potential of the Optical See-Through Augmented Reality (OST-AR) in the training of median and paramedian epidural anaesthesia administration. To this end, we propose EpiduralLens, an epidural needle insertion simulator that augments the training space by resorting to a dummy, a HoloLens, an AR target, 3D sound feedback, and voice commands. The proposed system projects relevant 3D anatomical information and visual guides that are placed on and around the dummy, which are complemented with aural feedback that guides the instruction process. EpiduralLens was evaluated by 6 anaesthesiologists. The results of the formal evaluation sessions indicate that our prototype had high acceptability by the experts, verifying that combining an aural interface with 3D visual interface is a useful way to aid immersion and improve the learnability of trainees. Moreover, the participants showed interest in using the application in future sessions as a training aid for median and paramedian epidural anaesthesia administration.
- 1 June 2020
- Published by Elsevier in Computerized Medical Imaging and Graphics
- Vol. 82, 101731
PIÑATA: Pinpoint insertion of intravenous needles via augmented reality training assistance
- 1 June 2020
- Published by Elsevier in Computerized Medical Imaging and Graphics
- Vol. 82, 101731
PIÑATA: Pinpoint insertion of intravenous needles via augmented reality training assistance
- Open Access
- 26 September 2007
- Published by Wiley in Magnetic Resonance in Medicine
- Vol. 58 (4) , 769-776
Spin-echo MRI underestimates functional changes in microvascular cerebral blood plasma volume using exogenous contrast agent
- 26 September 2007
- Published by Wiley in Magnetic Resonance in Medicine
- Vol. 58 (4) , 769-776
Open AccessSpin-echo MRI underestimates functional changes in microvascular cerebral blood plasma volume using exogenous contrast agent
- 1 February 2006
- Published by Elsevier in NeuroImage
- Vol. 29 (3) , 901-909
Characterization of event-related designs using BOLD and IRON fMRI
- 1 February 2006
- Published by Elsevier in NeuroImage
- Vol. 29 (3) , 901-909
Characterization of event-related designs using BOLD and IRON fMRI
- 1 June 2002
- Published by Elsevier in NeuroImage
- Vol. 16 (2) , 283-294
Repeated fMRI Using Iron Oxide Contrast Agent in Awake, Behaving Macaques at 3 Tesla
- 1 June 2002
- Published by Elsevier in NeuroImage
- Vol. 16 (2) , 283-294
Repeated fMRI Using Iron Oxide Contrast Agent in Awake, Behaving Macaques at 3 Tesla