Thi Phuoc Yen Tran
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
Thi Phuoc Yen Tran has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Dang Khoa Nguyen
Centre de recherche du Centre hospitalier de l'Université de Montréal Montréal Québec Canada
2 shared publications - David Roberge
Centre hospitalier de l’Université de Montréal (CHUM)
2 shared publications Dènahin Hinnoutondji Toffa
Centre de Recherche du Centre Hospitalier de l'Université de Montréal (CRCHUM) Montreal Quebec Canada
2 shared publications- Elie Bou Assi
Department of Neuroscience Université de Montréal Montreal Quebec Canada
2 shared publications - Fidaa Al-Shakfa
CHUM Research Centre, Centre de Recherche du Centre Hospitalier de l’Universite de Montreal, Montréal, Canada
2 shared publications - Giuseppina Laura Masucci
Division of Radiation Oncology, Centre Hospitalier de l'Université de Montréal (CHUM), University of Montreal, Montreal, QC, Canada
2 shared publications
Latest Publications
- Open Access
- 9 July 2025
- Published by Wiley in Epilepsia Open
Detection of focal impaired awareness seizures using a biometric shirt
Objective: In recent years, seizure detection using wearable technology has gained significant attention in research. Most studies, however, have focused on detecting generalized or focal to bilateral tonic–clonic seizures. This study evaluates the feasibility of using a biometric shirt to detect focal impaired awareness seizures (FIAS) by monitoring respiratory, electrocardiography, and accelerometry signals.Methods: Patients with epilepsy were recruited at the University of Montreal Hospital Center epilepsy monitoring unit. Seizures were annotated by epileptologists based on simultaneous video‐electroencephalographic recordings, blinded to the shirt data. Features were extracted from the respiratory, accelerometry, and electrocardiography signals using varying window sizes and steps. An XGBoost classifier was trained and tested using a nested leave‐one‐subject‐out cross‐validation. Post‐processing included a firing power regularization method to reduce false alarms.Results: We recorded 113 FIAS from 27 patients who wore the shirt continuously for over 4750 hours. Using a firing power threshold of 0.65, we detected 71 seizures, resulting in a mean sensitivity of 66%, a 15% time in warning, and a false alarm rate (FAR) of 30 per 24 hours. A firing power threshold of 0.85 allowed us to reduce false alarms (8% time in warning, FAR of 21 per 24 hours) but resulted in a lower sensitivity of 57%. Performances varied across patients: sensitivity was high and FAR was low for some patients and vice versa for others, indicating variability in algorithm effectiveness across patients.Significance: Our results demonstrate that detecting FIAS with a connected shirt could be feasible for certain patients, although the rate of false alarms remains an issue. Designing a personalized algorithm and selecting patients who exhibit significant physiological changes during seizures could make wearable‐based FIAS detection more viable in the near future.Plain Language Summary: Novel mobile health technologies could transform epilepsy care by enabling continuous monitoring of seizures in everyday life. In this study, we used a biometric shirt to detect seizures with impaired awareness automatically. We used the shirt to measure breathing, heart activity, and movement in 27 patients with epilepsy in a hospital setting. Our algorithm detected up to two‐thirds of seizures correctly. However, the number of incorrect alarms remains relatively high, with variable performances between patients. While the technology showed potential, these challenges highlight the need for further improvements and personalized care plans.
- 9 July 2025
- Published by Wiley in Epilepsia Open
Open AccessDetection of focal impaired awareness seizures using a biometric shirt
Objective: In recent years, seizure detection using wearable technology has gained significant attention in research. Most studies, however, have focused on detecting generalized or focal to bilateral tonic–clonic seizures. This study evaluates the feasibility of using a biometric shirt to detect focal impaired awareness seizures (FIAS) by monitoring respiratory, electrocardiography, and accelerometry signals.Methods: Patients with epilepsy were recruited at the University of Montreal Hospital Center epilepsy monitoring unit. Seizures were annotated by epileptologists based on simultaneous video‐electroencephalographic recordings, blinded to the shirt data. Features were extracted from the respiratory, accelerometry, and electrocardiography signals using varying window sizes and steps. An XGBoost classifier was trained and tested using a nested leave‐one‐subject‐out cross‐validation. Post‐processing included a firing power regularization method to reduce false alarms.Results: We recorded 113 FIAS from 27 patients who wore the shirt continuously for over 4750 hours. Using a firing power threshold of 0.65, we detected 71 seizures, resulting in a mean sensitivity of 66%, a 15% time in warning, and a false alarm rate (FAR) of 30 per 24 hours. A firing power threshold of 0.85 allowed us to reduce false alarms (8% time in warning, FAR of 21 per 24 hours) but resulted in a lower sensitivity of 57%. Performances varied across patients: sensitivity was high and FAR was low for some patients and vice versa for others, indicating variability in algorithm effectiveness across patients.Significance: Our results demonstrate that detecting FIAS with a connected shirt could be feasible for certain patients, although the rate of false alarms remains an issue. Designing a personalized algorithm and selecting patients who exhibit significant physiological changes during seizures could make wearable‐based FIAS detection more viable in the near future.Plain Language Summary: Novel mobile health technologies could transform epilepsy care by enabling continuous monitoring of seizures in everyday life. In this study, we used a biometric shirt to detect seizures with impaired awareness automatically. We used the shirt to measure breathing, heart activity, and movement in 27 patients with epilepsy in a hospital setting. Our algorithm detected up to two‐thirds of seizures correctly. However, the number of incorrect alarms remains relatively high, with variable performances between patients. While the technology showed potential, these challenges highlight the need for further improvements and personalized care plans.
- Open Access
Detection of focal to bilateral tonic–clonic seizures using a connected shirt
Objective: This study was undertaken to develop and evaluate a machine learning‐based algorithm for the detection of focal to bilateral tonic–clonic seizures (FBTCS) using a novel multimodal connected shirt.Methods: We prospectively recruited patients with epilepsy admitted to our epilepsy monitoring unit and asked them to wear the connected shirt while under simultaneous video‐electroencephalographic monitoring. Electrocardiographic (ECG) and accelerometric (ACC) signals recorded with the connected shirt were used for the development of the seizure detection algorithm. First, we used a sliding window to extract linear and nonlinear features from both ECG and ACC signals. Then, we trained an extreme gradient boosting algorithm (XGBoost) to detect FBTCS according to seizure onset and offset annotated by three board‐certified epileptologists. Finally, we applied a postprocessing step to regularize the classification output. A patientwise nested cross‐validation was implemented to evaluate the performances in terms of sensitivity, false alarm rate (FAR), time in false warning (TiW), detection latency, and receiver operating characteristic area under the curve (ROC‐AUC).Results: We recorded 66 FBTCS from 42 patients who wore the connected shirt for a total of 8067 continuous hours. The XGBoost algorithm reached a sensitivity of 84.8% (56/66 seizures), with a median FAR of .55/24 h and a median TiW of 10 s/alarm. ROC‐AUC was .90 (95% confidence interval = .88–.91). Median detection latency from the time of progression to the bilateral tonic–clonic phase was 25.5 s.Significance: The novel connected shirt allowed accurate detection of FBTCS with a low false alarm rate in a hospital setting. Prospective studies in a residential setting with a real‐time and online seizure detection algorithm are required to validate the performance and usability of this device.
Open AccessDetection of focal to bilateral tonic–clonic seizures using a connected shirt
Objective: This study was undertaken to develop and evaluate a machine learning‐based algorithm for the detection of focal to bilateral tonic–clonic seizures (FBTCS) using a novel multimodal connected shirt.Methods: We prospectively recruited patients with epilepsy admitted to our epilepsy monitoring unit and asked them to wear the connected shirt while under simultaneous video‐electroencephalographic monitoring. Electrocardiographic (ECG) and accelerometric (ACC) signals recorded with the connected shirt were used for the development of the seizure detection algorithm. First, we used a sliding window to extract linear and nonlinear features from both ECG and ACC signals. Then, we trained an extreme gradient boosting algorithm (XGBoost) to detect FBTCS according to seizure onset and offset annotated by three board‐certified epileptologists. Finally, we applied a postprocessing step to regularize the classification output. A patientwise nested cross‐validation was implemented to evaluate the performances in terms of sensitivity, false alarm rate (FAR), time in false warning (TiW), detection latency, and receiver operating characteristic area under the curve (ROC‐AUC).Results: We recorded 66 FBTCS from 42 patients who wore the connected shirt for a total of 8067 continuous hours. The XGBoost algorithm reached a sensitivity of 84.8% (56/66 seizures), with a median FAR of .55/24 h and a median TiW of 10 s/alarm. ROC‐AUC was .90 (95% confidence interval = .88–.91). Median detection latency from the time of progression to the bilateral tonic–clonic phase was 25.5 s.Significance: The novel connected shirt allowed accurate detection of FBTCS with a low false alarm rate in a hospital setting. Prospective studies in a residential setting with a real‐time and online seizure detection algorithm are required to validate the performance and usability of this device.
- Open Access
- 31 August 2023
- Published by Asian Spine Journal (ASJ) in Asian Spine Journal
- Vol. 17 (4) , 739-749
Assessing the Performance of Prognostic Scores in Patients with Spinal Metastases from Lung Cancer Undergoing Non-surgical Treatment
Study Design: Retrospective study.Purpose: The purpose of this study was to see how well the Tomita score, revised Tokuhashi score, modified Bauer score, Van der Linden score, classic Skeletal Oncology Research Group (SORG) algorithm, SORG nomogram, and New England Spinal Metastasis Score (NESMS) predicted 3-month, 6-month, and 1-year survival of non-surgical lung cancer spinal metastases.Overview of Literature: There has been no study assessing the performance of prognostic scores for non-surgical lung cancer spinal metastases.Methods: Data analysis was carried out to identify the variables that had a significant impact on survival. For all patients with spinal metastasis from lung cancer who received non-surgical treatment, the Tomita score, revised Tokuhashi score, modified Bauer score, Van der Linden score, classic SORG algorithm, SORG nomogram, and NESMS were calculated. The performance of the scoring systems was assessed by using receiver operating characteristic (ROC) curves at 3 months, 6 months, and 12 months. The predictive accuracy of the scoring systems was quantified using the area under the ROC curve (AUC).Results: A total of 127 patients are included in the present study. The median survival of the population study was 5.3 months (95% confidence interval [CI], 3.7–9.6 months). Low hemoglobin was associated with shorter survival (hazard ratio [HR], 1.49; 95% CI, 1.00–2.23; p =0.049), while targeted therapy after spinal metastasis was associated with longer survival (HR, 0.34; 95% CI, 0.21–0.51; p <0.001). In the multivariate analysis, targeted therapy was independently associated with longer survival (HR, 0.3; 95% CI, 0.17–0.5; p <0.001). The AUC of the time-dependent ROC curves for the above prognostic scores revealed all of them performed poorly (AUC <0.7).Conclusions: The seven scoring systems investigated are ineffective at predicting survival in patients with spinal metastasis from lung cancer who are treated non-surgically.
- 31 August 2023
- Published by Asian Spine Journal (ASJ) in Asian Spine Journal
- Vol. 17 (4) , 739-749
Open AccessAssessing the Performance of Prognostic Scores in Patients with Spinal Metastases from Lung Cancer Undergoing Non-surgical Treatment
Study Design: Retrospective study.Purpose: The purpose of this study was to see how well the Tomita score, revised Tokuhashi score, modified Bauer score, Van der Linden score, classic Skeletal Oncology Research Group (SORG) algorithm, SORG nomogram, and New England Spinal Metastasis Score (NESMS) predicted 3-month, 6-month, and 1-year survival of non-surgical lung cancer spinal metastases.Overview of Literature: There has been no study assessing the performance of prognostic scores for non-surgical lung cancer spinal metastases.Methods: Data analysis was carried out to identify the variables that had a significant impact on survival. For all patients with spinal metastasis from lung cancer who received non-surgical treatment, the Tomita score, revised Tokuhashi score, modified Bauer score, Van der Linden score, classic SORG algorithm, SORG nomogram, and NESMS were calculated. The performance of the scoring systems was assessed by using receiver operating characteristic (ROC) curves at 3 months, 6 months, and 12 months. The predictive accuracy of the scoring systems was quantified using the area under the ROC curve (AUC).Results: A total of 127 patients are included in the present study. The median survival of the population study was 5.3 months (95% confidence interval [CI], 3.7–9.6 months). Low hemoglobin was associated with shorter survival (hazard ratio [HR], 1.49; 95% CI, 1.00–2.23; p =0.049), while targeted therapy after spinal metastasis was associated with longer survival (HR, 0.34; 95% CI, 0.21–0.51; p <0.001). In the multivariate analysis, targeted therapy was independently associated with longer survival (HR, 0.3; 95% CI, 0.17–0.5; p <0.001). The AUC of the time-dependent ROC curves for the above prognostic scores revealed all of them performed poorly (AUC <0.7).Conclusions: The seven scoring systems investigated are ineffective at predicting survival in patients with spinal metastasis from lung cancer who are treated non-surgically.
- 24 August 2022
- Published by Elsevier in World Neurosurgery
- Vol. 167, e726-e731
Spinal Metastasis in Multiple Primary Malignancies Involving Lung Cancer: Clinical Characteristics and Survival
- 24 August 2022
- Published by Elsevier in World Neurosurgery
- Vol. 167, e726-e731
Spinal Metastasis in Multiple Primary Malignancies Involving Lung Cancer: Clinical Characteristics and Survival
- 1 September 2014
- Published by Elsevier in Annales Françaises d'Anesthésie et de Réanimation
- Vol. 33, A75-A76
Apport de la VNI prophylactique systématique en postopératoire d’œsophagectomie : étude rétrospective observationnelle
- 1 September 2014
- Published by Elsevier in Annales Françaises d'Anesthésie et de Réanimation
- Vol. 33, A75-A76
Apport de la VNI prophylactique systématique en postopératoire d’œsophagectomie : étude rétrospective observationnelle