Isabelle Laffont
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
Research Subjects
Research Interests
Isabelle Laffont has a total of 265 co-authors. Here are the top co-authors by number of shared publications:
- Denis Mottet
EuroMov Digital Health in Motion, Univ Montpellier, IMT Mines Ales, 34090 Montpellier, France
24 shared publications F. Coroian
Service de Médecine Physique et de Réadaptation, Hôpital Lapeyronie, CHU Montpellier, Avenue du doyen Gaston Giraud, 34295 Montpellier cedex 5, France
12 shared publications- Jérôme Froger
CHU Nîmes, route de Carnon, 30240 Le-Grau-du-Roi, France
12 shared publications K. Bakhti
CHRU de Montpellier, département de médecine physique et de réadaptation, 34090 Montpellier, France; Movement to Health (M2H), Euromov, université de Montpellier, Montpellier, France
8 shared publications- Bertrand Coulet
Department of Orthopedic Surgery, Hospital Lapeyronie, CHU Montpellier, Montpellier, France
6 shared publications E. Galano
CHU de Nîmes, hôpital Carémeau et du Grau du Roi, département de médecine physique et de réadaptation, 30029 Nîmes, France
6 shared publications
Latest Publications
- Open Access
Assessment of Clinical Competence Using AI-Standardized Clinical Examination
BACKGROUND: As artificial intelligence (AI) enters clinical practice, concerns about deskilling and never-skilling make the independent assessment of clinical competence increasingly important. The AI-Standardized Clinical Examination (ASCE) uses AI to simulate and score standardized clinical encounters, potentially overcoming some of the logistical and standardization constraints of conventional objective structured clinical examinations (OSCEs). Whether it provides valid and reliable assessment at scale is unknown. METHODS: In this prospective multicenter cohort study, final-year medical students from six French medical schools completed a 10-station ASCE six weeks before the national OSCE session. GPT-4o simulated standardized clinical partners; transcripts were subsequently scored by GPT-4.1 against faculty-defined rubrics. The primary outcome was the correlation between ASCE and national OSCE scores. Secondary outcomes were inter-rater reliability of expert transcript scoring, alignment of ASCE scores with expert ratings, and internal consistency. RESULTS: Among 948 enrolled students, 588 had paired ASCE and national OSCE scores. ASCE scores were correlated with national OSCE performance (Spearman’s ρ, 0.57; 95% CI, 0.51 to 0.63), with less than 1% of residual variance attributable to center (intraclass correlation coefficient, 0.01). Eight experts scored 20 randomly selected ASCE transcripts; Krippendorff’s α was 0.77 overall, 0.80 for clinical skills, and 0.70 for communication and attitude skills. Adding GPT-4.1 as an evaluator reduced α by 0.02, and its scores did not differ significantly from those of individual experts. Internal consistency was 0.67 across 10 stations and was projected to approach 0.80 with 20 stations. CONCLUSIONS: Scores from an examination delivered and scored by AI were associated with performance on a national high-stakes OSCE, with minimal center-level variation, tentative agreement among expert raters, and automated scores that aligned with expert ratings. These results support AI delivery and scoring of clinical examinations, with expert review of automated scores. Description: In what is, to our knowledge, the first prospective multicenter study to evaluate a clinical examination delivered and scored by AI against an independent national OSCE, 588 final-year medical students across six French medical schools completed an AI-Standardized Clinical Examination before the independent national OSCE. Scores correlated with national OSCE performance (Spearman’s ρ, 0.57), with negligible variation between centers, supporting AI-standardized assessment at scale.
Open AccessAssessment of Clinical Competence Using AI-Standardized Clinical Examination
BACKGROUND: As artificial intelligence (AI) enters clinical practice, concerns about deskilling and never-skilling make the independent assessment of clinical competence increasingly important. The AI-Standardized Clinical Examination (ASCE) uses AI to simulate and score standardized clinical encounters, potentially overcoming some of the logistical and standardization constraints of conventional objective structured clinical examinations (OSCEs). Whether it provides valid and reliable assessment at scale is unknown. METHODS: In this prospective multicenter cohort study, final-year medical students from six French medical schools completed a 10-station ASCE six weeks before the national OSCE session. GPT-4o simulated standardized clinical partners; transcripts were subsequently scored by GPT-4.1 against faculty-defined rubrics. The primary outcome was the correlation between ASCE and national OSCE scores. Secondary outcomes were inter-rater reliability of expert transcript scoring, alignment of ASCE scores with expert ratings, and internal consistency. RESULTS: Among 948 enrolled students, 588 had paired ASCE and national OSCE scores. ASCE scores were correlated with national OSCE performance (Spearman’s ρ, 0.57; 95% CI, 0.51 to 0.63), with less than 1% of residual variance attributable to center (intraclass correlation coefficient, 0.01). Eight experts scored 20 randomly selected ASCE transcripts; Krippendorff’s α was 0.77 overall, 0.80 for clinical skills, and 0.70 for communication and attitude skills. Adding GPT-4.1 as an evaluator reduced α by 0.02, and its scores did not differ significantly from those of individual experts. Internal consistency was 0.67 across 10 stations and was projected to approach 0.80 with 20 stations. CONCLUSIONS: Scores from an examination delivered and scored by AI were associated with performance on a national high-stakes OSCE, with minimal center-level variation, tentative agreement among expert raters, and automated scores that aligned with expert ratings. These results support AI delivery and scoring of clinical examinations, with expert review of automated scores. Description: In what is, to our knowledge, the first prospective multicenter study to evaluate a clinical examination delivered and scored by AI against an independent national OSCE, 588 final-year medical students across six French medical schools completed an AI-Standardized Clinical Examination before the independent national OSCE. Scores correlated with national OSCE performance (Spearman’s ρ, 0.57), with negligible variation between centers, supporting AI-standardized assessment at scale.
- Open Access
- 9 May 2026
- Published by Springer Nature in Journal of NeuroEngineering and Rehabilitation
- Vol. 23 (1)
Validity of FuncUseRatio for ecological monitoring of functional arm use after stroke: toward precision neurorehabilitation
The use of the paretic arm in activities of daily living after stroke is critical to prevent further decline in function over time. Accelerometers offer th
- 9 May 2026
- Published by Springer Nature in Journal of NeuroEngineering and Rehabilitation
- Vol. 23 (1)
Open AccessValidity of FuncUseRatio for ecological monitoring of functional arm use after stroke: toward precision neurorehabilitation
The use of the paretic arm in activities of daily living after stroke is critical to prevent further decline in function over time. Accelerometers offer th
- Top Cited Papers
- 24 July 2025
- Published by Massachusetts Medical Society in NEJM AI
- Vol. 2 (8)
AI-Standardized Clinical Examination Training on OSCE Performance
- 24 July 2025
- Published by Massachusetts Medical Society in NEJM AI
- Vol. 2 (8)
Top Cited PapersAI-Standardized Clinical Examination Training on OSCE Performance
- Open Access
- 31 December 2024
- Published by SAGE Publications in Neurorehabilitation and Neural Repair
- Vol. 39 (6) , 423-432
Beyond Arm Capacity in Chronic Stroke: Evaluating Paretic Arm Non-Use Through Arm Efficiency—A Cross-Sectional Study
Background: After a stroke, the use of the paretic arm is determined by its capacity (what it can or cannot do). When both arms have capacity to perform a task, the choice of which arm to use must be based on another criterion, probably by comparing the efficiency of each arm. Two numerical models account for this: the capacity model (the paretic arm is chosen in preference) and the efficiency model (the most efficient arm is chosen). Objective: To numerically determine whether capacity or efficiency best predict the use of the paretic arm in activities of daily living. Methods: We performed numerical simulations to predict paretic arm use with either the capacity model or the efficiency model. We used the Bayesian Information Criterion (BIC) to compare the adequacy of the 2 models in predicting clinical and accelerometric data collected from 30 patients with chronic stroke. Results: The efficiency model predicted arm use in activities of daily living better than the capacity model (BIC = −66.95 vs −5.89; root mean square error = 0.26 vs 0.72). Conclusions: The study highlights the importance of considering efficiency when assessing paretic arm non-use. Assessing individuals’ arm efficiency should help personalize rehabilitation strategies after stroke.
- 31 December 2024
- Published by SAGE Publications in Neurorehabilitation and Neural Repair
- Vol. 39 (6) , 423-432
Open AccessBeyond Arm Capacity in Chronic Stroke: Evaluating Paretic Arm Non-Use Through Arm Efficiency—A Cross-Sectional Study
Background: After a stroke, the use of the paretic arm is determined by its capacity (what it can or cannot do). When both arms have capacity to perform a task, the choice of which arm to use must be based on another criterion, probably by comparing the efficiency of each arm. Two numerical models account for this: the capacity model (the paretic arm is chosen in preference) and the efficiency model (the most efficient arm is chosen). Objective: To numerically determine whether capacity or efficiency best predict the use of the paretic arm in activities of daily living. Methods: We performed numerical simulations to predict paretic arm use with either the capacity model or the efficiency model. We used the Bayesian Information Criterion (BIC) to compare the adequacy of the 2 models in predicting clinical and accelerometric data collected from 30 patients with chronic stroke. Results: The efficiency model predicted arm use in activities of daily living better than the capacity model (BIC = −66.95 vs −5.89; root mean square error = 0.26 vs 0.72). Conclusions: The study highlights the importance of considering efficiency when assessing paretic arm non-use. Assessing individuals’ arm efficiency should help personalize rehabilitation strategies after stroke.
- Open Access
- 1 April 2024
- Published by Edizioni Minerva Medica in European Journal of Physical and Rehabilitation Medicine
- Vol. 60 (2) , 270-279
Post-polio syndrome is not a dysimmune condition
Article: Post-polio syndrome is not a dysimmune condition - European Journal of Physical and Rehabilitation Medicine 2024 Jan 22 - Minerva Medica - Journals
- 1 April 2024
- Published by Edizioni Minerva Medica in European Journal of Physical and Rehabilitation Medicine
- Vol. 60 (2) , 270-279
Open AccessPost-polio syndrome is not a dysimmune condition
Article: Post-polio syndrome is not a dysimmune condition - European Journal of Physical and Rehabilitation Medicine 2024 Jan 22 - Minerva Medica - Journals
- Open Access
- 29 November 2023
- Published by Elsevier in JSES International
- Vol. 8 (1) , 80-84
Arthroscopic shoulder suspensioplasty in painful hemiplegic shoulder subluxation—a case series
- 29 November 2023
- Published by Elsevier in JSES International
- Vol. 8 (1) , 80-84
Open AccessArthroscopic shoulder suspensioplasty in painful hemiplegic shoulder subluxation—a case series
- Open Access
- 27 April 2023
- Published by Springer Nature in Journal of NeuroEngineering and Rehabilitation
- Vol. 20 (1) , 1-10
Comparison of wrist actimetry variables of paretic upper limb use in post stroke patients for ecological monitoring
Background: To date, many wrist actimetric variables dedicated to measuring the upper limbs (UL) in post-stroke patients have been developed but very few comparisons have been made between them. The objective of this study was to compare different actimetric variables of the ULs between a stroke and healthy population.Methods: Accelerometers were worn continuously for a period of 7 days on both wrists of 19 post-stroke hemiparetic patients as well as 11 healthy subjects. Various wrist actimetry variables were calculated, including the Jerk ratio 50 (JR50, cumulative probability that the Jerk Ratio is between 1 and 2), absolute (FuncUse30) and relative (FuncUseRatio30) amounts of functional use of movements of the ULs with angular amplitude greater than 30°, and absolute (UH) and relative (UseHoursRatio) use hours.Results: FuncUse30, FuncUseRatio30, UH, UseHoursRatio and JR50 of the paretic UL of stroke patients were significantly lower than in the non-dominant UL of healthy subjects. Comparing the ratio variables in stroke patients, FuncUseRatio30 was significantly lower than UseHoursRatio and JR50, suggesting a more clinically sensitive variable to monitor. In an exploratory analysis, FuncUseRatio tends to decrease with angular range of motion for stroke patients while it remains stable and close to 1 for healthy subjects. UseHoursRatio, FuncUseRatio30 and JR50 show linear correlation with Fugl-Meyer score (FM), with r2equal to 0.53, 0.35 and 0.21, respectively.Conclusion: This study determined that the FuncUseRatio30 variable provides the most sensitive clinical biomarker of paretic UL use in post-stroke patients, and that FuncUseHours—angular range of motion relationship allows the identification of the UL behaviour of each patient. This ecological information on the level of functional use of the paretic UL can be used to improve follow-up and develop patient-specific therapy.
- 27 April 2023
- Published by Springer Nature in Journal of NeuroEngineering and Rehabilitation
- Vol. 20 (1) , 1-10
Open AccessComparison of wrist actimetry variables of paretic upper limb use in post stroke patients for ecological monitoring
Background: To date, many wrist actimetric variables dedicated to measuring the upper limbs (UL) in post-stroke patients have been developed but very few comparisons have been made between them. The objective of this study was to compare different actimetric variables of the ULs between a stroke and healthy population.Methods: Accelerometers were worn continuously for a period of 7 days on both wrists of 19 post-stroke hemiparetic patients as well as 11 healthy subjects. Various wrist actimetry variables were calculated, including the Jerk ratio 50 (JR50, cumulative probability that the Jerk Ratio is between 1 and 2), absolute (FuncUse30) and relative (FuncUseRatio30) amounts of functional use of movements of the ULs with angular amplitude greater than 30°, and absolute (UH) and relative (UseHoursRatio) use hours.Results: FuncUse30, FuncUseRatio30, UH, UseHoursRatio and JR50 of the paretic UL of stroke patients were significantly lower than in the non-dominant UL of healthy subjects. Comparing the ratio variables in stroke patients, FuncUseRatio30 was significantly lower than UseHoursRatio and JR50, suggesting a more clinically sensitive variable to monitor. In an exploratory analysis, FuncUseRatio tends to decrease with angular range of motion for stroke patients while it remains stable and close to 1 for healthy subjects. UseHoursRatio, FuncUseRatio30 and JR50 show linear correlation with Fugl-Meyer score (FM), with r2equal to 0.53, 0.35 and 0.21, respectively.Conclusion: This study determined that the FuncUseRatio30 variable provides the most sensitive clinical biomarker of paretic UL use in post-stroke patients, and that FuncUseHours—angular range of motion relationship allows the identification of the UL behaviour of each patient. This ecological information on the level of functional use of the paretic UL can be used to improve follow-up and develop patient-specific therapy.
- Open Access
Quantification and Rehabilitation of Unilateral Spatial Neglect in Immersive Virtual Reality: A Validation Study in Healthy Subjects
Unilateral spatial neglect is a common sensorimotor disorder following the occurrence of a stroke, for which prismatic adaptation is a promising rehabilitation method. However, the use of prisms for rehabilitation often requires the use of specific equipment that may not be available in clinics. To address this limitation, we developed a new software package that allows for the quantification and rehabilitation of unilateral spatial neglect using immersive virtual reality. In this study, we compared the effects of virtual and real prisms in healthy subjects and evaluated the performance of our virtual reality tool (HTC Vive) against a validated motion capture tool. Ten healthy subjects were randomly exposed to virtual and real prisms, and measurements were taken before and after exposure. Our findings indicate that virtual prisms are at least as effective as real prisms in inducing aftereffects (4.39° ± 2.91° with the virtual prisms compared to 4.30° ± 3.49° with the real prisms), but that these effects were not sustained beyond 2 h regardless of exposure modality. The virtual measurements obtained with our software showed excellent metrological qualities (ICC = 0.95, error = 0.52° ± 1.18°), demonstrating its validity and reliability for quantifying deviation during pointing movements. Overall, our results suggest that our virtual reality software (Virtualis, Montpellier, France) could provide an easy and reliable means of quantifying and rehabilitating spatial neglect. Further validation of these results is required in individuals with unilateral spatial neglect.
Open AccessQuantification and Rehabilitation of Unilateral Spatial Neglect in Immersive Virtual Reality: A Validation Study in Healthy Subjects
Unilateral spatial neglect is a common sensorimotor disorder following the occurrence of a stroke, for which prismatic adaptation is a promising rehabilitation method. However, the use of prisms for rehabilitation often requires the use of specific equipment that may not be available in clinics. To address this limitation, we developed a new software package that allows for the quantification and rehabilitation of unilateral spatial neglect using immersive virtual reality. In this study, we compared the effects of virtual and real prisms in healthy subjects and evaluated the performance of our virtual reality tool (HTC Vive) against a validated motion capture tool. Ten healthy subjects were randomly exposed to virtual and real prisms, and measurements were taken before and after exposure. Our findings indicate that virtual prisms are at least as effective as real prisms in inducing aftereffects (4.39° ± 2.91° with the virtual prisms compared to 4.30° ± 3.49° with the real prisms), but that these effects were not sustained beyond 2 h regardless of exposure modality. The virtual measurements obtained with our software showed excellent metrological qualities (ICC = 0.95, error = 0.52° ± 1.18°), demonstrating its validity and reliability for quantifying deviation during pointing movements. Overall, our results suggest that our virtual reality software (Virtualis, Montpellier, France) could provide an easy and reliable means of quantifying and rehabilitating spatial neglect. Further validation of these results is required in individuals with unilateral spatial neglect.
- 1 May 2022
- Published by Elsevier in Annals of Physical and Rehabilitation Medicine
- Vol. 65 (3) , 101572
Weakness of shoulder rotator muscles in children with brachial plexus palsy under age 5 years: Not only in lateral rotation
- 1 May 2022
- Published by Elsevier in Annals of Physical and Rehabilitation Medicine
- Vol. 65 (3) , 101572
Weakness of shoulder rotator muscles in children with brachial plexus palsy under age 5 years: Not only in lateral rotation
- 1 April 2022
- Published by Elsevier in Diagnostic and Interventional Imaging
- Vol. 103 (4) , 217-224
Prediction of clinical response to corticosteroid or platelet-rich plasma injection in plantar fasciitis with MRI: A prospective, randomized, double-blinded study
- 1 April 2022
- Published by Elsevier in Diagnostic and Interventional Imaging
- Vol. 103 (4) , 217-224
Prediction of clinical response to corticosteroid or platelet-rich plasma injection in plantar fasciitis with MRI: A prospective, randomized, double-blinded study