Théo Ghelfenstein-Ferreira

Assistance Publique - Hôpitaux de Paris
Country flagFrance

Research Interests

ApplyKite TwinLearns as you apply

Make your next move.

Prepare your application

Review drafts before you send them.

Explore related searches

Articles (10)

Year:

2025

Year:

2025

Malaria remains a global health problem, with 247 million cases and 619,000 deaths in 2021. Diagnosis of Plasmodium species is important for administering the appropriate treatment. The gold-standard diagnosis for accurate species identification remains the thin blood smear. Nevertheless, this method is time-consuming and requires highly skilled and trained microscopists. To overcome these issues, new diagnostic tools based on deep learning are emerging. This study aimed to evaluate the performances of a real-time detection transformer (RT-DETR) object detection algorithm to discriminate Plasmodium species on thin blood smear images. The algorithm was trained and validated on a data set consisting in 24,720 images from 475 thin blood smears corresponding to 2,002,597 labels. Performances were calculated with a test data set of 4,508 images from 170 smears corresponding to 358,825 labels coming from six French university hospitals. At the patient level, the RT-DETR algorithm exhibited an overall accuracy of 79.4% (135/170) with a recall of 74% (40/54) and 81.9% (95/116) for negative and positive smears, respectively. Among Plasmodium- positive smears, the global accuracy was 82.7% (91/110) with a recall of 90% (38/42), 81.8% (18/22), and 76.1% (35/46) for P. falciparum , P. malariae, and P. ovale/vivax, respectively. The RT-DETR model achieved a World Health Organization (WHO) competence level 2 for species identification. Besides, the RT-DETR algorithm may be run in real-time on low-cost devices such as a smartphone and could be suitable for deployment in low-resource setting areas lacking microscopy experts. IMPORTANCE Malaria remains a global health problem, with 247 million cases and 619,000 deaths in 2021. Diagnosis of Plasmodium species is important for administering the appropriate treatment. The gold-standard diagnosis for accurate species identification remains the thin blood smear. Nevertheless, this method is time-consuming and requires highly skilled and trained microscopists. To overcome these issues, new diagnostic tools based on deep learning are emerging. This study aimed to evaluate the performances of a real-time detection transformer (RT-DETR) object detection algorithm to discriminate Plasmodium species on thin blood smear images. Performances were calculated with a test data set of 4,508 images from 170 smears coming from six French university hospitals. The RT-DETR model achieved a World Health Organization (WHO) competence level 2 for species identification. Besides, the RT-DETR algorithm may be run in real-time on low-cost devices and could be suitable for deployment in low-resource setting areas.

Year:

2024

Year:

2024

Year:

2024

Year:

2024

Year:

2024

Year:

2024

The fight against antibiotic resistance has become a true global public health challenge of gargantuan proportions. Amongst the myriad of approaches being explored to tackle this predicament, one strategy involves enhancing prescriber knowledge and in particular their basic knowledge of medical bacteriology. Yet, as we well know in medical microbiology teachings, traditional lectures can be arduous, attempting to cram in a vast array of information in a limited time. An alternative solution to improve student engagement and enhance learning outcomes is to utilize educational games in complementary approach. Such games are an effective means of inspiring students to learn, encouraging self-assessment, and injecting diversity into the teaching process. To this end, we have developed and evaluated an educational card game, the ‘BacteriaGame,’ aimed at our medical students in medical bacteriology. Designed for students at the basic level, it serves as activity at the end of their apprenticeship to their bacteriology education. Additionally, it can also be used as a review tool by more advanced students, with teachers able to impart additional knowledge as the game progresses. We also use it in continuous training of medical laboratory staff. In this study, we evaluated the game at various stages of medical education, collecting feedback and analysing its impact on knowledge acquisition, comparing it to traditional lectures. Feedback from the majority of students revealed that the rules were clear, the game was enjoyable, and neither too lengthy nor too challenging. The integration of ‘BacteriaGame’ into their future training piqued their interest. In terms of learning outcomes, we discovered a significant increase in knowledge acquisition among those who used the game (P < .05). ‘BacteriaGame’ is now published by the French Society of Microbiology (SFM) and distributed in all medical and pharmacy schools thanks to a funding of the French Health Ministry. An English edition of the game is also available for international use as a physical copy to be purchased from the SFM. This will allow a large-scale distribution to colleagues who would like to use this game in their teaching.

Year:

2023

Year:

2023

Collaborators (4)

Mathilde Lescat

Sorbonne Université

FRANCE
View details

Sarah Dellière

Research associate

Institut Pasteur

FRANCE
View details

Grégoire Pasquier

University of Montpellier

FRANCE
View details

Guillaume DESOUBEAUX

Professeur des universités - praticien hospitalier

Université de Tours

FRANCE
View details