Yehya Mohamad
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yehya Mohamad has a total of 165 co-authors. Here are the top co-authors by number of shared publications:
- Carlos A. Velasco
Fraunhofer Institute for Applied Information Technology FIT
33 shared publications - Henrike Gappa
Fraunhofer Institute for Applied Information Technology (FIT), DE
9 shared publications - Naguib Heiba
Fraunhofer Institute for Applied Information Technology FIT
8 shared publications Henrike Gappa
Fraunhofer Institute for Applied Information Technology (FIT)
6 shared publicationsMichael Lawo
University of Bremen
6 shared publicationsAntoinette Fennell
NCBI Centre for Inclusive Technology
5 shared publications
Latest Publications
- 17 July 2026
- Published by Springer Nature
- p. 159-166
Intelligent, Inclusive, and Integrated Digital Healthcare: Foundations for Equitable and Trustworthy Care Innovation
- 17 July 2026
- Published by Springer Nature
- p. 159-166
Intelligent, Inclusive, and Integrated Digital Healthcare: Foundations for Equitable and Trustworthy Care Innovation
- 22 June 2025
- Published by Springer Nature
- p. 181-185
ELMTEX: Fine-Tuning LLMs for Structured Clinical Information Extraction. A Case Study on Clinical Reports
- 22 June 2025
- Published by Springer Nature
- p. 181-185
ELMTEX: Fine-Tuning LLMs for Structured Clinical Information Extraction. A Case Study on Clinical Reports
- Open Access
ELMTEX: Fine-Tuning Large Language Models for Structured Clinical Information Extraction. A Case Study on Clinical Reports
Europe's healthcare systems require enhanced interoperability and digitalization, driving a demand for innovative solutions to process legacy clinical data. This paper presents the results of our project, which aims to leverage Large Language Models (LLMs) to extract structured information from unstructured clinical reports, focusing on patient history, diagnoses, treatments, and other predefined categories. We developed a workflow with a user interface and evaluated LLMs of varying sizes through prompting strategies and fine-tuning. Our results show that fine-tuned smaller models match or surpass larger counterparts in performance, offering efficiency for resource-limited settings. A new dataset of 60,000 annotated English clinical summaries and 24,000 German translations was validated with automated and manual checks. The evaluations used ROUGE, BERTScore, and entity-level metrics. The work highlights the approach's viability and outlines future improvements.
Open AccessELMTEX: Fine-Tuning Large Language Models for Structured Clinical Information Extraction. A Case Study on Clinical Reports
Europe's healthcare systems require enhanced interoperability and digitalization, driving a demand for innovative solutions to process legacy clinical data. This paper presents the results of our project, which aims to leverage Large Language Models (LLMs) to extract structured information from unstructured clinical reports, focusing on patient history, diagnoses, treatments, and other predefined categories. We developed a workflow with a user interface and evaluated LLMs of varying sizes through prompting strategies and fine-tuning. Our results show that fine-tuned smaller models match or surpass larger counterparts in performance, offering efficiency for resource-limited settings. A new dataset of 60,000 annotated English clinical summaries and 24,000 German translations was validated with automated and manual checks. The evaluations used ROUGE, BERTScore, and entity-level metrics. The work highlights the approach's viability and outlines future improvements.
- Open Access
- 13 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 252-259
A Data Space infrastructure supporting the integration of clinical data nodes and cancer registries to improve personalized medicine
- 13 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 252-259
Open AccessA Data Space infrastructure supporting the integration of clinical data nodes and cancer registries to improve personalized medicine
- 5 July 2024
- Published by Springer Nature
- p. 295-302
Accessible, Smart and Integrated Healthcare Systems for Elderly and Persons with Disabilities
- 5 July 2024
- Published by Springer Nature
- p. 295-302
Accessible, Smart and Integrated Healthcare Systems for Elderly and Persons with Disabilities
- 2 December 2023
- Published by Springer Nature
- p. 39-54
Predicting and Understanding Care Levels of Elderly People with Machine Learning
- 2 December 2023
- Published by Springer Nature
- p. 39-54
Predicting and Understanding Care Levels of Elderly People with Machine Learning
- Open Access
- 31 August 2022
- Published by Association for Computing Machinery (ACM)
- p. 7-11
CAREPATH methodology for development of computer interpretable, integrated clinical guidelines
The process of developing a computer interpretable, integrated clinical guideline requires multiple considerations and decisions. As part of the CAREPATH project, a holistic approach to comorbidity has been adopted using an integrated clinical guideline for the management of multimorbid patients with mild cognitive impairment or mild dementia. The project’s clinical and technical teams would later interpret and implement the integrated clinical guideline into the CAREPATH holistic computer interpretable guideline. Three phases should be completed to accomplish the patient-centered computer interpretable guideline modelling, which include the conceptual modelling, interpretable modelling and localization phases, respectively. This paper describes the methodological viewpoints of this process and the relevant considerations.
- 31 August 2022
- Published by Association for Computing Machinery (ACM)
- p. 7-11
Open AccessCAREPATH methodology for development of computer interpretable, integrated clinical guidelines
The process of developing a computer interpretable, integrated clinical guideline requires multiple considerations and decisions. As part of the CAREPATH project, a holistic approach to comorbidity has been adopted using an integrated clinical guideline for the management of multimorbid patients with mild cognitive impairment or mild dementia. The project’s clinical and technical teams would later interpret and implement the integrated clinical guideline into the CAREPATH holistic computer interpretable guideline. Three phases should be completed to accomplish the patient-centered computer interpretable guideline modelling, which include the conceptual modelling, interpretable modelling and localization phases, respectively. This paper describes the methodological viewpoints of this process and the relevant considerations.
- Open Access
- 31 August 2022
- Published by Association for Computing Machinery (ACM)
- p. 31-36
A step forward in supporting home care more effectively
Due to the ongoing demographic change, informal care is even more to be considered as main pillar in caring for the increasing number of care-dependent older people. However, informal caregivers do not feel sufficiently informed about suitable support measures and meeting their care tasks can pose a high burden on them. Therefore, in the nationally funded research project INGE an app was developed to implement quality-assured and outcome-oriented effective in-home care consultancy utilizing machine learning. Yet, data on home care are missing to build machine learning features. So, synthetic data generation was used in the INGE-project as compensation and improved later on by real data collected with the INGE app during in-home care consultancy visits. Outcomes of real data collection and the design of the INGE app will be presented in this paper.
- 31 August 2022
- Published by Association for Computing Machinery (ACM)
- p. 31-36
Open AccessA step forward in supporting home care more effectively
Due to the ongoing demographic change, informal care is even more to be considered as main pillar in caring for the increasing number of care-dependent older people. However, informal caregivers do not feel sufficiently informed about suitable support measures and meeting their care tasks can pose a high burden on them. Therefore, in the nationally funded research project INGE an app was developed to implement quality-assured and outcome-oriented effective in-home care consultancy utilizing machine learning. Yet, data on home care are missing to build machine learning features. So, synthetic data generation was used in the INGE-project as compensation and improved later on by real data collected with the INGE app during in-home care consultancy visits. Outcomes of real data collection and the design of the INGE app will be presented in this paper.
- Open Access
- 31 August 2022
- Published by Association for Computing Machinery (ACM)
- p. 37-43
The design of a mobile platform providing personalized assistance to older multimorbid patients with mild dementia or mild cognitive impairment (MCI)
Management of multiple chronic conditions introduces demanding challenges for patients. This situation becomes more complex when multimorbidity is associated with dementia. In this paper, we present the design of a mobile Patient Empowerment Platform that enables older multimorbid patients with mild dementia or mild cognitive impairment (MCI) to easily follow their complex care plans and increase their adherence. We focus on the presentation of the human-centered design process that we have followed with the involvement of patients, informal caregivers, and healthcare professionals via the clinical pilot sites of the CAREPATH project. We elaborate the design challenges we have faced and present the iterative mock-ups that have been created in cooperation with end users to address these challenges and the final PEP design.
- 31 August 2022
- Published by Association for Computing Machinery (ACM)
- p. 37-43
Open AccessThe design of a mobile platform providing personalized assistance to older multimorbid patients with mild dementia or mild cognitive impairment (MCI)
Management of multiple chronic conditions introduces demanding challenges for patients. This situation becomes more complex when multimorbidity is associated with dementia. In this paper, we present the design of a mobile Patient Empowerment Platform that enables older multimorbid patients with mild dementia or mild cognitive impairment (MCI) to easily follow their complex care plans and increase their adherence. We focus on the presentation of the human-centered design process that we have followed with the involvement of patients, informal caregivers, and healthcare professionals via the clinical pilot sites of the CAREPATH project. We elaborate the design challenges we have faced and present the iterative mock-ups that have been created in cooperation with end users to address these challenges and the final PEP design.