Chedva Levin

Chedva Levin


Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 August 2024 in Journal of Clinical Nursing
Verified
Journal Article
Open access
CLChedva Levin
Chedva Levin
MSMoriya Suliman
Moriya Suliman
ENEtti Naimi
Etti Naimi
MSMor Saban
Mor Saban
Background: As generative artificial intelligence (GenAI) tools continue advancing, rigorous evaluations are needed to understand their capabilities relative to experienced clinicians and nurses. The aim of this study was to objectively compare the diagnostic accuracy and response formats of ICU nurses versus various GenAI models, with a qualitative interpretation of the quantitative results.Methods: This formative study utilized four written clinical scenarios representative of real ICU patient cases to simulate diagnostic challenges. The scenarios were developed by expert nurses and underwent validation against current literature. Seventy‐four ICU nurses participated in a simulation‐based assessment involving four written clinical scenarios. Simultaneously, we asked ChatGPT‐4 and Claude‐2.0 to provide initial assessments and treatment recommendations for the same scenarios. The responses from ChatGPT‐4 and Claude‐2.0 were then scored by certified ICU nurses for accuracy, completeness and response.Results: Nurses consistently achieved higher diagnostic accuracy than AI across open‐ended scenarios, though certain models matched or exceeded human performance on standardized cases. Reaction times also diverged substantially. Qualitative response format differences emerged such as concision versus verbosity. Variations in GenAI models system performance across cases highlighted generalizability challenges.Conclusions: While GenAI demonstrated valuable skills, experienced nurses outperformed in open‐ended domains requiring holistic judgement. Continued development to strengthen generalized decision‐making abilities is warranted before autonomous clinical integration. Response format interfaces should consider leveraging distinct strengths. Rigorous mixed methods research involving diverse stakeholders can help iteratively inform safe, beneficial human‐GenAI partnerships centred on experience‐guided care augmentation.Relevance to Clinical Practice: This mixed‐methods simulation study provides formative insights into optimizing collaborative models of GenAI and nursing knowledge to support patient assessment and decision‐making in intensive care. The findings can help guide development of explainable GenAI decision support tailored for critical care environments.Patient or Public Contribution: Patients or public were not involved in the design and implementation of the study or the analysis and interpretation of the data.

25 March 2025 in Journal of Primary Care & Community Health
Verified
Journal Article
Open access
OSOdelyah Saad
Odelyah Saad
MSMor Saban
Mor Saban
EKErika Kerner
Erika Kerner
CLChedva Levin
Chedva Levin
Objective: To compare the diagnostic accuracy and clinical decision-making of experienced community nurses versus state-of-the-art generative AI (GenAI) systems for simulated patient case scenarios. Methods: In the months of 5 to 6/2024, 114 community Israeli nurses completed a questionnaire including 4 medical case studies. Responses were also collected from 3 GenAI models (ChatGPT-4, Claude 3.0, and Gemini 1.5), analyzed both without word limits and with a 10-word constraint. Responses were scored on accuracy, speed, and comprehensiveness. Results: Nurses scored higher on average compared to the shortened GenAI responses. GenAI responses were faster but more verbose, and contained unnecessary information. Gemini (full version) and Claude (full version) achieved the highest accuracy among the GenAI models. Conclusions: While GenAI shows potential to support aspects of nursing practice, human clinicians currently exhibit advantages in holistic clinical reasoning abilities, a skill requiring experience, contextual knowledge, and ability to bring concise and practical responses. Further research is needed before GenAI can adequately substitute nursing expertise.

5 November 2021 in Journal of Clinical Nursing
Verified
Journal Article
Closed access
PDF file
CLChedva Levin
Chedva Levin
DRDebbie Rand
Debbie Rand
EGEfrat Gil
Efrat Gil
MAMaayan Agmon
Maayan Agmon

1 March 2017 in Geriatric Nursing
Verified
Journal Article
Closed access
CLChedva Levin
Chedva Levin
NGNurit Gur-Yaish
Nurit Gur-Yaish
MAMaayan Agmon
Maayan Agmon
EGEfrat Gil
Efrat Gil
DRDebbie Rand
Debbie Rand
AZAnna Zisberg
Anna Zisberg

3 June 2025 in Clinical Rehabilitation
Verified
Journal Article
Open access
khawla loubanikhawla loubani
khawla loubani
YKYishai Bachar Kirshenboim
Yishai Bachar Kirshenboim
RMRuth Maman
Ruth Maman
CLChedva Levin
Chedva Levin
DRDebbie Rand
Debbie Rand
Objective: To explore how individuals with chronic-stroke experience and engage in home-based self-training, aiming to highlight factors related to their adherence and overall experience of self-training. Design: A qualitative study. Setting: Community. Subjects: Individuals with chronic-stroke. Interventions: Participants underwent a structured 5-week home-based upper-extremity self-training via videogames or the Graded Repetitive Arm Supplementary Intervention which includes activities using everyday objects. Main measures: Participants were interviewed following their participation in the self-training intervention, using a semi-structured interview. Interviews were transcribed verbatim and then analyzed using thematic analysis. Findings were validated through author discussions. Results: Twenty-two participants (63% men) were included, aged 33 to 80, 6–36 months post-stroke. Participants had preserved cognitive ability, were mostly independent in daily living, and had a moderate upper-extremity motor ability (median (interquartile range (IQR)) Fugl-Meyer Motor Assessment score: 41 (29–47)/66 points). Three main themes were identified: 1) personal factors (e.g. devotion to perform self-training, commitment to the study, and personal roles), 2) self-training factors (e.g. experience and its influence on general condition), 3) environment-related factors (e.g. training equipment, home environment, and family support). The structured intervention and family support led to motivation and commitment. Challenges included time constraints, pain, and fatigue. Conclusions: This qualitative study deepens understanding of home-based self-training experiences among individuals with chronic-stroke, highlighting how motivational, environmental, and self-training factors interact to shape long-term adherence. These insights can guide clinicians tailor interventions to promote long-term adherence and engagement by addressing individual, environmental, and task-related factors, and by identifying participants who may require additional support.

13 August 2026 in Ethics and Information Technology
Verified
Journal Article
Closed access
PDF file
CLChedva Levin
Chedva Levin
BOBrurya Orkaby
Brurya Orkaby
MSMoriya Suliman
Moriya Suliman
MSMor Saban
Mor Saban