Chemical, biological, radiological, and nuclear (CBRN) incidents pose increasing transborder risks globally, necessitating enhanced health sector preparedness.

This study aimed to develop a comprehensive CBRN preparedness assessment tool (PAT), operational response guidelines (ORG), and tabletop simulation scenarios for the health sectors of the Middle East and North Africa (MENA) region.

A mixed-methods approach comprised a systematic review of the literature up to 2022 in English and French, modified expert interviews (MIM), and an online Delphi questionnaire. Content analysis was performed on interview data. Using R-Studio™, consensus metrics and artificial intelligence techniques, including natural language processing, sentiment analysis, and unsupervised machine learning (ML) clustering algorithms, were deployed for advanced data analysis across all phases.

The literature review identified 63 relevant studies illustrating various preparedness strategies. The MIM’s thematic analysis, reinforced by AI-driven content analysis, emphasized the need for stronger inter-regional cooperation facilitated by organizations such as WHO and standardized tabletop simulation training. A robust consensus was achieved on the proposed assessment tool and operational response guidelines. ML analysis identified distinct expert clusters, providing additional consensus perspectives.

The study emphasized the urgency for collaborative CBRN response strategies within MENA, valuing the innovative aspect of our suggested PAT, ORG, and simulation scenarios. This work advocates a dynamic, resilient approach to disaster medicine preparedness, which is crucial for regional security and global health resilience, especially in the MENA. It also highlights the significant role of AI analysis methods in enriching analytical outcomes in disaster medicine research and promoting data-informed preparedness strategies.

This study aimed to use artificial intelligence (AI) computing techniques to determine if they can validate the findings of a previously published thematic analysis article focusing on disaster medicine experts’ open-ended feedback about Middle East and North African countries (MENA) for chemical, biological, radiological, and nuclear (CBRN) threats.

Automated text analytics techniques were employed to explore and visualize the semantic essence of the experts’ feedback through word vector transformation and Principal Component Analysis (PCA) for dimensionality reduction. The t-distributed Stochastic Neighbor Embedding (t-SNE) is another more advanced dimensionality reduction technique that enhanced the capturing of the determined components.

Two prominent clusters emerged from the full textual data set representing word similarities groups in the original data set, denoting a thematic group of ideas that experts have emphasized in their responses. Upon deep reading the text feedback, the themes linked preparedness with different training types, such as tabletop exercises and policies/legislation. The findings are in line with currently adopted practices.

While AI methods demonstrated their valuable application in disaster medicine and helped validate the experts’ recommendations objectively, they should be approached cautiously, as they can be complex and challenging to comprehend fully.

Chemical, biological, radiological, and nuclear (CBRN) incidents require meticulous preparedness, particularly in the Middle East and North Africa (MENA) region. This study evaluated CBRN response operational flowcharts, tabletop training scenarios methods, and a health sector preparedness assessment tool specific to the MENA region.

An online Delphi survey engaging international disaster medicine experts was conducted. Content validity indices (CVIs) were used to validate the items. Consensus metrics, including interquartile ranges (IQRs) and Kendall’s W coefficient, were utilized to assess the panelists’ agreement levels. Advanced artificial intelligence computing methods, including sentiment analysis and machine-learning methods (t-distributed stochastic neighbor embedding [t-SNE] and k-means), were used to cluster the consensus data.

Forty experts participated in this study. The item-level CVIs for the CBRN response flowcharts, preparedness assessment tool, and tabletop scenarios were 0.96, 0.85, and 0.84, respectively, indicating strong content validity. Consensus analysis demonstrated an IQR of 0 for most items and a strong Kendall’s W coefficient, indicating a high level of agreement among the panelists. The t-SNE and k-means identified four clusters with greater European response engagement.

This study validated essential CBRN preparedness and response tools using broad expert consensus, demonstrating their applicability across different geographic areas.