Background:Brain development during embryogenesis and in early postnatal life is particularlycomplex and involves the interplay of many cellular processes and molecular mechanisms, makingit extremely vulnerable to exogenous insults, including ionizing radiation (IR). Microcephaly is oneof the most frequent neurodevelopmental abnormalities that is characterized by small brain size,and is often associated with intellectual deficiency. Decades of research span from epidemiologicaldata onin uteroexposure of the A-bomb survivors, to studies on animal and cellular models thatallowed deciphering the most prominent molecular mechanisms leading to microcephaly. TheAdverse Outcome Pathway (AOP) framework is used to organize, evaluate and portray the scien-tific knowledge of toxicological effects spanning different biological levels of organizations, fromthe initial interaction with molecular targets to the occurrence of a disease or adversity. In the pre-sent study, the framework was used in an attempt to organize the current scientific knowledge onmicrocephaly progression in the context of ionizing radiation (IR) exposure. This work was per-formed by a group of experts formed during a recent workshop organized jointly by theMultidisciplinary European Low Dose Initiative (MELODI) and the European Radioecology Alliance(ALLIANCE) associations to present the AOP approach and tools. Here we report on the develop-ment of a putative AOP for congenital microcephaly resulting from IR exposure based on discus-sions of the working group and we emphasize the use of a novel machine-learning approach toassist in the screening of the available literature to develop AOPs.Conclusion:The expert consultation led to the identification of crucial biological events for theprogression of microcephaly upon exposure to IR, and highlighted current knowledge gaps. Themachine learning approach was successfully used to screen the existing knowledge and helped torapidly screen the body of evidence and in particular the epidemiological data. This systematicreview approach also ensured that the analysis was sufficiently comprehensive to identify themost relevant data and facilitate rapid and consistent AOP development. We anticipate that asmachine learning approaches become more user-friendly through easy-to-use web interface, thiswould allow AOP development to become more efficient and less time consuming