Page 126 - Book of Abstracts 2023

126
1 Dr Ofir Cohen2
Shamoon College of Engineering Beer-Sheva
2Ben Gurion University Beer Beer Sheva
Sheva
Many efforts have been made over the the last decade to to to enhance cancer treatment by utilizing novel biological tools in in in in in immunotherapy Our goal is to to to develop a a a a a a a a a a a a a a a a a a a a a a a a machine-learning system that can can can predict the the the the the efficacy of medication therapy therapy for for cancer cancer patients Preliminary data from the the the the the BGU lab (IcAR) was used including cancer cancer cell information genetic sequencing and other parameters Computational examination of of of different models revealed a a a a a a a a a a a a a a a a a a correlation in in in in in in in in several number of of of cancer cancer cells of of of 87% between IcAR functionality and and gene expression determining the the the best tool for for predicting successful and and and targeted cancer cancer therapy This approach will bridge the the the the medical-software divide and and pave the the way for for future research Keywords: cancer treatment computational analysis drug therapy therapy therapy therapy future future research research immunotherapy machine learning successful therapy therapy therapy therapy targeted therapy therapy therapy therapy Hebrew text simplification using machine-learning SE-1-5
By: Israel Avihail israel avihail@gmail com com Maor Moav maormo9876@gmail com com com Ariel Epshtein ariel32168421@gmail com com Advisors: Dr Dr Marina Litvak Dr Dr Hadas Chassidim Shamoon College of Engineering Beer-Sheva
People with weak language language skills such as young children and the linguistically challenged face difficulties reading complex text The Hebrew language's rich morphology presents unique challenges challenges when creating an an an an an Automatic Text Simplification system (ATSs) To tackle these challenges challenges we present SimplHe an an an an an an ATSs ATSs that modifies Hebrew text to to to enhance readability and and and understandability by reducing complexity factors such as structure length and and and and unfamiliar words using Machine Learning and and and Natural Language Processing Our system system achieved a a a a a a a a a a a a a a a a a a a a a a a a 39 2 SARI score on a a a a a a a a a a a a a a a a a a a a novel dataset This system system implemented as as a a a a a a a a a a a a a a a a a a a a web plugin may potentially aid people with language barriers Keywords: ATS Hebrew language language model NLP summarization text text readability text text simplification Machine-learning prediction for cancer patients' medication treatment SE-1-6
By: Tal Ohana taloh13@gmail com 122 Advisors: Dr Dr Hadas Chassidim Prof Prof Moshe Elkabats Prof Prof Angel Porgador