What we're about

JerusML brings together experts from both industry and academy in the fields of Data Science, Machine Learning and Deep Learning. The goal is to empower the growing AI and Data Science community in Jerusalem and is open to attendees and lecturers from all over. The meetups happen on a regular basis and each meetup will include few lectures about interesting topics in the field. Topics can come from both research and real world applications.
We aim to be the place for people to meet, share ideas, and learn from the academy and industry experts about novel ideas and their applications in real life.
The series of meetups is done in collaboration with:
MadeInJLM (https://www.meetup.com/MadeinJLM/)
The meetups are sponsored by:
ORACLE for Startups
Jnext: http://www.jnext.org.il/
Start-up Nation Central: https://www.startupnationcentral.org/
The meetups are hosted by Jerusalem-based companies, hubs and accelerators.
For any questions or suggestions please contact Shuki Cohen at shokyco@gmail.com
Follow us on Facebook:

Upcoming events (1)

JerusML Meetup #43: Advancing Healthcare Research with Data Science


Data science is essential in advancing medical research by leveraging cutting-edge analytical tools to uncover insights from large medical data sets, leading to new discoveries in the diagnosis and treatment of diseases through the use of machine learning algorithms.

Hadassah, founded in 1912, is a renowned institution in Jerusalem known for its diverse healthcare services and research expertise.

In our 43rd meetup, we will explore how data science is used at Hadassah. Our discussion will cover the activities of the data research unit, the implementation of computational tools in cancer research, and an innovative way to protect patient privacy while allowing effective analysis.

We will meet in person at biohouse Hadassah, a medical startup tech-design space with majestic mountain views, in Hadassah Medical Center Ein Kerem Campus on Monday[masked] at 18:00, -4 floor of the mall building
We are pleased to offer free parking for a limited number of cars at our event. To reserve a free parking pass, please fill out the following form

On the agenda:
18:00-18:30 – Gathering, food and drinks
18:30-18:35 – Opening remarks : Shimon Yitshak - Community Leader @ JerusML
18:35-18:45 – Introduction: Data research at Hadassah Medical Center - Kinneret Misgav, director of the data research unit @ Hadassah Research Fund
18:45- 19:25 – Solving problems from cancer genetics and precision medicine within the machine learning setup - Gil Ben Cohen, MD PhD student @ Rosenberg lab, HUJI
19:25 - 20:05 – Protect privacy with the help of synthetic data - Luz Erez, CTO @ MDClone
More details:
Solving problems from cancer genetics and precision medicine within the machine learning setup – Gil Ben Cohen
In this talk, we will delve into the challenge of utilizing machine learning to solve problems in cancer genetics and precision medicine. Specifically, we will focus on TP53, a gene that is commonly mutated in human cancer. Despite the thousands of potential mutations that can occur in TP53, only a small percentage are known to cause cancer, while the effects of the majority are still not understood. We will explore how combining biological knowledge with machine learning techniques can aid in predicting the impact of TP53 mutations. Can we take advantage of biological knowledge, in this case of cancer genetics research, to better define what we want to learn, and how?
Gil is an MD-PhD student at The Hebrew University of Jerusalem. In his PhD, he studies the applications of ML and DL in cancer genetics and in precision medicine, at Dr. Shai Rosenberg's lab in Hadassah Ein Kerem. He is deeply interested in integrating the tremendous technological progress achieved in AI into daily clinical practice, and specifically for improving treatment of cancer patients.
Protect privacy with the help of synthetic data – Luz Erez
Medical privacy is an important aspect of the patient-doctor relationship and is essential to maintaining trust between patients and their healthcare providers. It is also an important aspect of personal autonomy and the right to control one's own medical information. Medical privacy is protected by various laws and regulations, such as the (HIPAA) in the United States.
In this talk, we will discuss a new method to protect patient confidentiality and allow retrospective medical studies to be conducted. This new method involves Synthetic data creation.
There are several ways to create synthetic data, which is a type of data that is artificially generated to mimic real-world data but is not actually based on real individuals or events. Some common methods for creating synthetic data include:
Sampling and perturbation: This method involves selecting a sample of real data, perturbing (or altering) certain aspects of the data, and using the perturbed data as the synthetic data.
Data generation algorithms: There are various algorithms that can be used to generate synthetic data, such as random number generators or machine learning models. These algorithms can be used to generate synthetic data that has certain statistical properties or follows certain patterns.
Data augmentation: This method involves taking a sample of real data and generating additional synthetic data based on the real data.
Engineer and scientist, Luz Erez served in a series of firms as CTO, VP development and Chief Engineer. Luz specializes in complex data initiatives, including big data projects, unique software and hardware technologies, RFID development, retail infrastructure, and more. He has served as a member on the FCC NCIT-T20 ANSI location based RFID committee and the IXRtail NRF committee as an XML expert. Luz founded ISI, which was merged into Ness Technologies, Inc. (Ness) – a global provider of information technology (IT) and listed on the Nasdaq. He has also served as a member of numerous open source projects such as IUI and Ghostscript