Open Ph.D. positions in AI and Digital Health with Knowledge Graphs

Apologies for cross-postings.

The LAMA-WeST laboratory (http://www.labowest.ca/) is in the process of
recruiting two doctoral students for a new project at the intersection of
AI and digital health: GAI-ORKG : Generative AI for Oncology Research with
Knowledge Graphs.

*DETAILED DESCRIPTION*

Over the last two decades, healthcare has moved from a paper-based reality
to a digital one and a trove of digital health data now exists.
Simultaneously, an era of AI has dawned with benefits to many areas of
society. However, the unstructured and siloed nature of a lot of health
data mean these parallel developments have barely converged and the
benefits of AI in healthcare remain, as yet, unrealized. This is
particularly true in cancer care. For many cancer patients, important
information is buried in clinical notes in disparate parts of their
electronic health record. Likewise, useful information, that could
otherwise contribute to AI-powered cancer research, lies trapped and
inaccessible to researchers. A solution to combine, consolidate, and
exploit unstructured health data is needed.

To achieve this objective, the research team will leverage modern standards
for health data to build/learn a cancer patient knowledge base (i.e. a
fully-structured record for each patient) from both structured and
unstructured data in electronic health records. We will investigate how
neural architectures, pretrained language models, and knowledge graphs can
be used to extract such a knowledge base and provide relevant information
to specialists through natural language generation approaches

Two PhDs are planned in this project:

The objective of the first PhD (D1) will be to design and implement a
methodology and model for extracting information from texts and populating
a knowledge base in oncology. This will therefore involve knowledge
representation and knowledge extraction challenges, alignment challenges,
as well as neural (including generative) NLP models.

The objective of the second PhD (D2) will be to design and implement a
methodology to generate adapted summaries from clinical notes and the
oncology knowledge base. This will therefore involve challenges in natural
language synthesis and generation and integration of knowledge graph
embeddings, as well as methods to avoid and detect model hallucination
issues.
*Requirements:*

The doctoral candidate must have a master's degree in natural language
processing / machine learning and/or Semantic Web (creation of ontologies,
knowledge bases, etc.). He or she must be passionate about research and
have knowledge of Python programming. Experience in the field of AI and
health is a plus.

Please send to amal.zouaq@polymtl.ca  a CV, a transcript, as well as a
letter motivating how your past experience can contribute to this project.
Please indicate in the subject of the message: Doctorate (D1 or D2) -
GAI-ORKG: Generative AI for Oncology Research with Knowledge Graphs.
Best regards,

-- 

-- 
Dr. Amal Zouaq, Ing., PhD

FRQS (Dual) Chair in AI and Digital Health | Titulaire de la chaire
(double) FRQS en IA et santé numérique

Associate Professor | Professeure agrégée
Polytechnique Montréal
Office / Bureau: M-3416
Phone / Tel:  (514)340-4711 ext.2228

http://www.polymtl.ca/expertises/zouaq-amal

http://www.labowest.ca/