Matúš Falis

Introduction

I am a PhD student in the Institute of Language Cognition and Computation at the University of Edinburgh supervised by Doctor Beatrice Alex and Doctor Alexandra Birch. I am a member of the CDT in Biomedical AI.

My research focuses on Large-Scale Multi-Label Document Classification in the medical domain in the task of Automatic ICD Coding of discharge summaries.

Prior to my PhD studies, I worked as a research engineer at Canon Medical Research Europe. My undergraduate degree was an integrated Master of Informatics at the University of Edinburgh. A full CV is available upon request.

Research

My research focuses on incorporating external biomedical knowledge (e.g., the International Classification of Diseases ontology) into deep learning methods. This includes adjustments in data preparation (through augmentation and synthesis based on external knowledge), evaluation, and architecture-building.

Automated Clinical Coding: What, Why, and Where We Are?
Hang Dong, Matúš Falis, William Whiteley, Beatrice Alex, Joshua Matterson, Shaoxiong Ji, Jiaoyan Chen, Honghan Wu
npj Digital Medicine
[arxiv preprint]

Horses to Zebras: Ontology-Guided Data Augmentation and Synthesis for ICD-9 Coding
Matúš Falis, Hang Dong, Alexandra Birch, Beatrice Alex
BioNLP 2022
[pdf]

CoPHE: A Count-Preserving Hierarchical Evaluation Metric in Large-Scale Multi-Label Text Classification
Matúš Falis, Hang Dong, Alexandra Birch, Beatrice Alex
EMNLP 2021
[pdf]

Paying Per-label Attention for Multi-label Extraction from Radiology Reports
Patrick Schrempf, Hannah Watson, Shadia Mikhael, Maciej Pajak, Matúš Falis, Aneta Lisowska, Keith W Muir, David Harris-Birtill, Alison Q O’Neil
Interpretable and Annotation-Efficient Learning for Medical Image Computing, 2020
[pdf]

Language Transfer for Early Warning of Epidemics from Social Media
Mattias Appelgren, Patrick Schrempf, Matúš Falis, Satoshi Ikeda, Alison Q. O'Neil
Accepted HADR+AI workshop, NeurIPS, 2019
[arxiv]

Ontological attention ensembles for capturing semantic concepts in ICD code prediction from clinical text
Matúš Falis, Maciej Pajak, Aneta Lisowska, Patrick Schrempf, Lucas Deckers, Shadia Mikhael, Sotirios Tsaftaris, Alison O’Neil
Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI), 2019
[pdf]

Software feature request detection in issue tracking systems
Thorsten Merte, Matúš Falis, Paul Hübner, Thomas Quirchmayr, Simone Bürsner, Barbara Paech
IEEE 24th International Requirements Engineering Conference, 2016
[pdf]

Sunday Tea

Sunday Tea is an iniative designed to promote honest and open in-person communication.

The COVID-19 pandemic highlighted to me the issues of physical, mental, and emotional isolation. Coming back from the lockdowns, I would like to have a timeslot dedicated to understanding people — both others and myself. The spirit of the initiative is to say whatever needs to be said — be it your challenges with your PhD/work/daily life, your deep philosophical thoughts, or the most beautiful thing that happened to you last week. I cannot promise to understand, but I will do my best to listen.

If interested in attending Sunday Tea, please sign up here.

Contact

Email: s1206296[at]ed[dot]ac[dot]uk

Office: Room 3.34, Informatics Forum, 10 Crichton Street, Edinburgh, EH8 9AB

• Linkedin
• GitHub
• Twitter

Elements

i = 0;

while (!deck.isInOrder()) {
    print 'Iteration ' + i;
    deck.shuffle();
    i++;
}

print 'It took ' + i + ' iterations to sort the deck.';