Latest News Archive

Please select Category, Year, and then Month to display items
Previous Archive
14 December 2022 | Story André Damons | Photo André Damons
Dr Michael Pienaar, Senior Lecturer and specialist in the UFS Department of Paediatrics and Child Health being presented to the acting Chancellor by his supervisor Prof Stephen Brown.

A lecturer from the University of the Free State (UFS) says the need to improve the care of seriously ill children is a vital part of reducing preventable deaths and diseases, and this led him to investigate the use of artificial neural networks to develop models for the prediction of patient outcomes in children with severe illness. The study was done for his PhD thesis. 

This forms the basis for the PhD thesis of Dr Michael Pienaar, Senior Lecturer and specialist in the UFS Department of Paediatrics and Child Health, called, The Development and Validation of Predictive Models for Paediatric Critical Illness in Children in Central South Africa using Artificial Neural Networks. His thesis reports the development and testing of several machine learning models designed to help healthcare workers identify seriously ill children early in a range of resource-limited settings. Combining a systematic literature search and Delphi technique with clinical data from 1 032 participants, this research led to significant progress towards implementable models for community health workers in clinical practice.

Care for critically ill children is a mission and calling 

Dr Pienaar graduated with a PhD specialising in Paediatrics on Monday (12 December) during the Faculty of Health Sciences’ December graduation ceremony. It took him three years to complete this degree. His supervisor was Prof Stephen Brown, Principal Specialist and Head of the Division of Paediatric Cardiology in the Department of Paediatrics and Child Health in the Faculty of Health Sciences at the UFS. Prof Nicolaas Luwes and Dr EC George were his co-supervisors. 

“I have been working in paediatric critical care since 2019 and see the care of critically ill children as my mission and calling in life. At the outset of the project, I was interested in approaches to complex phenomena and wanted to investigate new methods for tackling these in healthcare. 

“I have been interested in technology since childhood and in collaborating with other disciplines since I joined the university in 2019. Machine learning seemed like a great fit that could incorporate these interests and yield meaningful clinical results,” explains Dr Pienaar the reason why he chose this topic for his thesis.

He hopes that, in time, this work will lead to the implementation of integrated machine learning models to improve care and clinical outcomes for children in South Africa. From a scholarship perspective, he continues, his hope is that this work draws interest to this field in clinical research and encourages a move towards incorporating these new methods, as well as skills in areas such as coding and design in the armamentarium of a new generation of clinicians.

Medicine chooses you

According to Dr Pienaar, he always had broad interests, of which medicine is one. “I am very grateful to have found my way in medicine and am humbled and privileged to be allowed to walk with children and their families on a difficult and important journey. I believe this profession will choose you and put you where you are needed if you give it time and are prepared to listen.”

He describes graduating as a complicated ending to this period of his life and the beginning of a next chapter. He was humbled by the graduation ceremony. 

“It was wonderful to graduate with undergraduates and postgraduates in my profession – I felt great pride and solidarity joining these new colleagues and specialists in taking the oath. I am certainly relieved, proud, excited, and happy. I am also very grateful to the university, my promotors, colleagues, friends, and family for supporting me through this process. I must confess, it is also slightly bittersweet, I loved working on this and do miss it, but look forward to the next exciting project. 

“I would like to thank my Head of Department, Dr (Nomakhuwa) Tabane, my supervisors, my family and friends once again. I would also like to acknowledge and thank the National Research Foundation (NRF) as well as the University of the Free State for their assistance with funding this research.”

News Archive

Harvard couple to present lectures on Biostatistics and Mathematics at the UFS
2015-12-07


Professor Donald Rubin

Prof Donald Rubin (John L. Loeb Professor of Statistics at Harvard University) and Elizabeth Zell (MStat - mathematical statistician in the Division of Bacterial Diseases) will visit the University of the Free State (UFS) where they will present lectures on their respective work.

Over his prestigious academic career, Prof Don Rubin’s 400 publications and 13 books have earned him around 180 000 citations at an h-index of 113. He is one of the most cited statisticians/mathematicians/economists/psychologists in the world over the last 10 -15 years. He has supervised 35 PhD candidates as sole-supervisor, 17 more as co-supervisor, with a further eight in the pipeline.

Prof Rubin who will meet with UFS academics in the Department of Mathematics and Actuarial Sciences will also deliver a lecture: Rerandomisation to improve covariate balance in experiments.

Randomised experiments are the “gold standard” for estimating causal effects, yet in practice, chance imbalances often exist in covariate distributions between treatment groups. If covariate data are available before units are exposed to treatments, these chance imbalances can be mitigated by first checking covariate balance before the physical experiment takes place. Provided a precise definition of imbalance has been specified in advance, unbalanced randomisations can be discarded, followed by a rerandomisation. This process can continue until a randomisation yielding balance according to the definition is achieved. By improving covariate balance, rerandomisation provides more precise and trustworthy estimates of treatment effects.

Prof Rubin received an honorary professorship from the Faculty of Natural and Agricultural Sciences at the UFS.


Elizabeth Zell

The lecture will take place on:
Date: Tuesday 8 December 2015
Time: 16:00
Venue: Albert Wessels Auditorium, Bloemfontein Campus

Zell earned her Master’s degree in Statistics at North Carolina State University, and for more than two decades, was an active bio-statistical researcher in various offices of the Centers for Disease Control (CDC). Since 2013, she has been the Principal Statistician and President of Stat-Epi Associates, Inc. Her 150+ publications have earned her 14 500 citations at an h-index of over 50. She is a Fellow of the American Statistical Association, and, in 2010, she received the Statistics Section Government Award for outstanding contributions to statistics and public health by the American Public Health Association. During her career at the CDC, she earned more than 20 CDC research awards and honours.

She will deliver two lectures at the UFS. The first is entitled A Potential Outcomes Approach to Documenting the Public Health Impact of the Introduction of PCV13 for the Prevention of Invasive Pneumococcal Disease. The topic of her second lecture is: Assessing the Effectiveness of Intrapartum Antibiotic Prophylaxis for Prevention of Early-Onset Group B Streptococcus Disease through Propensity Score Design

Elizabeth’s lectures will take place on:
Date: Wednesday 9 December 2015
Time: 10:45 and 13:00
Venue: West Block 111, Bloemfontein Campus

For more information, please contact Dr Michael von Maltitz at VMaltitzMJ@ufs.ac.za.

We use cookies to make interactions with our websites and services easy and meaningful. To better understand how they are used, read more about the UFS cookie policy. By continuing to use this site you are giving us your consent to do this.

Accept