SASA Gauteng Chapter

– Seminar invitation

On behalf of the Gauteng Chapter of the South African Statistical Association (SASA) and the Institute of Certificated and Chartered Statisticians of South Africa (ICCSSA) board, we would like to invite you to a seminar:

Title: Natural Language Processing and Machine Learning Approaches for Parsing Pathology Reports

Speaker name: Gciniwe Dlamini

Abstract:   Unstructured medical notes, such as pathology reports and medical discharge summaries, contain a lot of information about patients. This information can be mined for potentially actionable insights to improve the care of patients and to improve health systems in general. However, information extraction from these medical texts is a challenging problem which has sparked great interest from both the natural language processing (NLP) and medical informatics communities. Because of this, statistical modelling and machine learning approaches are increasingly being used in conjunction with NLP methods in order to effectively and efficiently extract relevant content from medical texts.

In our work, the utility of machine learning in this setting is demonstrated through a case study where machine learning classifiers are built for the automatic labelling of free-text, breast cancer pathology reports according to their International Classification of Diseases for Oncology (ICD-O) topographical codes across nine classes for breast cancer.

Speaker details: Gciniwe is a research scientist within the Data-Driven Healthcare thematic group at IBM Research-Africa in Johannesburg, South Africa. She is currently working on developing robust machine learning and statistical models to analyse real healthcare data and to derive insights from it. In one of her projects, she is using natural language processing (NLP) tools for the predictive analysis of cancer pathology reports in free-text format. Before joining IBM, Gciniwe was a full-time, SASA-sponsored MSc student at the University of Cape Town where she was majoring in Statistical Sciences (with a focus on analytics). For the research component of her master’s degree, she worked on acoustic modelling where she utilised digital signal processing techniques as well as deep machine learning algorithms.


Free (need to register)


6 September 2018 at 10:00


41 De Korte St, Johannesburg . 20 parking bays available at the basement parking at South Point towers that IBM employees use. South Point towers is located just one street away from the IBM Research premises at 41 De Korte St. De Korte Street is parallel to Juta Street where IBM Research is located. Please see the map on the right.

Although 41 De Korte is the official address for the building (and hence the basement parking), the entrance to the basement is actually at Station street, which is ‘perpendicular’ to both Juta and De Korte streets.




ICCSSA Event Programme:

Programme director Ms Yoko Chhana (CEO of ICCSSA)

Registration - 08:00 - 09:00
Part 1: Setting the scene - from 09:00 - 10:45

Welcome – 09:00 – 09:15
Dr Pravesh Debba (Chairperson of ICCSSA) and Mr Desan Naidoo (Vice President of Africa Region for SAS)

A brief presentation on ICCSSA (history) – 09:15 – 09:30
Dr Pravesh Debba

Presentation on CPD and Accreditation of Courses – 09:30 – 10:00
Mr Philip Steyn

High profile guest speaker – 10:00 -10:45

Tea break - 10:45 - 11:00
Part 2: High profile technical speakers - 11:00 - 13:15

Professional Training and Research Programmes in Data Science – 11:00 – 11:45
High profile technical speaker 1: Prof Riaan de Jongh (Director of the Centre for Business Mathematics and Informatics® at North-West University)

The role of analytics, big data and machine learning as a driver for digital and artificial intelligence transformation – 11:45 – 12:30
High profile technical speaker 2: Dr Mark Nasila (Head of Advanced Analytics at First National Bank)

Need for Statisticians, Actuaries and Data Scientists – 12:30 – 13:15
High profile technical speaker 3: Mr Piet Maree (Head of Analytics at Discovery Health)

Lunch break - 13:15 - 14:00
Part 3: ICCSSA General Assembly (GA) and closing - 14:00 - 15:30

ICCSSA GA (compulsory for Chartered and Certificated Statisticians) – 14:00 – 15:20
Dr Pravesh Debba (Chairperson of ICCSSA)

Vote of thanks – 15:20 – 15:30
Ms Yoko Chhana (CEO of ICCSSA)

Tea break - 15:30 - 15:45