Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
A comparison between existing mortality risk algorithms and machine learning techniques
Thesis (MCom)--Stellenbosch University, 2022.
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | en_ZA |
| Published: |
Stellenbosch : Stellenbosch University
2023
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1867613789404266496 |
|---|---|
| access_status_str | Open Access |
| author | Scholtz, Jenny |
| author2 | Burger, Rulof |
| author_browse | Burger, Rulof Scholtz, Jenny |
| author_facet | Burger, Rulof Scholtz, Jenny |
| author_sort | Scholtz, Jenny |
| collection | Thesis |
| dc_rights_str_mv | Stellenbosch University |
| description | Thesis (MCom)--Stellenbosch University, 2022. |
| format | Thesis |
| id | oai:scholar.sun.ac.za:10019.1/126394 |
| institution | Stellenbosch University (South Africa) |
| language | en_ZA |
| last_indexed | 2026-06-10T12:41:43.824Z |
| license_str | Other — see source repository |
| provenance_str_mv | Harvested via OAI-PMH from SUNScholar — Stellenbosch University Repository |
| publishDate | 2023 |
| publishDateRange | 2023 |
| publishDateSort | 2023 |
| publisher | Stellenbosch : Stellenbosch University |
| publisherStr | Stellenbosch : Stellenbosch University |
| record_format | dspace |
| source_str | SUNScholar — Stellenbosch University Repository |
| spelling | oai:scholar.sun.ac.za:10019.1/126394 A comparison between existing mortality risk algorithms and machine learning techniques Scholtz, Jenny Burger, Rulof Retief, Riani Stellenbosch University. Faculty of Economic and Management Sciences. Dept. of Economics. COVID-19 (Disease) -- Mortality -- South Africa -- Hospitals Machine Learning -- South Africa -- Hospitals Data mining -- South Africa -- Hospitals COVID-19 (Disease) -- Mathematical models -- South Africa UCTD Thesis (MCom)--Stellenbosch University, 2022. ENGLISH SUMMARY: This thesis assesses the feasibility and benefits of using the patient data of a large private South African hospital group to estimate a model of mortality risk using flexible machine learning techniques. Specifically, I investigate whether such a model would have been able to outperform a commonly used medical scoring system, SAPS 3, in predicting mortality during the second half of the Covid-19 pandemic. A LightGBM machine learning model is shown to be much more accurate in predicting mortality (76.15% accuracy, compared to 56.58% for SAPS 3) for the Covid-19 positive sample. Roughly half of this gain in predictive accuracy is obtained from using the most recent and relevant data to train the model, while the remaining lift is attributable to allowing the model to find patient symptoms and attributes that are measured but ignored by SAPS 3. Interestingly, the flexible functional form of the machine learning models, which allow the predictors to affect mortality through non-linearities and interactions, has a negligible effect on predictive accuracy. The same method is also found to produce more accurate forecasts for patients who tested negative for Covid-19, but this improvement is smaller than for Covid-19 positive sample. The results of this thesis illustrate that machine learning methods are valuable tools to predict patient outcomes, particularly when there are unexpected shifts in the relationship between patient features and patient outcomes. Large hospital groups can obtain more accurate forecasts from a dynamic scoring system which is frequently frequently retrained on their own patient data. AFRIKAANSE OPSOMMING: Geen opsomming beskikbaar. Masters 2023-01-26T06:59:43Z 2023-01-26T06:59:43Z 2022-12 Thesis http://hdl.handle.net/10019.1/126394 en_ZA Stellenbosch University 33 pages : illustrations, includes annexures application/pdf Stellenbosch : Stellenbosch University |
| spellingShingle | COVID-19 (Disease) -- Mortality -- South Africa -- Hospitals Machine Learning -- South Africa -- Hospitals Data mining -- South Africa -- Hospitals COVID-19 (Disease) -- Mathematical models -- South Africa UCTD Scholtz, Jenny A comparison between existing mortality risk algorithms and machine learning techniques |
| title | A comparison between existing mortality risk algorithms and machine learning techniques |
| title_full | A comparison between existing mortality risk algorithms and machine learning techniques |
| title_fullStr | A comparison between existing mortality risk algorithms and machine learning techniques |
| title_full_unstemmed | A comparison between existing mortality risk algorithms and machine learning techniques |
| title_short | A comparison between existing mortality risk algorithms and machine learning techniques |
| title_sort | comparison between existing mortality risk algorithms and machine learning techniques |
| topic | COVID-19 (Disease) -- Mortality -- South Africa -- Hospitals Machine Learning -- South Africa -- Hospitals Data mining -- South Africa -- Hospitals COVID-19 (Disease) -- Mathematical models -- South Africa UCTD |
| url | http://hdl.handle.net/10019.1/126394 |
| work_keys_str_mv | AT scholtzjenny acomparisonbetweenexistingmortalityriskalgorithmsandmachinelearningtechniques AT scholtzjenny comparisonbetweenexistingmortalityriskalgorithmsandmachinelearningtechniques |