Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Using machine learning to predict the risk severity of late effects o f childhood cancer survivors
Thesis (MEng)--Stellenbosch University, 2024.
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Published: |
Stellenbosch : Stellenbosch University
2025
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1867613868679757824 |
|---|---|
| access_status_str | Open Access |
| author | Nortje, Lene |
| author2 | Grobler, J. |
| author_browse | Grobler, J. Nortje, Lene |
| author_facet | Grobler, J. Nortje, Lene |
| author_sort | Nortje, Lene |
| collection | Thesis |
| dc_rights_str_mv | Stellenbosch University |
| description |
Thesis (MEng)--Stellenbosch University, 2024. |
| format | Thesis |
| id | oai:scholar.sun.ac.za:10019.1/131868 |
| institution | Stellenbosch University (South Africa) |
| last_indexed | 2026-06-10T12:42:59.065Z |
| license_str | Other — see source repository |
| provenance_str_mv | Harvested via OAI-PMH from SUNScholar — Stellenbosch University Repository |
| publishDate | 2025 |
| publishDateRange | 2025 |
| publishDateSort | 2025 |
| publisher | Stellenbosch : Stellenbosch University |
| publisherStr | Stellenbosch : Stellenbosch University |
| record_format | dspace |
| source_str | SUNScholar — Stellenbosch University Repository |
| spelling | oai:scholar.sun.ac.za:10019.1/131868 Using machine learning to predict the risk severity of late effects o f childhood cancer survivors Nortje, Lene Grobler, J. Van Zyl, Anel Kruger, M. Stellenbosch University. Faculty of Engineering. Institute of Biomedical Engineering. Cancer in children -- Prognosis Artificial intelligence -- Medical applications Survival analysis (Biometry) UCTD Thesis (MEng)--Stellenbosch University, 2024. ENGLISH ABSTRACT: With improvements in childhood cancer treatment, the number of survivors is continuously increasing. Childhood cancer survivors have a significant risk of developing late effects due to the underlying cancer or the treatment received. These late effects can affect any organ and may influence the survivors’ health related quality of life from a young age. It is important to identify the risk severity of late effects and diagnose them as soon as possible to plan appropriate long-term follow-up care, manage late effects early, and potentially improve the health-related quality of life of these survivors. In low-and-middle-income countries, there is often limited access to routine screening for healthcare problems, which makes it challenging to provide adequate long-term follow-up care for childhood cancer survivors. Due to limited access to health care, there is an opportunity for developing other techniques to predict the risk severity of these late effects. This study utilised two datasets: a South African childhood cancer survivor cohort (comprising haematological and solid cancers) and a North American childhood rhabdomyosarcoma survivor cohort. For both datasets, data analysis, and three clustering- and six classification algorithms were applied to select the best strategy for predicting the risk severity of late effects. The clustering was necessary because the target feature required for the supervised machine learning algorithms was not a single obvious feature already present in the dataset. Therefore, to comprehensively report the extent to which late effects manifested among childhood cancer survivors, the features related to the grade and number of late effects were utilised during the clustering. The indices of these newly created clusters formed the target feature for the supervised machine learning algorithms. Five performance metrics were measured to evaluate the respective classification models. For both the South African and North American cohorts, the gradient boosting model yielded the most promising results across the selected performance metrics of the classification algorithms. The gradient boosting model of the South African cohort identified anthracycline dose, radiotherapy dose, age at study visit, treatment modalities, body mass index, and age at diagnosis as the most important features for predicting the risk severity of late effects. The gradient boosting model of the North American rhabdomyosarcoma cohort identified age at follow-up, age at diagnosis, neck radiotherapy, participants’ educational status, and head radiotherapy as the most important features for these predictions. Risk stratification into low- or high-risk categories may assist with long-term follow-up care planning for childhood cancer survivors. Predicted risk severity of late effects can assist with providing more intensive follow-up to survivors with a higher risk for late effects and reducing the burden on the healthcare system for the follow-up of survivors with a lower risk of complications. Furthermore, since age at diagnosis, age at follow-up, and treatment modalities (including radiotherapy and chemotherapy) were identified in both cohorts, these risk factors can be important to incorporate in managing and planning appropriate long-term follow-up care for childhood cancer survivors to improve their health-related quality of life potentially. AFRIKAANSE OPSOMMING: Die populasie van kinderkanker oorlewendes neem voortdurend toe as gevolg van die verbetering in kinderkankerbehandeling. Kinderkanker oorlewendes het ’n hoë risiko om laat effekte te ontwikkel as gevolg van die onderliggende kanker of die behandeling wat ontvang is. Hierdie laat effekte kan enige orgaan beïnvloed en kan die oorlewendes se gesondheidsverwante lewenskwaliteit vanaf ’n jong ouderdom af beïnvloed. Dit is belangrik om die risiko erns van laat effekte te identifiseer en dit so gou moontlik te diagnoseer om sodoende toepaslike langtermyn opvolgsorg te beplan, laat effekte vroeg te behandel, en moontlik die lewenskwaliteit van hierdie oorlewendes te verbeter. In lae- en middelinkomstelande is daar dikwels beperkte toegang tot roetinesifting vir gesondheidsorgprobleme, wat dit uitdagend maak om voldoende langtermyn opvolgsorg vir oorlewendes van kinderkanker te verskaf. As gevolg van beperkte toegang tot gesondheidsorg, is daar ’n geleentheid vir die ontwikkeling van ander tegnieke om die risiko erns van hierdie laat effekte te voorspel. Hierdie studie het twee datastelle gebruik, naamlik ’n Suid-Afrikaanse kinderkanker oorlewende kohort en ’n Noord-Amerikaanse kinder rabdomiosarkoom oorlewende kohort. Vir beide datastelle is data analise, en drie groeperingen ses klassifikasie-algoritmes toegepas om die beste strategie te selekteer vir die voorspelling van die risiko erns van laat effekte. Die groepering was nodig omdat die teiken kenmerk wat benodig word vir die supervised masjienleer algoritmes nie ’n enkele ooglopende kenmerk was wat reeds in die datastel teenwoordig was nie. Daarom, om die mate waarin laat effekte onder kinderkanker oorlewendes gemanifesteer het, omvattend te rapporteer, is die kenmerke wat verband hou met die graad en aantal laat effekte tydens die groepering gebruik. Hierdie nuutgeskepte groepe het die teiken kenmerk vir die supervised masjienleeralgoritmes gevorm. Vyf prestasiemaatstawwe is gemeet om die onderskeie klassifikasie modelle te evalueer. Vir beide die Suid-Afrikaanse en Noord-Amerikaanse kohorte het die gradiëntversterkende model die mees belowende resultate oor die geselekteerde prestasiemaatstawwe van die klassifikasie-algoritmes opgelewer. Die gradiëntversterkende model van die Suid-Afrikaanse kohort het antrasikliendosis, radioterapie dosis, ouderdom tydens studiebesoek, behandelingsmodaliteite, liggaamsmassa indeks en ouderdom by diagnose as die belangrikste faktore vir voorspellings geïdentifiseer. Die gradiëntversterkende model van die Noord-Amerikaanse rabdomiosarkoom kohort het ouderdom tydens opvolg, ouderdom by diagnose, bestraling in die nek area, opvoedkundige status en bestraling in die kop area, as die belangrikste faktore vir voorspellings geïdentifiseer. Risiko-stratifikasie in lae- of hoërisikokategorieë kan help met langtermynopvolgsorgbeplanning vir oorlewendes van kinderkanker. Voorspelde risiko erns van laat effekte kan help met die verskaffing van meer intensiewe opvolgsorg aan oorlewendes met ’n hoër risiko vir laat effekte en om die las op die gesondheidsorgstelsel vir die opvolg van oorlewendes met ’n laer risiko van komplikasies te verminder. Verder, aangesien ouderdom by diagnose, ouderdom by opvolgbesoek, en behandelingsmodaliteite (insluitend radioterapie en chemoterapie) in beide kohorte geïdentifiseer is, kan hierdie risikofaktore belangrike faktore wees om in te sluit in die hantering en beplanning van langtermyn opvolgsorg vir kinderkanker oorlewendes. Hierdie bevindinge kan help met die voorsiening van toepaslike langtermyn opvolgsorg vir kinderkanker oorlewendes om moontlik hulle gesondheidsverwante lewenskwaliteit te verbeter. Masters 2025-04-04T07:41:19Z 2025-04-04T07:41:19Z 2025-03 Thesis https://scholar.sun.ac.za/handle/10019.1/131868 Stellenbosch University xxiii, 159 pages : illustrations application/pdf Stellenbosch : Stellenbosch University |
| spellingShingle | Cancer in children -- Prognosis Artificial intelligence -- Medical applications Survival analysis (Biometry) UCTD Nortje, Lene Using machine learning to predict the risk severity of late effects o f childhood cancer survivors |
| title | Using machine learning to predict the risk severity of late effects o f childhood cancer survivors |
| title_full | Using machine learning to predict the risk severity of late effects o f childhood cancer survivors |
| title_fullStr | Using machine learning to predict the risk severity of late effects o f childhood cancer survivors |
| title_full_unstemmed | Using machine learning to predict the risk severity of late effects o f childhood cancer survivors |
| title_short | Using machine learning to predict the risk severity of late effects o f childhood cancer survivors |
| title_sort | using machine learning to predict the risk severity of late effects o f childhood cancer survivors |
| topic | Cancer in children -- Prognosis Artificial intelligence -- Medical applications Survival analysis (Biometry) UCTD |
| url | https://scholar.sun.ac.za/handle/10019.1/131868 |
| work_keys_str_mv | AT nortjelene usingmachinelearningtopredicttheriskseverityoflateeffectsofchildhoodcancersurvivors |