EUVIMEDEUVIMED entdecken
Open Access

Machine Learning to Predict Interim Response in Pediatric Classical Hodgkin Lymphoma Using Affordable Blood Tests

Jennifer A Geel iD, Artsiom Hramyka iD, Jan du Plessis iD, Yasmin Goga iD, Anel Van Zyl iD, Marc G Hendricks iD, Thanushree Naidoo iD, Rema Mathew iD, Lizette Louw iD, Amy Carr iD, Beverley Neethling iD, Tanya M Schickerling iD und 10 weitere

JCO Global Oncology · 2024

DOI: 10.1200/go.23.00435 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JCO Global Oncology, 2024. Verfasst von Jennifer A Geel und 21 weiteren Autor:innen. Beteiligte Einrichtung: Department of Paediatrics and Child Health, Paediatric Haematology-Oncology, Charlotte Maxeke Johannesburg Academic Hospital, Wits Donald Gordon Medi…. Hauptthemen laut MEDLINE: Hodgkin Disease, Machine Learning. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSE Response assessment of classical Hodgkin lymphoma (cHL) with positron emission tomography-computerized tomography (PET-CT) is standard of care in well-resourced settings but unavailable in most African countries. We aimed to investigate correlations between changes in PET-CT findings at interim analysis with changes in blood test results in pediatric patients with cHL in 17 South African centers. METHODS Changes in ferritin, lactate dehydrogenase (LDH), erythrocyte sedimentation rate (ESR), albumin, total white cell count (TWC), absolute lymphocyte count (ALC), and absolute eosinophil count were compared with PET-CT Deauville scores (DS) after two cycles of doxorubicin, bleomycin, vinblastine, and dacarbazine in 84 pediatric patients with cHL. DS 1-3 denoted rapid early response (RER) while DS 4-5 denoted slow early response (SER). Missing values were imputed using the k-nearest neighbor algorithm. Baseline and follow-up blood test values were combined into a single difference variable. Data were split into training and testing sets for analysis using Python scikit-learn 1.2.2 with logistic regression, random forests, naïve Bayes, and support vector machine classifiers. RESULTS Random forest analysis achieved the best validated test accuracy of 73% when predicting RER or SER from blood samples. When applied to the full data set, the optimal model had a predictive accuracy of 80% and a receiver operating characteristic AUC of 89%. The most predictive variable was the differences in ALC, contributing 21% to the model. Differences in ferritin, LDH, and TWC contributed 15%-16%. Differences in ESR, hemoglobin, and albumin contributed 11%-12%. CONCLUSION Changes in low-cost, widely available blood tests may predict chemosensitivity for pediatric cHL without access to PET-CT, identifying patients who may not require radiotherapy. Changes in these nonspecific blood tests should be assessed in combination with clinical findings and available imaging to avoid undertreatment.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Hodgkin DiseaseMachine LearningHumansChildMaleFemaleAdolescentPositron Emission Tomography Computed TomographyHematologic TestsChild, PreschoolAntineoplastic Combined Chemotherapy ProtocolsBleomycinSouth AfricaDoxorubicin

Substanzen

BleomycinDoxorubicin

Autor:innen und Institutionen

  • Department of Paediatrics and Child Health, Paediatric Haematology-Oncology, Charlotte Maxeke Johannesburg Academic Hospital, Wits Donald Gordon Medical Centre, University of the Witwatersrand, Johannesburg, South Afric…
  • Computer Science, St Andrew's University, St Andrew's, United Kingdom.
  • Universitas Hospital, Bloemfontein, South Africa.
  • Paediatric Haematology-Oncology, University of the Free State, Bloemfontein, South Africa.
  • Paediatric Haematology-Oncology, University of KwaZulu-Natal, Durban, South Africa.
  • Greys Hospital, Pietermaritzburg, South Africa.

ORCID-Profile: Jennifer A Geel, Artsiom Hramyka, Jan du Plessis, Yasmin Goga, Anel Van Zyl, Marc G Hendricks, Thanushree Naidoo, Rema Mathew, Lizette Louw, Amy Carr, Beverley Neethling, Tanya M Schickerling, Fareed Omar, Liezl Du Plessis, Elelwani Madzhia, Vhutshilo Netshituni, Katherine Eyal, Thandeka V Z Ngcana, Tom Kelsey, Daynia E Ballott, Monika L Metzger

Zitieren

APA

Geel, J. A., Hramyka, A., du Plessis, J., Goga, Y., Van Zyl, A., Hendricks, M. G., Naidoo, T., Mathew, R., Louw, L., Carr, A., Neethling, B., Schickerling, T. M., Omar, F., Du Plessis, L., Madzhia, E., Netshituni, V., Eyal, K., Ngcana, T. V. Z., Kelsey, T., …, & South African Children's Cancer Study Group (2024). Machine Learning to Predict Interim Response in Pediatric Classical Hodgkin Lymphoma Using Affordable Blood Tests. JCO Global Oncology. https://doi.org/10.1200/go.23.00435

Vancouver

Geel JA, Hramyka A, du Plessis J, Goga Y, Van Zyl A, Hendricks MG, et al. Machine Learning to Predict Interim Response in Pediatric Classical Hodgkin Lymphoma Using Affordable Blood Tests. JCO Global Oncology. 2024. doi:10.1200/go.23.00435

BibTeX
@article{Geel2024,
  author = {Geel, Jennifer A and Hramyka, Artsiom and du Plessis, Jan and Goga, Yasmin and Van Zyl, Anel and Hendricks, Marc G and Naidoo, Thanushree and Mathew, Rema and Louw, Lizette and Carr, Amy and Neethling, Beverley and Schickerling, Tanya M and Omar, Fareed and Du Plessis, Liezl and Madzhia, Elelwani and Netshituni, Vhutshilo and Eyal, Katherine and Ngcana, Thandeka V Z and Kelsey, Tom and Ballott, Daynia E and Metzger, Monika L and South African Children's Cancer Study Group, South African Children's Cancer Study Group},
  title = {Machine Learning to Predict Interim Response in Pediatric Classical Hodgkin Lymphoma Using Affordable Blood Tests},
  journal = {JCO Global Oncology},
  year = {2024},
  doi = {10.1200/go.23.00435}
}
Kostenlos starten →