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

Autor:	Geel JA; 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 Africa., Hramyka A; Computer Science, St Andrew's University, St Andrew's, United Kingdom., du Plessis J; Universitas Hospital, Bloemfontein, South Africa.; Paediatric Haematology-Oncology, University of the Free State, Bloemfontein, South Africa., Goga Y; Paediatric Haematology-Oncology, University of KwaZulu-Natal, Durban, South Africa.; Greys Hospital, Pietermaritzburg, South Africa., Van Zyl A; Faculty of Medicine and Health Sciences, Stellenbosch University and Tygerberg Hospital, Cape Town, South Africa., Hendricks MG; Red Cross War Memorial Children's Hospital, Cape Town, South Africa.; University of Cape Town, Cape Town, South Africa., Naidoo T; Department of Radiation Sciences, Paediatric Radiation Oncology, Charlotte Maxeke Johannesburg Academic Hospital, Wits Donald Gordon Medical Centre, University of the Witwatersrand, Johannesburg, South Africa., Mathew R; Frere Hospital, East London, South Africa.; Paediatric Haematology-Oncology, Walter Sisulu University, East London, South Africa., Louw L; Nuclear Medicine, Center of Molecular Imaging and Theranostics, Johannesburg, South Africa., Carr A; Paediatric Haematology-Oncology, University of KwaZulu-Natal, Durban, South Africa.; Greys Hospital, Pietermaritzburg, South Africa., Neethling B; Paediatric Haematology-Oncology, University of KwaZulu-Natal, Durban, South Africa.; Inkosi Albert Luthuli Central Hospital, Durban, South Africa., Schickerling TM; Netcare Alberton Hospital, Alberton, South Africa., Omar F; Paediatric Haematology-Oncology, Steve Biko Academic Hospital, University of Pretoria, Pretoria, South Africa., Du Plessis L; Paediatric Haematology-Oncology, Robert Mangaliso Sobukwe Hospital, Kimberley, South Africa., Madzhia E; Dr George Mukhari Hospital, Garankuwa, South Africa.; Paediatric Haematology-Oncology, Sefako Makgatho University, Garankuwa, South Africa., Netshituni V; Polokwane-Mankweng Hospital Complex, Polokwane, South Africa.; Paediatric Haematology-Oncology, University of Limpopo, Polokwane, South Africa., Eyal K; University of Cape Town, Cape Town, South Africa.; Southern Africa Labour and Development Research Unit, School of Economics, Cape Town, South Africa., Ngcana TVZ; Paediatric Haematology-Oncology, Chris Hani Baragwanath Academic Hospital, Wits Donald Gordon Medical Centre, University of the Witwatersrand, Johannesburg, South Africa., Kelsey T; Computer Science, St Andrew's University, St Andrew's, United Kingdom., Ballott DE; School of Clinical Medicine, University of the Witwatersrand, Johannesburg, South Africa., Metzger ML; Pediatric, Medicins Sans Frontières, Geneva, Switzerland.
Jazyk:	angličtina
Zdroj:	JCO global oncology [JCO Glob Oncol] 2024 Oct; Vol. 10, pp. e2300435. Date of Electronic Publication: 2024 Oct 24.
DOI:	10.1200/GO.23.00435
Abstrakt:	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.
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu