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

Title:
Machine Learning to Predict Interim Response in Pediatric Classical Hodgkin Lymphoma Using Affordable Blood Tests.
Authors:
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.
Corporate Authors:
South African Children's Cancer Study Group
Source:
JCO global oncology [JCO Glob Oncol] 2024 Oct; Vol. 10, pp. e2300435. Date of Electronic Publication: 2024 Oct 24.
Publication Type:
Journal Article
Language:
English
Journal Info:
Publisher: American Society of Clinical Oncology Country of Publication: United States NLM ID: 101760170 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 2687-8941 (Electronic) Linking ISSN: 26878941 NLM ISO Abbreviation: JCO Glob Oncol Subsets: MEDLINE
Imprint Name(s):
Original Publication: Alexandria, VA : American Society of Clinical Oncology, [2020]-
MeSH Terms:
Hodgkin Disease*/blood , Hodgkin Disease*/diagnosis , Hodgkin Disease*/drug therapy , Machine Learning*, Humans ; Child ; Male ; Female ; Adolescent ; Positron Emission Tomography Computed Tomography ; Hematologic Tests ; Child, Preschool ; Antineoplastic Combined Chemotherapy Protocols/therapeutic use ; Bleomycin/administration & dosage ; South Africa ; Doxorubicin/therapeutic use ; Doxorubicin/administration & dosage
References:
S Afr Med J. 2015 Oct 16;106(1 Pt 2):105-22. (PMID: 26792318)
Eur J Cancer. 2016 Jan;52:33-40. (PMID: 26630532)
Acta Haematol. 1982;67(1):67-70. (PMID: 6800204)
Clin Cancer Res. 2013 Feb 1;19(3):731-42. (PMID: 23224400)
Lancet. 2018 Dec 23;390(10114):2790-2802. (PMID: 29061295)
Pediatr Blood Cancer. 2016 Jun;63(6):1024-30. (PMID: 26855007)
Blood. 2009 Sep 3;114(10):2051-9. (PMID: 19584400)
Pediatr Radiol. 2013 Jan;43(1):86-92. (PMID: 23151729)
N Engl J Med. 1998 Nov 19;339(21):1506-14. (PMID: 9819449)
J Biomed Inform. 2019 Jul;95:103208. (PMID: 31078660)
J Clin Oncol. 2015 Sep 20;33(27):2975-85. (PMID: 26304892)
Med Sci Monit. 2020 Aug 27;26:e926544. (PMID: 32848125)
Lancet. 1986 Feb 8;1(8476):307-10. (PMID: 2868172)
Oncologist. 2022 Nov 3;27(11):958-970. (PMID: 36094141)
J Extracell Vesicles. 2021 Jul;10(9):e12121. (PMID: 34295456)
Leuk Lymphoma. 2009 Aug;50(8):1257-60. (PMID: 19544140)
J Clin Pathol. 1987 Mar;40(3):247-50. (PMID: 3558857)
Ann Hematol. 2020 Jan;99(1):1-5. (PMID: 31811361)
J Egypt Natl Canc Inst. 2008 Jun;20(2):99-110. (PMID: 20029465)
Leuk Res. 2017 Nov;62:91-97. (PMID: 28992524)
Medicine (Baltimore). 2017 Feb;96(5):e5973. (PMID: 28151888)
Lancet Oncol. 2022 Jun;23(6):e251-e312. (PMID: 35550267)
JCO Clin Cancer Inform. 2021 Jan;5:66-80. (PMID: 33439725)
Br J Haematol. 2015 Aug;170(3):356-66. (PMID: 25868485)
Cancer Radiother. 2012 Oct;16(7):627-32. (PMID: 23084987)
J Trop Pediatr. 1994 Jun;40(3):185-7. (PMID: 8078119)
Hell J Nucl Med. 2022 May-Aug;25(2):125-131. (PMID: 35913858)
Pediatr Blood Cancer. 2024 Jan;71(1):e30712. (PMID: 37814417)
Contributed Indexing:
Investigator: D Stones; R Cockroft; A Davidson; A Andrade; A Buchner; A Van Eyssen; B van Emmenes; B Rowe; C Stannard; C Stefan; D Reynders; D MacKinnon; E Mathews; F Omar; F Desai; G Steytler; G Naidu; J Poole; J Parkes; J Vermeulen; K Lecuona; K Thomas; K Bennett; K Reddy; K Moodley; K Pillay; M Kruger; J van Heerden; L Wainwright; L Schoonraad; L de Jager; M Bassingthwaighte; M Vaithilingum; N Moonsamy; O Wedi; P Radebe; R Uys; S Poyiadjis; T Ngcana; T Naidoo; R Thejpal; R Schwyzer; J Du Plessis; C Hendricks; P Hesseling; B Vanemmenes; J Schoeman; M Adamjee; M Chitnis; P Hartley; W Mathiassen; A Millar; C Wright; N Beringer; N Mahlachana; T Nkabi; J Flood; M Jonas; H Van Staaden; T Naicker; P Schubert; B Masoka
Substance Nomenclature:
11056-06-7 (Bleomycin)
80168379AG (Doxorubicin)
Entry Date(s):
Date Created: 20241024 Date Completed: 20241024 Latest Revision: 20241103
Update Code:
20250114
PubMed Central ID:
PMC11529834
DOI:
10.1200/GO.23.00435
PMID:
39447089
Database:
MEDLINE

Further Information

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.