1
|
Li X, Yang Z, Li J, Wang G, Sun A, Wang Y, Zhang W, Liu Y, Lei H. The development of a prediction model based on random survival forest for the prognosis of non- Hodgkin lymphoma: A prospective cohort study in China. Heliyon 2024; 10:e32788. [PMID: 39022101 PMCID: PMC11252655 DOI: 10.1016/j.heliyon.2024.e32788] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/10/2023] [Revised: 06/07/2024] [Accepted: 06/10/2024] [Indexed: 07/20/2024] Open
Abstract
Background and objective The pathological staging of non-Hodgkin lymphoma (NHL) is complex, the clinical manifestations are varied, and the prognosis differ considerably. To provide a useful reference for early detection and effective treatment of NHL, we developed a random survival forest (RSF) prognostic model based on machine learning (ML) algorithms using prospective cohort data collected from Chongqing Cancer Hospital from Jan 1, 2017 to Dec 31, 2019 (n = 1449) to compare with the traditional cornerstone method Cox proportional hazards (CPH) model and evaluate the predictability of the model. Methods Patients were randomly split into a training cohort (TC) and validation cohort (VC) based on 65/35 ratio. The least absolute shrinkage and selection operator (LASSO) regression analysis was used to extracted the important features. And the RSF was modeled to explore the prognostic factors impacting the overall survival (OS) of patients with NHLs in the TC and validated in the VC. The C-index, the Integrated Brier Score (IBS), Kaplan-Meir method, the receiver operating characteristic (ROC) curve, and the area under the ROC curve (AUC) were selected to measure performances and discriminations of the models. In addition, individual survival probability predicted for NHL patients. Results According to the features extracted by LASSO model and univariable Cox model, 16 variables were selected to develop the RSF model with log-rank splitting rule, which were age, ethnicity, medical insurance, Ann Arbor stage, pathology, targeted-therapy, chemo-therapy, peripheral blood neutrophil count to lymphocyte count ratio (NLR), peripheral blood platelet count to lymphocyte count ratio (PLR), serum lactate dehydrogenase (LDH), CD4/CD8, platelet (PLT), absolute neutrophil count (ANC), lymphocyte (LYM), B-symptoms, and (CPR) were important prognostic factors. Compared to the CPH model (C-index = 0.748, IBS = 0.166), the RSF model (C-index = 0.786, IBS = 0.165) is outperformed in predictability and accuracy. The AUC of the RSF model to estimate the 1-, 3-, and 5-year OS in TC were 0.847, 0.847, and 0.809, respectively; while those in the CPH were 0.816, 0.803, and 0.750, respectively. Conclusions To provide practical implications for the implementation of individualized therapy, the study constructed a high-performed RSF model and reveal that it outperformed the traditional model CPH. And the RSF model ranked the risk variables. In addition, we stratified the risk of NHL patients and estimated individual survival probability based on the RSF model.
Collapse
Affiliation(s)
- Xiaosheng Li
- Chongqing Key Laboratory of Translational Research for Cancer Metastasis and Individualized Treatment, Chongqing University Cancer Hospital, Chongqing, 400030, China
| | - Zailin Yang
- Chongqing Key Laboratory of Translational Research for Cancer Metastasis and Individualized Treatment, Chongqing University Cancer Hospital, Chongqing, 400030, China
| | - Jieping Li
- Chongqing Key Laboratory of Translational Research for Cancer Metastasis and Individualized Treatment, Chongqing University Cancer Hospital, Chongqing, 400030, China
| | - Guixue Wang
- MOE Key Lab for Biorheological Science and Technology, State and Local Joint Engineering Laboratory for Vascular Implants, College of Bioengineering Chongqing University, Chongqing, 400030, China
| | - Anlong Sun
- Chongqing Key Laboratory of Translational Research for Cancer Metastasis and Individualized Treatment, Chongqing University Cancer Hospital, Chongqing, 400030, China
| | - Ying Wang
- Chongqing Key Laboratory of Translational Research for Cancer Metastasis and Individualized Treatment, Chongqing University Cancer Hospital, Chongqing, 400030, China
| | - Wei Zhang
- Chongqing Key Laboratory of Translational Research for Cancer Metastasis and Individualized Treatment, Chongqing University Cancer Hospital, Chongqing, 400030, China
| | - Yao Liu
- Chongqing Key Laboratory of Translational Research for Cancer Metastasis and Individualized Treatment, Chongqing University Cancer Hospital, Chongqing, 400030, China
| | - Haike Lei
- Chongqing Cancer Multi-omics Big Data Application Engineering Research Center, Chongqing University Cancer Hospital, Chongqing, 400030, China
| |
Collapse
|
2
|
Manachai N, Umnuayyonvaree D, Punyathi P, Rungsipipat A, Rattanapinyopituk K. Impact of serum C-reactive protein level as a biomarker of cancer dissemination in canine lymphoid neoplasia. Vet World 2022; 15:2810-2815. [PMID: 36718344 PMCID: PMC9880848 DOI: 10.14202/vetworld.2022.2810-2815] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/15/2022] [Accepted: 10/26/2022] [Indexed: 12/14/2022] Open
Abstract
Background and Aim C-reactive protein (CRP) is a highly sensitive but non-specific acute phase protein that has been widely used to predict the biological behavior of patients with cancer. This study aimed to examine the significance of the serum CRP biomarker in predicting the prognosis of dogs with lymphoma. Materials and Methods Blood samples (5 mL) were collected from 34 lymphoma dogs and control healthy dogs. Canine lymphoma clinical staging was classified using the World Health Organization (WHO) criteria. All lymphoma dogs were reclassified into two groups based on the disease stage. Stages IV and V were designated as advanced stages, and Stages I-III were designated as other stages. The serum CRP level was then determined using a commercial canine CRP fluorescent immunoassay kit and routine hematological and biochemical analyses. C-reactive protein levels, circulating inflammatory parameters, such as neutrophil-to-lymphocyte ratio, lymphocyte-to-monocyte ratio, and platelet-to-lymphocyte ratio, and albumin levels were compared between advanced stages (IV and V) and Stages I to III using Mann-Whitney U tests. Receiver operating characteristic (ROC) curves were also generated to determine the cutoff value, diagnostic sensitivity, and specificity of the CRP level. Results A prospective study identified 34 dogs recently diagnosed with canine lymphoma. C-reactive protein levels were significantly higher in lymphoma dogs in advanced stages (IV and V) than in lymphoma dogs in Stages I-III. According to the ROC curve analysis, a CRP cutoff level of 54.1 mg/L indicates advanced-stage canine lymphoma, which can be used as a biomarker to predict cancer dissemination. Conclusion Serum CRP concentrations can assist clinical decision-making on the WHO stage in lymphoma dogs in clinical applications. The limitations of this study include a small number of lymphomas and no survival analysis.
Collapse
Affiliation(s)
- Nawin Manachai
- Department of Pathology, Faculty of Veterinary Science, Chulalongkorn University, Pathumwan, Bangkok, Thailand,Center of Excellence - Companion Animal Cancer (CE-CAC), Chulalongkorn University, Pathumwan, Bangkok, Thailand,Department of Companion Animals and Wildlife Clinics, Faculty of Veterinary Medicine, Chiang Mai University, Chiang Mai, Thailand
| | - Duangchanok Umnuayyonvaree
- Department of Pathology, Faculty of Veterinary Science, Chulalongkorn University, Pathumwan, Bangkok, Thailand,Center of Excellence - Companion Animal Cancer (CE-CAC), Chulalongkorn University, Pathumwan, Bangkok, Thailand
| | - Panitnan Punyathi
- Department of Pathology, Faculty of Veterinary Science, Chulalongkorn University, Pathumwan, Bangkok, Thailand,Center of Excellence - Companion Animal Cancer (CE-CAC), Chulalongkorn University, Pathumwan, Bangkok, Thailand
| | - Anudep Rungsipipat
- Department of Pathology, Faculty of Veterinary Science, Chulalongkorn University, Pathumwan, Bangkok, Thailand,Center of Excellence - Companion Animal Cancer (CE-CAC), Chulalongkorn University, Pathumwan, Bangkok, Thailand
| | - Kasem Rattanapinyopituk
- Department of Pathology, Faculty of Veterinary Science, Chulalongkorn University, Pathumwan, Bangkok, Thailand,Center of Excellence - Companion Animal Cancer (CE-CAC), Chulalongkorn University, Pathumwan, Bangkok, Thailand,Corresponding author: Kasem Rattanapinyopituk, e-mail: Co-authors: NM: , DU: , PP: , AR:
| |
Collapse
|
3
|
Long Non-coding RNA H19 Recruits NFYB to Activate MBTD1 and Regulate Doxorubicin Resistance in Lymphoma Cells. Mol Biotechnol 2022; 65:997-1009. [DOI: 10.1007/s12033-022-00600-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/27/2022] [Accepted: 10/31/2022] [Indexed: 11/27/2022]
|
4
|
Triumbari EKA, Morland D, Cuccaro A, Maiolo E, Hohaus S, Annunziata S. Classical Hodgkin Lymphoma: A Joint Clinical and PET Model to Predict Poor Responders at Interim Assessment. Diagnostics (Basel) 2022; 12:diagnostics12102325. [PMID: 36292014 PMCID: PMC9600607 DOI: 10.3390/diagnostics12102325] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/20/2022] [Revised: 08/24/2022] [Accepted: 09/22/2022] [Indexed: 11/21/2022] Open
Abstract
(1) This study aimed to investigate whether baseline clinical and Positron Emission Tomography/Computed Tomography (bPET)-derived parameters could help predicting early response to the first two cycles of chemotherapy (Deauville Score at interim PET, DS at iPET) in patients with classical Hodgkin lymphoma (cHL) to identify poor responders (DS ≥ 4) who could benefit from first-line treatment intensification at an earlier time point. (2) cHL patients with a bPET and an iPET imaging study in our Centre’s records (2013−2019), no synchronous/metachronous tumors, no major surgical resection of disease prior to bPET, and treated with two cycles of ABVD chemotherapy before iPET were retrospectively included. Baseline International Prognostic Score for HL (IPS) parameters were collected. Each patient’s bPET total metabolic tumor volume (TMTV) and highest tumoral SUVmax were collected. ROC curves and Youden’s index were used to derive the optimal thresholds of TMTV and SUVmax with regard to the DS (≥4). Chi-square or Fisher’s exact test were used for the univariate analysis. A multivariate analysis was then performed using logistic regression. The type I error rate in the hypothesis testing was set to 5%. (3) A total of 146 patients were included. The optimal threshold to predict a DS ≥ 4 was >177 mL for TMTV and >14.7 for SUVmax (AUC of 0.65 and 0.58, respectively). The univariate analysis showed that only TMTV, SUVmax, advanced disease stage, and age were significantly associated with a DS ≥ 4. A multivariate model was finally derived from TMTV, SUVmax, and age, with an AUC of 0.77. (4) A multivariate model with bPET parameters and age at diagnosis was satisfactorily predictive of poor response at iPET after ABVD induction chemotherapy in cHL patients. More studies are needed to validate these results and further implement DS-predictive factors at baseline in order to prevent poor response and intensify therapeutic strategies a-priori when needed.
Collapse
Affiliation(s)
- Elizabeth Katherine Anna Triumbari
- Nuclear Medicine Unit, TracerGLab, Department of Radiology, Radiotherapy and Hematology, Fondazione Policlinico Universitario A. Gemelli IRCCS, 00168 Rome, Italy
- Correspondence: ; Tel.: +39-0630-154-777; Fax: +39-0630-137-45
| | - David Morland
- Nuclear Medicine Unit, TracerGLab, Department of Radiology, Radiotherapy and Hematology, Fondazione Policlinico Universitario A. Gemelli IRCCS, 00168 Rome, Italy
- Service de Médecine Nucléaire, Institut Godinot, 51100 Reims, France
- Laboratoire de Biophysique, UFR de Médecine, Université de Reims Champagne-Ardenne, 51100 Reims, France
- CReSTIC (Centre de Recherche en Sciences et Technologies de l’Information et de la Communication), EA 3804, Université de Reims Champagne-Ardenne, 51100 Reims, France
| | - Annarosa Cuccaro
- Hematology Unit, Department of Radiology, Radiotherapy and Hematology, Fondazione Policlinico Universitario A. Gemelli IRCCS, 00168 Rome, Italy
- Hematology Unit, Center for Translational Medicine, Azienda USL Toscana NordOvest, 55100 Livorno, Italy
| | - Elena Maiolo
- Hematology Unit, Department of Radiology, Radiotherapy and Hematology, Fondazione Policlinico Universitario A. Gemelli IRCCS, 00168 Rome, Italy
| | - Stefan Hohaus
- Hematology Unit, Department of Radiology, Radiotherapy and Hematology, Fondazione Policlinico Universitario A. Gemelli IRCCS, 00168 Rome, Italy
- Hematology Section, Department of Radiological Sciences and Hematology, Università Cattolica del Sacro Cuore, 00168 Rome, Italy
| | - Salvatore Annunziata
- Nuclear Medicine Unit, TracerGLab, Department of Radiology, Radiotherapy and Hematology, Fondazione Policlinico Universitario A. Gemelli IRCCS, 00168 Rome, Italy
| |
Collapse
|
5
|
Wajid S, Samad FA, Syed AS, Kazi F. Ki-67 and Its Relation With Complete Pathological Response in Patients With Breast Cancer. Cureus 2021; 13:e16788. [PMID: 34513395 PMCID: PMC8412210 DOI: 10.7759/cureus.16788] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 07/31/2021] [Indexed: 11/17/2022] Open
Abstract
Introduction Ki-67 is a nuclear antigen present in the synthesis phase of the cell cycle. Studies have shown that a high value of Ki-67 results in greater response to chemotherapy with higher incidence of complete pathological response, which ultimately results in improved overall survival. Methods and materials The objective of the study was to determine the frequency of high Ki-67 levels in breast cancer patients and to find the correlation of complete pathological response in breast cancer with Ki-67 levels. It is a descriptive case series with a correlational study design done at Fauji Foundation Hospital Rawalpindi. Eighty patients with locally advanced breast cancer who underwent neoadjuvant chemotherapy followed by surgery were recruited. Their Ki-67 levels were determined on trucut biopsy. Pathological response in the post-op sample was correlated with Ki-67 levels. Results The results showed 27 (33%) patients out of the 80 had high Ki-67 values. Among them 17 (63%) had complete pathological response, seven (26%) showed partial pathological response whereas three (11%) had disease progression. In contrast, out of the 53 patients having low Ki-67 values, only nine (17%) had complete pathological response, 31 (58%) showed partial pathological response and 13 (25%) had progressive disease. A Chi-square test was applied which showed significant correlation between Ki-67 and complete pathological response, with a p value of 0.00018. Conclusion Therefore high Ki-67 values in patients with breast cancer correlated well with attainment of complete pathological response. We can incorporate Ki-67 in the initial clinical assessment of breast cancer patients to help predict effectiveness as well as response to chemotherapy.
Collapse
Affiliation(s)
- Sana Wajid
- Oncology, Fauji Foundation Hospital, Rawalpindi, PAK
| | | | - Abdus S Syed
- Department of Radiation Oncology, Combined Military Hospital, Rawalpindi, PAK
| | - Faiza Kazi
- Pathology, Fauji Foundation Hospital, Rawalpindi, PAK
| |
Collapse
|