Machine Learning Analysis of Individual Tumor Lesions in Four Metastatic Colorectal Cancer Clinical Studies: Linking Tumor Heterogeneity to Overall Survival

Diego Vera-Yunca,Nadia Terranova,Alain Munafo,Pascal Girard,Iñaki F Trocóniz,Zinnia P Parra-Guillen

doi:10.1208/s12248-020-0434-7

Diego Vera-Yunca, Nadia Terranova + Show 4 more

Open Access

https://doi.org/10.1208/s12248-020-0434-7

Copy DOI

Abstract

Total tumor size (TS) metrics used in TS models in oncology do not consider tumor heterogeneity, which could help to better predict drug efficacy. We analyzed individual target lesions (iTLs) of patients with metastatic colorectal carcinoma (mCRC) to determine differences in TS dynamics by using the ClassIfication Clustering of Individual Lesions (CICIL) methodology. Results from subgroup analyses comparing genetic mutations and TS metrics were assessed and applied to survival analyses. Data from four mCRC clinical studies were analyzed (1781 patients, 6369 iTLs). CICIL was used to assess differences in lesion TS dynamics within a tissue (intra-class) or across different tissues (inter-class). First, lesions were automatically classified based on their location. Cross-correlation coefficients (CCs) determined if each pair of lesions followed similar or opposite dynamics. Finally, CCs were grouped by using the K-means clustering method. Heterogeneity in tumor dynamics was lower in the intra-class analysis than in the inter-class analysis for patients receiving cetuximab. More tumor heterogeneity was found in KRAS mutated patients compared to KRAS wild-type (KRASwt) patients and when using sum of longest diameters versus sum of products of diameters. Tumor heterogeneity quantified as the median patient’s CC was found to be a predictor of overall survival (OS) (HR = 1.44, 95% CI 1.08–1.92), especially in KRASwt patients. Intra- and inter-tumor tissue heterogeneities were assessed with CICIL. Derived metrics of heterogeneity were found to be a predictor of OS time. Considering differences between lesions’ TS dynamics could improve oncology models in favor of a better prediction of OS.

Highlights

Model-Informed Drug Discovery and Development (MID3) [1] has demonstrated its usefulness to improve drug development in several cases, including the oncology area and the modeling of tumor size (TS) [2,3]
TS data of individual tumor lesions (iTLs) in patients with epidermal growth factor receptor (EGFR) expressing metastatic colorectal carcinoma (mCRC) were obtained from four clinical studies: (i) CRYSTAL (Cetuximab combined with iRinotecan in first-line therapY for metaSTatic colorectAL cancer, electronic medical record 62202-013) [16], (ii) APEC (Asia Pacific nonrandomized, open-label phase II study evaluating the safety and efficacy of folinic acid (FA) + 5-fluorouracil (5-FU) + irinotecan (FOLFIRI) plus cetuximab (Erbitux) or FA + 5FU + oxaliplatin (FOLFOX) plus cetuximab as first-line therapy in subjects with KRAS wild-type (KRASwt) metastatic Colorectal cancer, electronic medical record 62202-505) [17], (iii) Study 045 [18], and (iv) OPUS (OxaliPlatin and cetUximab in firSt-line treatment of mCRC, electronic medical record 62202-047) [19]
Separate ClassIfication Clustering of Individual Lesions (CICIL) analyses were performed for each study by considering different subsets of data: (i) all patients, (ii) patients receiving cetuximab, and (iii) KRASwt patients receiving cetuximab

Summary

Introduction

Model-Informed Drug Discovery and Development (MID3) [1] has demonstrated its usefulness to improve drug development in several cases, including the oncology area and the modeling of tumor size (TS) [2,3]. Individual tumor lesions (iTLs) measurable and defined as “target lesions” at baseline, as described by Response Evaluation Criteria in Solid Tumors (RECIST) [4]. Each patient presents multiple iTLs, which can be primary or metastatic and located in several organs or tissues. This means that all tumor lesions, regardless of their location and status, are reduced to this single SLD value, called the total TS, at each assessment visit within a patient. The iTLs are assessed throughout the clinical study; the SLD is derived at each time point and categorized to quantify the tumor response to the treatment [4]. Observed or model-derived TS metrics, such as the early tumor shrinkage (ETS, relative reduction of total TS at certain time points) or time to tumor growth, have been shown to be predictors of overall survival (OS) [5]

Objectives

Methods

Results

Discussion

Conclusion