Cancer of Unknown Primary Presenting as Bone-Predominant or Lymph Node-Only Disease: A Clinicopathologic Portrait

Development of a web-based calculator to predict three-month mortality among patients with bone metastases from cancer of unknown primary: An internally and externally validated study using machine-learning techniques

Background

Individualized therapeutic strategies can be carried out under the guidance of expected lifespan, hence survival prediction is important. Nonetheless, reliable survival estimation in individuals with bone metastases from cancer of unknown primary (CUP) is still scarce. The objective of the study is to construct a model as well as a web-based calculator to predict three-month mortality among bone metastasis patients with CUP using machine learning-based techniques.

Methods

This study enrolled 1010 patients from a large oncological database, the Surveillance, Epidemiology, and End Results (SEER) database, in the United States between 2010 and 2018. The entire patient population was classified into two cohorts at random: a training cohort (n=600, 60%) and a validation cohort (410, 40%). Patients from the validation cohort were used to validate models after they had been developed using the four machine learning approaches of random forest, gradient boosting machine, decision tree, and eXGBoosting machine on patients from the training cohort. In addition, 101 patients from two large teaching hospital were served as an external validation cohort. To evaluate each model's ability to predict the outcome, prediction measures such as area under the receiver operating characteristic (AUROC) curves, accuracy, and Youden index were generated. The study's risk stratification was done using the best cut-off value. The Streamlit software was used to establish a web-based calculator.

Results

The three-month mortality was 72.38% (731/1010) in the entire cohort. The multivariate analysis revealed that older age (P=0.031), lung metastasis (P=0.012), and liver metastasis (P=0.008) were risk contributors for three-month mortality, while radiation (P=0.002) and chemotherapy (P<0.001) were protective factors. The random forest model showed the highest area under curve (AUC) value (0.796, 95% CI: 0.746-0.847), the second-highest precision (0.876) and accuracy (0.778), and the highest Youden index (1.486), in comparison to the other three machine learning approaches. The AUC value was 0.748 (95% CI: 0.653-0.843) and the accuracy was 0.745, according to the external validation cohort. Based on the random forest model, a web calculator was established: https://starxueshu-codeok-main-8jv2ws.streamlitapp.com/. When compared to patients in the low-risk groups, patients in the high-risk groups had a 1.99 times higher chance of dying within three months in the internal validation cohort and a 2.37 times higher chance in the external validation cohort (Both P<0.001).

Conclusions

The random forest model has promising performance with favorable discrimination and calibration. This study suggests a web-based calculator based on the random forest model to estimate the three-month mortality among bone metastases from CUP, and it may be a helpful tool to direct clinical decision-making, inform patients about their prognosis, and facilitate therapeutic communication between patients and physicians.

Efficacy of pembrolizumab in patients with advanced cancer of unknown primary (CUP): a phase 2 non-randomized clinical trial

BACKGROUND

Cancer of unknown primary (CUP) is an aggressive rare malignancy with limited treatment options. Data regarding clinical activity of immune checkpoint inhibitors in CUP is lacking. Therefore, we evaluated the efficacy of pembrolizumab, a programmed cell death-1 inhibitor, in patients with CUP.

METHODS

The study was designed as a phase 2 basket trial for independent rare tumor cohorts including CUP. Adult patients with CUP who had progressed on previous systemic therapy, performance status 0/1 and measurable disease per Response Evaluation Criteria in Solid Tumors (RECIST V.1.1) were eligible. Patients received pembrolizumab (200 mg) intravenously every 21 days. Twenty-nine patients were enrolled and treated between August 2016 and June 2020. The primary endpoint was non-progression rate (NPR) at 27 weeks (NPR-27) per immune-related RECIST. Key prespecified secondary endpoints were confirmed objective response rate (ORR), safety, duration of response (DoR), progression-free survival (PFS) and overall survival (OS). Pretreatment biopsies were examined for biomarkers of response (programmed cell death ligand-1 (PD-L1) expression and tumor infiltrating lymphocytes (TILs)).

RESULTS

Among 25 (of 29 enrolled) eligible and evaluable patients, 14 (56%) had poorly differentiated carcinoma. Patients received a median of two lines of therapy prior to enrollment. Median follow-up was 27.3 months. NPR-27 was observed in seven patients (28.0% (95% CI: 12.1 to 49.4)). ORR was 20.0% (95% CI: 6.8 to 40.7) with five patients achieving immune-related partial response with median DoR of 14.7 months (95% CI: 9.8 to 19.6). Median PFS and OS were 4.1 (95% CI: 3.1 to 5.1) and 11.3 (95% CI: 5.5 to 17.1) months, respectively. Treatment-related adverse events of any and grade ≥3 were seen in 19 (76%) and 4 (16%) patients, respectively. One (4%) patient had grade 3 immune-related acute kidney injury requiring treatment discontinuation. Neither PD-L1 nor TILs were associated with NPR-27. Both positive PD-L1 staining (44.4% vs 6.3%; p=0.040) and intense TIL infiltration (44.4% vs 6.3%; p=0.040) were associated with response.

CONCLUSION

Pembrolizumab showed encouraging efficacy in patients with CUP with acceptable safety profile.

TRIAL REGISTRATION NUMBER

NCT02721732.