Bayesian Networks to Support Decision-Making for Immune-Checkpoint Blockade in Recurrent/Metastatic (R/M) Head and Neck Squamous Cell Carcinoma (HNSCC)

Abstract

New diagnostic methods and novel therapeutic agents spawn additional and heterogeneous information, leading to an increasingly complex decision-making process for optimal treatment of cancer. A great amount of information is collected in organ-specific multidisciplinary tumor boards (MDTBs). By considering the patient's tumor properties, molecular pathological test results, and comorbidities, the MDTB has to consent an evidence-based treatment decision. Immunotherapies are increasingly important in today's cancer treatment, resulting in detailed information that influences the decision-making process. Clinical decision support systems can facilitate a better understanding via processing of multiple datasets of oncological cases and molecular genetic information, potentially fostering transparency and comprehensibility of available information, eventually leading to an optimum treatment decision for the individual patient. We constructed a digital patient model based on Bayesian networks to combine the relevant patient-specific and molecular data with depended probabilities derived from pertinent studies and clinical guidelines to calculate treatment decisions in head and neck squamous cell carcinoma (HNSCC). In a validation analysis, the model can provide guidance within the growing subject of immunotherapy in HNSCC and, based on its ability to calculate reliable probabilities, facilitates estimation of suitable therapy options. We compared actual treatment decisions of 25 patients with the calculated recommendations of our model and found significant concordance (Cohen's κ = 0.505, p = 0.009) and 84% accuracy.

Keywords: Bayesian network; clinical decision support system (CDSS); head and neck squamous cell carcinoma (HNSCC); immune checkpoint blockade (ICB) targeted therapy; immunotherapy; molecular tumor board; multidisciplinary tumor board.

Figure 1

The initial literature research on HNSCC, ICB, and potential future targets of ICB led to a first graph model with more than 290 nodes. The input of regular expert meetings (depicted by the dashed arrow) and visits of the university hospital’s tumor board (depicted by the drawn trough arrow) were integrated into the model development process. After step-by-step adoption of the model (with regular meetings, depicted by the dotted line), we finalized the model for validation analysis.

Figure 2

An overview of the complete model. Thematically related variables share the same color. Orange: TNM, yellow: Immunohistochemistry and genetic targets; pink: HNSCC, blue: additional conditions to match indications or treatment conditions; lilac: drugs and other therapeutic measures.

Figure 3

(a): A part of the main model, representing the essential variables, leading to a decision regarding whether Pembrolizumab or Nivolumab is a suitable choice or not. The color scheme matches the explanations above. We implemented TNM, the ECOG score and recurrence node from the blue group and PD-1, immunohistochemistry as well as CPS and TPS nodes from the yellow group. (b) For R/M HNSCC patients without information about the PD-L1 status and an observed progression during or after platinum-based therapy, the use of Nivolumab is recommended by the model. Because the approval of Nivolumab is independent from TPS and CPS, the probability for Nivolumab treatment increases compared to the use of Pembrolizumab (cf. CheckMate-141 and KEYNOTE-048).