Precision association of lymphatic disease spread with radiation-associated toxicity in oropharyngeal squamous carcinomas

Determining risk and predictors of head and neck cancer treatment-related lymphedema: A clinicopathologic and dosimetric data mining approach using interpretable machine learning and ensemble feature selection

Background and purpose

The ability to determine the risk and predictors of lymphedema is vital in improving the quality of life for head and neck (HN) cancer patients. However, selecting robust features is challenging due to the multicollinearity and high dimensionality of radiotherapy (RT) data. This study aims to overcome these challenges using an ensemble feature selection technique with machine learning (ML).

Materials and methods

Thirty organs-at-risk, including bilateral cervical lymph node levels, were contoured, and dose-volume data were extracted from 76 HN treatment plans. Clinicopathologic data was collected. Ensemble feature selection was used to reduce the number of features. Using the reduced features as input to ML and competing risk models, internal and external lymphedema prediction capability was evaluated with the ML models, and time to lymphedema event and risk stratification were estimated using the risk models.

Results

Two ML models, XGBoost and random forest, exhibited robust prediction performance. They achieved average F1-scores and AUCs of 84 ± 3.3 % and 79 ± 11.9 % (external lymphedema), and 64 ± 12 % and 78 ± 7.9 % (internal lymphedema). Predictive ML and risk models identified common predictors, including bulky node involvement, high dose to various lymph node levels, and lymph nodes removed during surgery. At 180 days, removing 0-25, 26-50, and > 50 lymph nodes increased external lymphedema risk to 72.1 %, 95.6 %, and 57.7 % respectively (p = 0.01).

Conclusion

Our approach, involving the reduction of HN RT data dimensionality, resulted in effective ML models for HN lymphedema prediction. Predictive dosimetric features emerged from both predictive and competing risk models. Consistency with clinicopathologic features from other studies supports our methodology.

Roses Have Thorns: Understanding the Downside of Oncological Care Delivery Through Visual Analytics and Sequential Rule Mining

Personalized head and neck cancer therapeutics have greatly improved survival rates for patients, but are often leading to understudied long-lasting symptoms which affect quality of life. Sequential rule mining (SRM) is a promising unsupervised machine learning method for predicting longitudinal patterns in temporal data which, however, can output many repetitive patterns that are difficult to interpret without the assistance of visual analytics. We present a data-driven, human-machine analysis visual system developed in collaboration with SRM model builders in cancer symptom research, which facilitates mechanistic knowledge discovery in large scale, multivariate cohort symptom data. Our system supports multivariate predictive modeling of post-treatment symptoms based on during-treatment symptoms. It supports this goal through an SRM, clustering, and aggregation back end, and a custom front end to help develop and tune the predictive models. The system also explains the resulting predictions in the context of therapeutic decisions typical in personalized care delivery. We evaluate the resulting models and system with an interdisciplinary group of modelers and head and neck oncology researchers. The results demonstrate that our system effectively supports clinical and symptom research.

Investigating Predictive Factors of Dysphagia and Treatment Prolongation in Patients with Oral Cavity or Oropharyngeal Cancer Receiving Radiation Therapy Concurrently with Chemotherapy

Radiation therapy (RT) treatment for head and neck cancer has been associated with dysphagia manifestation leading to worse outcomes and decrease in life quality. In this study, we investigated factors leading to dysphagia and treatment prolongation in patients with primaries arising from oral cavity or oropharynx that were submitted to radiation therapy concurrently with chemotherapy. The records of patients with oral cavity or oropharyngeal cancer that received RT treatment to the primary and bilateral neck lymph nodes concurrently with chemotherapy were retrospectively reviewed. Logistic regression models were used to analyze the potential correlation between explanatory variables and the primary (dysphagia ≥ 2) and secondary (prolongation of total treatment duration ≥ 7 days) outcomes of interest. The Toxicity Criteria of the Radiation Therapy Oncology Group (RTOG) and the European Organization for Research and Treatment of Cancer (EORTC) were used to evaluate dysphagia. A total of 160 patients were included in the study. Age mean was 63.31 (SD = 8.24). Dysphagia grade ≥ 2 was observed in 76 (47.5%) patients, while 32 (20%) experienced treatment prolongation ≥ 7 days. The logistic regression analysis showed that the volume in the primary site of disease that received dose ≥ 60 Gy (≥118.75 cc, p < 0.001, (OR = 8.43, 95% CI [3.51-20.26]) and mean dose to the pharyngeal constrictor muscles > 40.6 Gy (p < 0.001, OR = 11.58, 95% CI [4.84-27.71]) were significantly associated with dysphagia grade ≥ 2. Treatment prolongation ≥ 7 days was predicted by higher age (p = 0.007, OR = 1.079, 95% CI [1.021-1.140]) and development of grade ≥ 2 dysphagia (p = 0.005, OR = 4.02, 95% CI [1.53-10.53]). In patients with oral cavity or oropharyngeal cancer that receive bilateral neck irradiation concurrently with chemotherapy, constrictors mean dose and the volume in the primary site receiving ≥ 60 Gy should be kept below 40.6 Gy and 118.75 cc, respectively, whenever possible. Elderly patients or those that are considered at high risk for dysphagia manifestation are more likely to experience treatment prolongation ≥ 7 days and they should be closely monitored during treatment course for nutritional support and pain management.

Optimal Treatment Selection in Sequential Systemic and Locoregional Therapy of Oropharyngeal Squamous Carcinomas: Deep Q-Learning With a Patient-Physician Digital Twin Dyad

BACKGROUND

Currently, selection of patients for sequential versus concurrent chemotherapy and radiation regimens lacks evidentiary support and it is based on locally optimal decisions for each step.

OBJECTIVE

We aim to optimize the multistep treatment of patients with head and neck cancer and predict multiple patient survival and toxicity outcomes, and we develop, apply, and evaluate a first application of deep Q-learning (DQL) and simulation to this problem.

METHODS

The treatment decision DQL digital twin and the patient's digital twin were created, trained, and evaluated on a data set of 536 patients with oropharyngeal squamous cell carcinoma with the goal of, respectively, determining the optimal treatment decisions with respect to survival and toxicity metrics and predicting the outcomes of the optimal treatment on the patient. Of the data set of 536 patients, the models were trained on a subset of 402 (75%) patients (split randomly) and evaluated on a separate set of 134 (25%) patients. Training and evaluation of the digital twin dyad was completed in August 2020. The data set includes 3-step sequential treatment decisions and complete relevant history of the patient cohort treated at MD Anderson Cancer Center between 2005 and 2013, with radiomics analysis performed for the segmented primary tumor volumes.

RESULTS

On the test set, we found mean 87.35% (SD 11.15%) and median 90.85% (IQR 13.56%) accuracies in treatment outcome prediction, matching the clinicians' outcomes and improving the (predicted) survival rate by +3.73% (95% CI -0.75% to 8.96%) and the dysphagia rate by +0.75% (95% CI -4.48% to 6.72%) when following DQL treatment decisions.

CONCLUSIONS

Given the prediction accuracy and predicted improvement regarding the medically relevant outcomes yielded by this approach, this digital twin dyad of the patient-physician dynamic treatment problem has the potential of aiding physicians in determining the optimal course of treatment and in assessing its outcomes.

THALIS: Human-Machine Analysis of Longitudinal Symptoms in Cancer Therapy

Although cancer patients survive years after oncologic therapy, they are plagued with long-lasting or permanent residual symptoms, whose severity, rate of development, and resolution after treatment vary largely between survivors. The analysis and interpretation of symptoms is complicated by their partial co-occurrence, variability across populations and across time, and, in the case of cancers that use radiotherapy, by further symptom dependency on the tumor location and prescribed treatment. We describe THALIS, an environment for visual analysis and knowledge discovery from cancer therapy symptom data, developed in close collaboration with oncology experts. Our approach leverages unsupervised machine learning methodology over cohorts of patients, and, in conjunction with custom visual encodings and interactions, provides context for new patients based on patients with similar diagnostic features and symptom evolution. We evaluate this approach on data collected from a cohort of head and neck cancer patients. Feedback from our clinician collaborators indicates that THALIS supports knowledge discovery beyond the limits of machines or humans alone, and that it serves as a valuable tool in both the clinic and symptom research.