Individualized quality of life benefit and cost-effectiveness estimates of proton therapy for patients with oropharyngeal cancer

A Systematic Review of the Economic Burden of Proton Therapy in Head and Neck Cancer

BACKGROUND

Radiation therapy is used to treat head and neck cancer (HNC) patients. Proton beam therapy (PBT) is one of the newer treatment options. This systematic review will describe the cost and cost-effectiveness of PBT compared with other first-line treatment options based on available literature and provide a better understanding of its usage in HNC in the future.

METHODS

This systematic review was conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Systematic searches were conducted in PUBMED, EMBASE and SCOPUS till February 2022. Original pharmacoeconomic articles written in English that considered PBT for HNC were included; the title, abstract and full text of the search items were screened. The included studies were critically appraised using the Drummond Checklist followed by data extraction.

RESULTS

Eight of the ten included studies were of good quality; most were cost-effectiveness or cost comparison studies and used the Markov model and lifetime horizon. The dominant comparator was intensity-modulated radiotherapy. The willingness to pay threshold ranged from $30,828 to $150,000 per QALY. The incremental cost-effectiveness ratio (ICER) was between $4,436.1 and $695,000 per QALY. In HNC patients with human papillomavirus infection, the ICER was lower ($288,000/QALY) from the payer's perspective, but much higher ($390,000/QALY) from the societal perspective.

CONCLUSION

Our systematic review showed that appropriate patient selection can make PBT cost-effective. HPV-associated tumors can be cost-effectively treated with PBT. From the payer's perspective, PBT is a cost-effective treatment option. In younger patients, PBT can result in lesser incidence of adverse effects, and hence, can reduce the subsequent need for long-term supportive care. Lower fractionation schedules can also make PBT a cost-effective treatment.

Patient selection for proton therapy using Normal Tissue Complication Probability with deep learning dose prediction for oropharyngeal cancer

BACKGROUND

In cancer care, determining the most beneficial treatment technique is a key decision affecting the patient's survival and quality of life. Patient selection for proton therapy (PT) over conventional radiotherapy (XT) currently entails comparing manually generated treatment plans, which requires time and expertise.

PURPOSE

We developed an automatic and fast tool, AI-PROTIPP (Artificial Intelligence Predictive Radiation Oncology Treatment Indication to Photons/Protons), that assesses quantitatively the benefits of each therapeutic option. Our method uses deep learning (DL) models to directly predict the dose distributions for a given patient for both XT and PT. By using models that estimate the Normal Tissue Complication Probability (NTCP), namely the likelihood of side effects to occur for a specific patient, AI-PROTIPP can propose a treatment selection quickly and automatically.

METHODS

A database of 60 patients presenting oropharyngeal cancer, obtained from the Cliniques Universitaires Saint Luc in Belgium, was used in this study. For every patient, a PT plan and an XT plan were generated. The dose distributions were used to train the two dose DL prediction models (one for each modality). The model is based on U-Net architecture, a type of convolutional neural network currently considered as the state of the art for dose prediction models. A NTCP protocol used in the Dutch model-based approach, including grades II and III xerostomia and grades II and III dysphagia, was later applied in order to perform automatic treatment selection for each patient. The networks were trained using a nested cross-validation approach with 11-folds. We set aside three patients in an outer set and each fold consists of 47 patients in training, five in validation and five for testing. This method allowed us to assess our method on 55 patients (five patients per test times the number of folds).

RESULTS

The treatment selection based on the DL-predicted doses reached an accuracy of 87.4% for the threshold parameters set by the Health Council of the Netherlands. The selected treatment is directly linked with these threshold parameters as they express the minimal gain brought by the PT treatment for a patient to be indicated to PT. To validate the performance of AI-PROTIPP in other conditions, we modulated these thresholds, and the accuracy was above 81% for all the considered cases. The difference in average cumulative NTCP per patient of predicted and clinical dose distributions is very similar (less than 1% difference).

CONCLUSIONS

AI-PROTIPP shows that using DL dose prediction in combination with NTCP models to select PT for patients is feasible and can help to save time by avoiding the generation of treatment plans only used for the comparison. Moreover, DL models are transferable, allowing, in the future, experience to be shared with centers that would not have PT planning expertise.

Proton Beam Radiation Therapy for Oropharyngeal Squamous Cell Carcinoma

Purpose

To discuss the role of proton beam therapy (PBT) in the treatment of patients with oropharyngeal squamous cell carcinoma (OPSCC).

Materials and Methods

A review of the pertinent literature.

Results

Proton beam therapy likely results in reduced acute and late toxicity as compared with intensity-modulated radiation therapy (IMRT). The extent of the reduced toxicity, which may be modest, depends on the endpoint and technical factors such as pencil beam versus passive scattered PBT and adaptive replanning. The disease control rates after PBT are likely similar to those after IMRT.

Conclusion

Proton beam therapy is an attractive option to treat patients with OPSCC. Whether it becomes widely available depends on access.