Longitudinal effects of a novel advanced pneumatic compression device on patient-reported outcomes in the management of cancer-related head and neck lymphedema: A preliminary report

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.

Under recognition and treatment of lymphedema in head and neck cancer survivors - a database study

PURPOSE

Head and neck cancer (HNC) will be diagnosed in approximately 54,000 Americans in 2022 with more than 11,000 dying as a result. The treatment of HNC often involves aggressive multimodal therapy including surgery, radiotherapy, and systemic therapy. HNC and its treatments are associated with multiple painful and function-limiting neuromusculoskeletal and visceral long-term and late effects. Among these is head and neck lymphedema (HNL), the abnormal accumulation of protein rich fluid, in as many as 90% of survivors. Though HNL is common and potentially contributory to other function-limiting issues in this population, it is notoriously understudied, underrecognized, underdiagnosed, and undertreated. This study seeks to determine the incidence of HNC-related lymphedema diagnosis and treatment in a large US healthcare claims repository database.

METHODS

A retrospective observational cohort design and data from an integrated US healthcare claims repository-the IBM MarketScan Commercial Claims and Encounters (CCAE) and Medicare Supplemental and Coordination of Benefits (MDCR) Databases spanning the period April 1, 2012 through March 31, 2020.

RESULTS

Of the 16,654 HNC patients eligible for evaluation, 1,082 (6.5%) with a diagnosis of lymphedema were identified based on eligibility criteria. Of the 521 HNC patients evaluated for lymphedema treatment, 417 (80.0%) patients received 1.5 courses of MLD, 71 (13.6%) patients were prescribed compression garments, and 45 (8.6%) patients received an advanced pneumatic compression device.

CONCLUSION

HNL in this population of HNC survivors was underdiagnosed and treated compared with contemporary assessments HNL incidence.

Assessment of Measures of Head and Neck Lymphedema Following Head and Neck Cancer Treatment: A Systematic Review

Purpose: Head and neck lymphedema is a common condition following head and neck cancer (HNC) treatment, with substantial functional morbidity. This systematic review aimed to (1) identify tools used to assess head and neck lymphedema in HNC patients and (2) determine their validity and reliability. Methods: Electronic and hand searches of Prospero, MEDLINE, Cochrane Library, and Embase were searched from their inception until April 2021, and hand searches were independently screened by two reviewers. Studies were included if they were available in English and measured lymphedema in adult HNC patients (aged ≥18 years). Data including psychometric characteristics were extracted and synthesized narratively, with the Quality Assessment of Diagnostic Accuracy Studies-2 and the COnsensus-based Standards for the selection of health Measurement INstruments checklists used to assess risk of bias. Results: Thirty-three studies, reporting 38 assessment tools, were included. Assessments included clinician rating scales, symptom inventories, size measures, measures of internal edema, radiographic and ultrasonographic measures, and quality-of-life measures. Of the 38 measures cited, only 11 had any degree of validation and reliability testing. Risk of bias varied among the different assessment tools. Conclusion: While many tools are used in the assessment of head and neck lymphedema, the majority of these tools lack validation and reliability data. Only one tool, the Head and Neck Lymphedema and Fibrosis Symptom Inventory, met criteria for strong quality assessment. Further efforts to establish a core set of metrics for this complex condition are warranted.

Systematic review of head and neck lymphedema assessment

Head and neck lymphedema (HNL) is an increasingly recognized complication of head and neck cancer and its treatment. However, no consensus exists on the "gold-standard" assessment tool for the purposes of diagnosis, classification, or monitoring of HNL. We conducted a systematic review of the literature regarding HNL assessment to determine the optimal method/s of assessment for patients with HNL. A review of publications between January 2000 and September 2021 was undertaken on four electronic databases. Studies were excluded if no clear assessment method of HNL was documented. Sixty-seven articles were included in the study. A wide range of assessment methods for HNL have been reported in the literature. For the purposes of diagnosis and classification of physical findings, computed tomography (CT) appears the most promising tool available for both external and internal HNL. In terms of monitoring, ultrasound appears optimal for external HNL, while a clinician-reported rating scale on laryngoscopy is the gold standard for internal HNL. Patient-reported assessment must be considered alongside objective methods to classify symptom burden and monitor improvement with treatment.

State of Rehabilitation Research in the Head and Neck Cancer Population: Functional Impact vs. Impairment-Focused Outcomes

PURPOSE OF REVIEW

Management of head and neck cancer (HNC) typically involves a morbid combination of surgery, radiation, and systemic therapy. As the number of HNC survivors grows, there is growing interest in rehabilitation strategies to manage HNC-related comorbidity. In this review, we summarize the current state of HNC rehabilitation research.

RECENT FINDINGS

We have organized our review using the World Health Organization's International Classification of Function (ICF) model of impairment, activity, and participation. Specifically, we describe the current research on rehabilitation strategies to prevent and treat impairments including dysphagia, xerostomia, dysgeusia, dysosmia, odynophagia, trismus, first bite syndrome, dysarthria, dysphonia, lymphedema, shoulder syndrome, cervicalgia, cervical dystonia and dropped head syndrome, deconditioning, and fatigue. We also discuss the broader impact of HNC-related impairment by exploring the state of rehabilitation literature on activity, participation, psychosocial distress, and suicidality in HNC survivors. We demonstrate that research in HNC rehabilitation continues to focus primarily on impairment-driven interventions. There remains a dearth of HNC rehabilitation studies directly examining the impact of rehabilitation interventions on outcomes related to activity and participation. More high-quality interventional studies and reviews are needed to guide prevention and treatment of functional loss in HNC survivors.

Lymphoedema after head and neck cancer treatment: an overview for clinical practice

Lymphoedema is a disorder of the lymphatic system that presents as an atypical swelling and accumulation of protein-rich fluid within the interstitial spaces. Head and neck lymphoedema (HNL) is highly prevalent in patients who have been treated for head and neck cancer (HNC) and may manifest externally on the face and neck; internally within the oral cavity, pharynx or larynx; or as a combination of both. HNL is known to contribute to a wide range of physical, functional and psychological issues, and presents several unique challenges in terms of its management. This review article provides an overview of HNL for clinicians and aims to improve awareness of this condition and the impact it has on patients.

Longitudinal effects of a novel advanced pneumatic compression device on patient-reported outcomes in the management of cancer-related head and neck lymphedema: A preliminary report

Background

Head and neck cancer (HNC) survivors experience head and neck lymphedema (HNL), which requires treatment to prevent morbidity. We explore the self‐reported outcomes and satisfaction of patients with HNC receiving treatment for HNL with an advanced pneumatic compression device (APCD).

Methods

HNC survivors (n = 205) prescribed with an at‐home Flexitouch head and neck APCD completed pretreatment and posttreatment self‐reported assessments addressing efficacy, function, and symptoms. Participant average age was 60 years with 74% male. Pre‐post responses for ≥25 days of use were assessed via the non‐parametric Wilcoxon Signed Rank test.

Results

Analysis revealed statistically significant improvement in all symptoms and all function items (P < 0.00001). Compliance with prescribed therapy (at least 30 minutes daily) was high with 71% of participants reporting daily use and 87% reporting overall satisfaction.

Conclusions

The reported improvements in function and symptoms, and high compliance rate, provide a rationale for a subsequent randomized controlled trial.