The utility of using area under the curve to analyze symptom burden during radiation/chemoradiation for head and neck cancer.

6067 Background: Patients with head and neck cancer (HNC) experience a significant treatment-related symptom burden during therapy that presents management challenges for both patients and treatment staff. Typical symptom measurement approaches have failed to capture the extent of this symptom burden over the course of therapy. We evaluated frequent symptom measurement summarized as area under the curve (AUC) as a way of portraying treatment related symptom burden in HNC patients, and explored this method for comparing symptoms produced by treatments that were expected to produce different levels of symptom impact. Methods: The M. D. Anderson Symptom Inventory - Head and Neck module - was administered at baseline and weekly for 10 weeks following the start of treatment to patients undergoing radiation therapy (XRT) as a single modality therapy (N = 49) and a second group receiving chemoradiotherapy CXRT (N = 53). We expected that treatment-related symptom burden would be greater for those patients receiving CXRT. A single value (AUC) was calculated based on the core symptoms reported by both groups of patients. Results: AUC comparisons for mean symptom severity for core symptom items demonstrated the expected greater symptom burden associated with CXRT (170.6 vs 120.9, p < 0.008). The AUC for symptom interference, as measured by the MDASI-HN, was also greater for the CXRT group (p < 0.002). AUCs for individual symptoms, such as fatigue (p < 0.002), sleep disturbance (p < 0.05) and lack of appetite (p < 0.02), were also significantly larger for the CXRT group. Conclusions: The AUC of individual and combined symptoms during cancer therapy present a useful summary of treatment related symptoms that can be used to compare treatment-related symptom burden between different treatment strategies used for the same disease. No significant financial relationships to disclose.

Download Full-text

Smoking status and symptom burden in surgical head and neck cancer patients

The Laryngoscope ◽

10.1002/lary.26159 ◽

2016 ◽

Vol 127 (1) ◽

pp. 127-133 ◽

Cited By ~ 10

Author(s):

Katherine R. Sterba ◽

Elizabeth Garrett-Mayer ◽

Matthew J. Carpenter ◽

Janet A. Tooze ◽

Jeanne L. Hatcher ◽

...

Keyword(s):

Head And Neck Cancer ◽

Head And Neck ◽

Cancer Patients ◽

Neck Cancer ◽

Smoking Status ◽

Symptom Burden

Download Full-text

Developing a Stacked Ensemble-Based Classification Scheme to Predict Second Primary Cancers in Head and Neck Cancer Survivors

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph182312499 ◽

2021 ◽

Vol 18 (23) ◽

pp. 12499

Author(s):

Chi-Chang Chang ◽

Tse-Hung Huang ◽

Pei-Wei Shueng ◽

Ssu-Han Chen ◽

Chun-Chia Chen ◽

...

Keyword(s):

Head And Neck Cancer ◽

Head And Neck ◽

Neck Cancer ◽

Classification Scheme ◽

Area Under The Curve ◽

Primary Site ◽

Second Primary ◽

Second Primary Cancer ◽

Second Primary Cancers ◽

N Status

Despite a considerable expansion in the present therapeutic repertoire for other malignancy managements, mortality from head and neck cancer (HNC) has not significantly improved in recent decades. Moreover, the second primary cancer (SPC) diagnoses increased in patients with HNC, but studies providing evidence to support SPCs prediction in HNC are lacking. Several base classifiers are integrated forming an ensemble meta-classifier using a stacked ensemble method to predict SPCs and find out relevant risk features in patients with HNC. The balanced accuracy and area under the curve (AUC) are over 0.761 and 0.847, with an approximately 2% and 3% increase, respectively, compared to the best individual base classifier. Our study found the top six ensemble risk features, such as body mass index, primary site of HNC, clinical nodal (N) status, primary site surgical margins, sex, and pathologic nodal (N) status. This will help clinicians screen HNC survivors before SPCs occur.

Download Full-text

Predictive quantitative ultrasound radiomic markers associated with treatment response in head and neck cancer

Future Science OA ◽

10.2144/fsoa-2019-0048 ◽

2020 ◽

Vol 6 (1) ◽

pp. FSO433 ◽

Cited By ~ 2

Author(s):

William T Tran ◽

Harini Suraweera ◽

Karina Quaioit ◽

Daniel Cardenas ◽

Kai X Leong ◽

...

Keyword(s):

Head And Neck Cancer ◽

Lymph Nodes ◽

Head And Neck ◽

Treatment Response ◽

Neck Cancer ◽

Quantitative Ultrasound ◽

Area Under The Curve ◽

Imaging Features ◽

Metastatic Lymph Nodes ◽

Metastatic Lymph

Aim: We aimed to identify quantitative ultrasound (QUS)-radiomic markers to predict radiotherapy response in metastatic lymph nodes of head and neck cancer. Materials & methods: Node-positive head and neck cancer patients underwent pretreatment QUS imaging of their metastatic lymph nodes. Imaging features were extracted using the QUS spectral form, and second-order texture parameters. Machine-learning classifiers were used for predictive modeling, which included a logistic regression, naive Bayes, and k-nearest neighbor classifiers. Results: There was a statistically significant difference in the pretreatment QUS-radiomic parameters between radiological complete responders versus partial responders (p < 0.05). The univariable model that demonstrated the greatest classification accuracy included: spectral intercept (SI)-contrast (area under the curve = 0.741). Multivariable models were also computed and showed that the SI-contrast + SI-homogeneity demonstrated an area under the curve = 0.870. The three-feature model demonstrated that the spectral slope-correlation + SI-contrast + SI-homogeneity-predicted response with accuracy of 87.5%. Conclusion: Multivariable QUS-radiomic features of metastatic lymph nodes can predict treatment response a priori.

Download Full-text