Survival Rates Using Individualized Bioselection Treatment Methods in Patients With Advanced Laryngeal Cancer

Abstract

Importance: Use of chemoradiotherapy for advanced laryngeal cancer led to a major shift in treatment as an alternative to laryngectomy. Despite widespread adoption of chemoradiotherapy, survival rates have not improved and the original premise of matching neoadjuvant chemotherapy tumor response to determine subsequent treatment has not been followed.

Objective: To determine whether improved survival could be achieved by incorporating a single cycle of neoadjuvant chemotherapy to select patients with advanced disease for either laryngectomy or concurrent chemoradiotherapy.

Design, setting, and participants: An unselected cohort of 247 patients with laryngeal cancer in an academic institution between 2002 and 2012 was evaluated. Patients with limited disease (stages I and II) underwent endoscopic resection, radiotherapy, or chemoradiotherapy for deeply invasive T2 lesions. For patients with advanced disease (stages III and IV), neoadjuvant chemotherapy, concurrent chemoradiotherapy, or primary surgery was recommended. Overall survival (OS) and disease-specific survival (DSS) were analyzed. Median follow-up was 48 months. The study was conducted from January 1, 2002, to December 31, 2012; data analysis was completed December 1, 2015.

Interventions: Endoscopic resection, radiotherapy, chemoradiotherapy, neoadjuvant chemotherapy, concurrent chemoradiotherapy, and primary surgery.

Main outcomes and measures: Overall survival and DSS.

Results: Of the 247 patients, 191 (77.3%) were male; mean (SD) age was 59.6 (10.4) years. Of 94 patients with limited disease, 33 (35.1%) underwent endoscopic resection; 50 (53.2%), radiotherapy alone; and 11 (11.7%), chemoradiotherapy for deeply invasive T2 lesions. Of 153 patients with advanced disease, 71 (46.4%) received neoadjuvant chemotherapy; 50 (32.7%), concurrent chemoradiotherapy; and 32 (20.9%), surgery. Five-year OS and DSS was 75% (95% CI, 68%-81%) and 83% (95% CI, 77%-88%), respectively, for the entire cohort. The DSS was 92% (95% CI, 83%-97%) for patients with stage I or II and 78% (95% CI, 69%-84%) for patients with stage III or IV disease. For patients with advanced disease, 5-year OS and DSS ranged from 78% (95% CI, 55%-90%) and 91% (95% CI, 67%-98%), respectively, for surgery; to 76% (95% CI, 63%-85%) and 79% (95% CI, 67%-88%), respectively, for neoadjuvant bioselection; and to 61% (95% CI, 44%-75%) and 66% (95% CI, 48%-79%), respectively, for primary chemoradiotherapy. Propensity-adjusted, multivariable controlling for known prognostic factors DSS was significantly improved in the neoadjuvant group compared with the chemoradiotherapy group (hazard ratio [HR], 0.48; 95% CI, 0.29-0.80).

Conclusions and relevance: Superior survival rates were achieved with a bioselective treatment approach using a single cycle of neoadjuvant chemotherapy. Good survival rates were also achieved in patients selected for primary surgery, and both neoadjuvant chemotherapy and primary surgery were better than survival rates with concurrent chemoradiotherapy, suggesting that the optimal individualized treatment approach for patients with advanced laryngeal cancer has not yet been defined.

Figure 1

Distribution of 247 patients according to clinical tumor stage, primary treatment modality and frequency of total laryngectomy.

Figure 2

Overall (OS) and disease-specific Kaplan Meier survival (DSS) curves for 247 patients with laryngeal squamous carcinoma grouped by clinical tumor stage. Differences in outcomes were apparent comparing Stage I to Stage IV patients for DSS and OS. Overall survival rates did not differ significantly for other stage comparisons.

Figure 3

Overall and disease-specific survival for 247 patients with laryngeal squamous carcinoma according to initial primary treatment modality. Survival outcomes were significantly better for patients treated with primary surgery.

Figure 4

Overall and disease-specific survival for patients with Stage I and II laryngeal cancer according to primary treatment modality. Overall survival rates for early disease patients were significantly better for primary surgery compared to radiation or chemoradiation, however, differences in DSS did not reach statistical significance. The treatment differences were confounded by differences in patient characteristics such as T class. Surgically treated patients were significantly more likely to be lower stage (p<0.001). After excluding the 9 patients with in situ carcinoma and controlling for stage in a multivariable Cox model, neither OS and DSS differences remained statistically significant (data not shown.)

Figure 5

Overall and disease-specific survival (DSS) for 153 patients with advanced (Stage III, IV) laryngeal cancer according to planned initial treatment modality. Although overall survival curve comparisons did not differ significantly by planned treatment, planned chemoradiation tended to have worse overall and disease specific outcomes. By Cox regression analysis, DSS was significantly improved in the neoadjuvant group over definitive chemoradiation/radiation without induction selection [Hazard ratio 0.27, 95%CI: (0.11, 0.68)] after controlling for age, stage (III vs IV), gender, and current smoking and DSS for the neoadjuvant group was similar to the surgery group, [Hazard ratio 2.80, 95%CI: (0.62, 12.61)].