Improving guideline sensitivity and specificity for the identification of proactive gastrostomy placement in patients with head and neck cancer

Development of machine learning models for the prediction of long-term feeding tube dependence after oral and oropharyngeal cancer surgery

PURPOSE

To predict the necessity of enteral nutrition at 28 days after surgery in patients undergoing major head and neck oncologic procedures for oral and oropharyngeal cancers.

MATERIAL AND METHODS

Data from 193 patients with oral cavity and oropharyngeal squamous cell carcinoma were retrospectively collected at two tertiary referral centers to train (n = 135) and validate (n = 58) six supervised machine learning (ML) models for binary prediction employing 29 clinical variables available pre-operatively.

RESULTS

The accuracy of the six ML models ranged between 0.74 and 0.88, while the measured area under the curve (AUC) between 0.75 and 0.87. The ML algorithms showed high specificity (range 0.87-0.96) and moderate sensitivity (range: 0.31-0.77) in detecting patients with ≥28 days feeding tube dependence. Negative predictive value was higher (range: 0.81-0.93) compared to positive predictive value (range: 0.40-0.71). Finally, the F1 score ranged between 0.35 and 0.74.

CONCLUSIONS

Classification performance of the ML algorithms showed optimistic accuracy in the prediction of enteral nutrition at 28 days after surgery. Prospective studies are mandatory to define the clinical benefit of a ML-based pre-operative prediction of a personalized nutrition protocol.

Enteral nutrition support and treatment toxicities in patients with head and neck cancer receiving definitive or adjuvant helical intensity-modulated radiotherapy with concurrent chemotherapy

BACKGROUND

Enteral nutrition (EN) is often required in patients with head and neck cancer (HNSCC); however, initiation criteria is limited or inconsistent. This study aimed to describe the relationship of treatment toxicities and requirement for EN and investigate toxicity and baseline characteristics association with EN duration.

METHODS

Acute toxicities and baseline characteristics were collected from patients with HNSCC (n = 110) undergoing H-IMRT. Percentage EN contributing to estimated requirements and EN duration were measured.

RESULTS

The threshold for patients needing ≥50% of estimated requirements via EN increased from week 3 to 4 for grade ≥2 oral/pharyngeal mucositis, dysgeusia, thick saliva and nausea, and for grade 3 dysphagia. Patients with grade 2-3 dysphagia had a reduced risk of ceasing EN compared to those with grade 0-1 dysphagia.

CONCLUSIONS

Using acute toxicities in clinical practice may be a useful tool to inform prompt initiation of EN prior to decline in nutritional status and anticipate EN duration.

Anesthesia and Enhanced Recovery After Head and Neck Surgery

Enhanced recovery protocols have been developed from gastrointestinal, colorectal, and thoracic surgery populations. The basic tenets of head and neck enhanced recovery are: a multidisciplinary team working around the patient, preoperative carbohydrate loading, multimodal analgesia, early mobilization and oral feeding, and frequent reassessment and auditing of protocols to improve patient outcomes. The implementation of enhanced recovery protocols across surgical populations appear to decrease length of stay, reduce cost, and improve patient satisfaction without sacrificing patient quality of care or changing readmission rates. This article examines evidence-based enhanced recovery interventions and tailors them to a major head and neck surgery population.

Randomised controlled trial of early prophylactic feeding vs standard care in patients with head and neck cancer

Background:

Weight loss remains significant in patients with head and neck cancer, despite prophylactic gastrostomy and intensive dietary counseling. The aim of this study was to improve outcomes utilising an early nutrition intervention.

Methods:

Patients with head and neck cancer at a tertiary hospital in Australia referred for prophylactic gastrostomy prior to curative intent treatment were eligible for this single centre randomised controlled trial. Exclusions included severe malnutrition or dysphagia. Patients were assigned following computer-generated randomisation sequence with allocation concealment to either intervention or standard care. The intervention group commenced supplementary tube feeding immediately following tube placement. Primary outcome measure was percentage weight loss at three months post treatment.

Results:

Recruitment completed June 2015 with 70 patients randomised to standard care (66 complete cases) and 61 to intervention (56 complete cases). Following intention-to-treat analysis, linear regression found no effect of the intervention on weight loss (10.9±6.6% standard care vs 10.8±5.6% intervention, P=0.930) and this remained non-significant on multivariable analysis (P=0.624). No other differences were found for quality of life or clinical outcomes. No serious adverse events were reported.

Conclusions:

The early intervention did not improve outcomes, but poor adherence to nutrition recommendations impacted on potential outcomes.

Comparison of Nutritional and Clinical Outcomes in Patients with Head and Neck Cancer Undergoing Chemoradiotherapy Utilizing Prophylactic versus Reactive Nutrition Support Approaches

BACKGROUND

The optimal method of tube feeding for patients with head and neck cancer remains unclear. A validated protocol is available that identifies high-nutritional-risk patients who would benefit from prophylactic gastrostomy tube placement. Adherence to this protocol is ultimately determined by clinical team discretion or patient decision.

OBJECTIVE

The study aim was to compare outcomes after adherence and nonadherence to this validated protocol, thus comparing a prophylactic and reactive approach to nutrition support in this patient population.

DESIGN

We conducted a prospective comparative cohort study. Patients were observed during routine clinical practice over 2 years.

PARTICIPANTS/SETTING

Patients with head and neck cancer having curative-intent treatment between August 2012 and July 2014 at a tertiary hospital in Queensland, Australia, were included if assessed as high nutrition risk according to the validated protocol (n=130). Patients were grouped according to protocol adherence as to whether they received prophylactic gastrostomy (PEG) per protocol recommendation (prophylactic PEG group, n=69) or not (no PEG group, n=61).

MAIN OUTCOME MEASURES

Primary outcome was percentage weight change during treatment. Secondary outcomes were feeding tube use and hospital admissions.

STATISTICAL ANALYSIS PERFORMED

Fisher's exact, χ², and two sample t tests were performed to determine differences between the groups. Linear and logistic regression were used to examine weight loss and unplanned admissions, respectively.

RESULTS

Patients were 88% male, median age was 59 years, with predominantly stage IV oropharyngeal cancer receiving definitive chemoradiotherapy. Statistically significantly less weight loss in the prophylactic PEG group (7.0% vs 9.0%; P=0.048) and more unplanned admissions in the no PEG group (82% vs 75%; P=0.029). In the no PEG group, 26 patients (43%) required a feeding tube or had ≥10% weight loss.

CONCLUSIONS

Prophylactic gastrostomy improved nutrition outcomes and reduced unplanned hospital admissions. Additional investigation of characteristics of patients with minimal weight loss or feeding tube use could help refine and improve the protocol.

New radiotherapy techniques do not reduce the need for nutrition intervention in patients with head and neck cancer

BACKGROUND/OBJECTIVES

Since 2007, our institution has used validated guidelines for the insertion of proactive gastrostomy feeding tubes in patients with head and neck cancer. Helical intensity-modulated radiotherapy (H-IMRT) delivered by Tomotherapy, is an advanced radiotherapy technique introduced at our centre in 2010. This form of therapy reduces long-term treatment-related toxicity to normal tissues. The aim of this study is to compare weight change and need for tube feeding following H-IMRT (n=53) with patients that would have previously been treated with three-dimensional conformal radiotherapy (n=134).

SUBJECTS/METHODS

Patients with head and neck cancer assessed as high nutritional risk with recommendation for proactive gastrostomy were identified from cohorts from 2007 to 2008 and 2010 to 2011. Retrospective data were collected on clinical factors, weight change from baseline to completion of treatment, incidence of severe weight loss (⩾ 10%) and tube feeding. Statistical analyses to compare outcomes between the two treatments included χ(2)-test, Fisher's exact and two-sample Wilcoxon tests (P<0.05).

RESULTS

The H-IMRT cohort had higher proportions of patients with definitive chemoradiotherapy (P=0.032) and more advanced N stage (P<0.001). Nutrition outcomes were not significantly different between H-IMRT and conformal radiotherapy, respectively: need for proactive gastrostomy (n=49, 92% versus n=115, 86%, P=0.213), median percentage weight change (-7.2% versus -7.3%, P=0.573) and severe weight loss incidence (28% versus 27%, P=0.843).

CONCLUSIONS

Both groups had median weight loss >5% and high incidences of tube feeding and severe weight loss. Nutrition intervention remains critical in this patient population, despite advances in radiotherapy techniques, and no changes to current management are recommended.