RESUMEN

OBJECTIVE: This study aimed to assess reporting quality of machine learning (ML) algorithms in the head and neck oncology literature using the TRIPOD-AI criteria. DATA SOURCES: A comprehensive search was conducted using PubMed, Scopus, Embase, and Cochrane Database of Systematic Reviews, incorporating search terms related to "artificial intelligence," "machine learning," "deep learning," "neural network," and various head and neck neoplasms. REVIEW METHODS: Two independent reviewers analyzed each published study for adherence to the 65-point TRIPOD-AI criteria. Items were classified as "Yes," "No," or "NA" for each publication. The proportion of studies satisfying each TRIPOD-AI criterion was calculated. Additionally, the evidence level for each study was evaluated independently by two reviewers using the Oxford Centre for Evidence-Based Medicine (OCEBM) Levels of Evidence. Discrepancies were reconciled through discussion until consensus was reached. RESULTS: The study highlights the need for improvements in ML algorithm reporting in head and neck oncology. This includes more comprehensive descriptions of datasets, standardization of model performance reporting, and increased sharing of ML models, data, and code with the research community. Adoption of TRIPOD-AI is necessary for achieving standardized ML research reporting in head and neck oncology. CONCLUSION: Current reporting of ML algorithms hinders clinical application, reproducibility, and understanding of the data used for model training. To overcome these limitations and improve patient and clinician trust, ML developers should provide open access to models, code, and source data, fostering iterative progress through community critique, thus enhancing model accuracy and mitigating biases. LEVEL OF EVIDENCE: NA Laryngoscope, 2024.

RESUMEN

BACKGROUND: The management of acute hemorrhage in patients with previously treated head and neck squamous cell carcinoma (HNSCC) is challenging due to the lack of substantial evidence to guide clinical decision making. METHODS: A systematic review and retrospective chart review were performed to identify patients with a history of HNSCC who underwent either primary or adjuvant radiation therapy (RT) and presented with hemorrhagic complications requiring embolization. Patient characteristics, history, presentation, and outcomes were reviewed. RESULTS: The systematic review included a total of 182 patients. Heterogeneity existed in outcomes reporting; 1-year overall survival approached 50%. From the retrospective chart review, 51 patients were included. Median survival time following hemorrhage was 2.2 months (range 1.2-11.4 months). Patients with malignancy at time of hemorrhage were identified as having worse survival. CONCLUSIONS: Acute hemorrhage in patients with a history of previously radiated HNSCC portends a high risk of mortality, with patients with active malignancy representing a worse prognostic group.

RESUMEN

OBJECTIVE: Advanced-stage laryngeal squamous cell carcinoma is treated with primary surgery or chemoradiation. We aim to determine if there are differences in postoperative functional oral intake in primary (PL) versus salvage laryngectomees (SL). STUDY DESIGN: Retrospective cohort study. SETTING: Patients who underwent laryngectomy between 2011 and 2021. METHODS: We examined demographic, diagnostic, treatment, and swallow function data pre- and postoperatively. A follow-up survey was distributed to assess current swallow status. RESULTS: One hundred twenty-five patients were included. Preoperatively, 68.8% of patients reported dysphagia. Median functional oral intake score (FOIS) was 4.0 [interquartile range, IQR: 1.0-6.75]. The SL group had lower preop FOIS [2.0; IQR: 1.0-4.75] that did not reach significance compared to the PL group [4.5; IQR: 1.0-7.0] (P = .052). 73.4% of patients had a feeding tube. The PL group was more likely to have the tube removed [odds ratio, OR: 2.4; confidence interval, CI: 1.0-5.7]. The SL group was more likely to require feeding tube placement more than 6 months postop [OR: 6.9; CI: 1.65-32.6]. SL FOIS scores improved by 3 months postop to 5 (SL ΔFOIS = 3, P = .0150). PL scores improved to 7 [PL ΔFOIS = 2, P = .0005] at 12 to 15 months. Sixty-nine patients were contacted for a follow-up survey and 16 completed this survey. 30.4% patients reported dietary restrictions (mean 4.4 years postop). CONCLUSION: Patients undergoing SL appear to obtain similar swallow outcomes compared to PL at 3 to 6 months postlaryngectomy, but plateau. The PL group continues to improve up to 1 year postoperatively. Fifty percent of patients report on-going dysphagia after 5 years.

Asunto(s)

RESUMEN

OBJECTIVE: To localize structural laryngeal lesions within digital flexible laryngoscopic images and to classify them as benign or suspicious for malignancy using state-of-the-art computer vision detection models. STUDY DESIGN: Cross-sectional diagnostic study SETTING: Tertiary care voice clinic METHODS: Digital stroboscopic videos, demographic and clinical data were collected from patients evaluated for a structural laryngeal lesion. Laryngoscopic images were extracted from videos and manually labeled with bounding boxes encompassing the lesion. Four detection models were employed to simultaneously localize and classify structural laryngeal lesions in laryngoscopic images. Classification accuracy, intersection over union (IoU) and mean average precision (mAP) were evaluated as measures of classification, localization, and overall performance, respectively. RESULTS: In total, 8,172 images from 147 patients were included in the laryngeal image dataset. Classification accuracy was 88.5 for individual laryngeal images and increased to 92.0 when all images belonging to the same sequence (video) were considered. Mean average precision across all four detection models was 50.1 using an IoU threshold of 0.5 to determine successful localization. CONCLUSION: Results of this study showed that deep neural network-based detection models trained using a labeled dataset of digital laryngeal images have the potential to classify structural laryngeal lesions as benign or suspicious for malignancy and to localize them within an image. This approach provides valuable insight into which part of the image was used by the model to determine a diagnosis, allowing clinicians to independently evaluate models' predictions.

Asunto(s)

RESUMEN

BACKGROUND: Several prospective studies report improved outcomes with pretreatment nutrition interventions prior to radiation therapy for head and neck cancer (HNC), but none have assessed similar interventions before surgery for HNC. METHODS: POINT, a pilot randomized controlled trial, was conducted to evaluate a multimodal nutrition intervention. Patients undergoing primary surgery with free flap reconstruction for HNC were randomly assigned to the control arm or a preoperative multimodal nutrition intervention. RESULTS: POINT included 49 patients. Nutrition risk scores did not change significantly for either the intervention or control group. Control patients had a significant decrease in body weight in the preoperative period (p < 0.001). Conversely, weight among intervention patients did not significantly decrease (p = 0.680). The intervention mitigated weight loss in patients with dysphagia (p = 0.001). CONCLUSIONS: Preoperative nutrition optimization shows potential to reduce weight loss normally experienced by patients with head and neck cancer prior to surgical extirpation, especially among those with subjective dysphagia.

Asunto(s)

RESUMEN

Importance: In clinically localized (T1-2) oral cavity squamous cell carcinoma (OCSCC), regional lymph node metastasis is associated with a poor prognosis. Given the high propensity of subclinical nodal disease in these patients, upfront elective neck dissections (END) for patients with clinically node-negative disease are common and associated with better outcomes. Unfortunately, even with this risk-adverse treatment paradigm, disease recurrence still occurs, and our understanding of the factors that modulate this risk and alter survival have yet to be fully elucidated. Objective: To investigate the prognostic value of lymph node yield (LNY), lymph node ratio (LNR), and weighted LNR (wLNR) in patients with clinically node-negative T1-2 OCSCC. Design, Setting, and Participants: In this cohort study, data were collected retrospectively from 7 tertiary care academic medical centers. Overall, 523 patients with cT1-2N0 OCSCC who underwent elective neck dissections after primary surgical extirpation were identified. Exposures: Lymph node yield was defined as the number of lymph nodes recovered from elective neck dissection. Lymph node ratio was defined as the ratio of positive nodes against total LNY. Weighted LNR incorporated information from both LNY and LNR into a single continuous metric. Main Outcomes and Measures: Locoregional control (LRC) and disease-free survival (DFS) were both evaluated using nonparametric Kaplan-Meier estimators and semiparametric Cox regression. Results: On multivariable analysis, LNY less than or equal to 18 lymph nodes was found to be significantly associated with decreased LRC (aHR, 1.53; 95% CI, 1.04-2.24) and DFS (aHR, 1.46; 95% CI, 1.12-1.92) in patients with pN0 disease, but not those with pN-positive disease. Importantly, patients with pN0 disease with LNY less than or equal to 18 and those with pN1 diseasehad nearly identical 5-year LRC (69.7% vs 71.4%) and DFS (58.2% vs 55.7%). For patients with pN-positive disease, LNR greater than 0.06 was significantly associated with decreased LRC (aHR, 2.66; 95% CI, 1.28-5.55) and DFS (aHR, 1.65; 95% CI, 1.07-2.53). Overall, wLNR was a robust prognostic variable across all patients with cN0 disease, regardless of pathologic nodal status. Risk stratification via wLNR thresholds demonstrated greater optimism-corrected concordance compared with American Joint Committee on Cancer (AJCC) 8th edition nodal staging for both LRC (0.61 vs 0.57) and DFS (0.61 vs 0.58). Conclusions and Relevance: Movement toward more robust metrics that incorporate quantitative measures of neck dissection quality and regional disease burden, such as wLNR, could greatly augment prognostication in cT1-2N0 OCSCC by providing more reliable and accurate risk estimations.

Asunto(s)

RESUMEN

Importance: Given that early-stage oral cavity squamous cell carcinoma (OCSCC) has a high propensity for subclinical nodal metastasis, elective neck dissection has become standard practice for many patients with clinically negative nodes. Unfortunately, for most patients without regional metastasis, this risk-averse treatment paradigm results in unnecessary morbidity. Objectives: To develop and validate predictive models of occult nodal metastasis from clinicopathological variables that were available after surgical extirpation of the primary tumor and to compare predictive performance against depth of invasion (DOI), the currently accepted standard. Design, Setting, and Participants: This diagnostic modeling study collected clinicopathological variables retrospectively from 7 tertiary care academic medical centers across the US. Participants included adult patients with early-stage OCSCC without nodal involvement who underwent primary surgical extirpation with or without upfront elective neck dissection. These patients were initially evaluated between January 1, 2000, and December 31, 2019. Exposures: Largest tumor dimension, tumor thickness, DOI, margin status, lymphovascular invasion, perineural invasion, muscle invasion, submucosal invasion, dysplasia, histological grade, anatomical subsite, age, sex, smoking history, race and ethnicity, and body mass index (calculated as weight in kilograms divided by height in meters squared). Main Outcomes and Measures: Occult nodal metastasis identified either at the time of elective neck dissection or regional recurrence within 2 years of initial surgery. Results: Of the 634 included patients (mean [SD] age, 61.2 [13.6] years; 344 men [54.3%]), 114 (18.0%) had occult nodal metastasis. Patients with occult nodal metastasis had a higher frequency of lymphovascular invasion (26.3% vs 8.1%; P < .001), perineural invasion (40.4% vs 18.5%; P < .001), and margin involvement by invasive tumor (12.3% vs 6.3%; P = .046) compared with those without pathological lymph node metastasis. In addition, patients with vs those without occult nodal metastasis had a higher frequency of poorly differentiated primary tumor (20.2% vs 6.2%; P < .001) and greater DOI (7.0 vs 5.4 mm; P < .001). A predictive model that was built with XGBoost architecture outperformed the commonly used DOI threshold of 4 mm, achieving an area under the curve of 0.84 (95% CI, 0.80-0.88) vs 0.62 (95% CI, 0.57-0.67) with DOI. This model had a sensitivity of 91.7%, specificity of 72.6%, positive predictive value of 39.3%, and negative predictive value of 97.8%. Conclusions and Relevance: Results of this study showed that machine learning models that were developed from multi-institutional clinicopathological data have the potential to not only reduce the number of pathologically node-negative neck dissections but also accurately identify patients with early OCSCC who are at highest risk for nodal metastases.

Asunto(s)

RESUMEN

BACKGROUND: The specificity of sentinel lymph node biopsy (SLNB) for detecting lymph node metastasis in head and neck melanoma (HNM) is low under current National Comprehensive Cancer Network (NCCN) treatment guidelines. METHODS: Multiple machine learning (ML) algorithms were developed to identify HNM patients at very low risk of occult nodal metastasis using National Cancer Database (NCDB) data from 8466 clinically node negative HNM patients who underwent SLNB. SLNB performance under NCCN guidelines and ML algorithm recommendations was compared on independent test data from the NCDB (n = 2117) and an academic medical center (n = 96). RESULTS: The top-performing ML algorithm (AUC = 0.734) recommendations obtained significantly higher specificity compared to the NCCN guidelines in both internal (25.8% vs. 11.3%, p < 0.001) and external test populations (30.1% vs. 7.1%, p < 0.001), while achieving sensitivity >97%. CONCLUSION: Machine learning can identify clinically node negative HNM patients at very low risk of nodal metastasis, who may not benefit from SLNB.

Asunto(s)

RESUMEN

This case report describes a child who developed Pott's puffy tumor and was treated at the Children's Mercy Hospital in Kansas City. In addition to a discussion of a case, a review of the literature was completed on this topic describing the typical embryology and development of the frontal sinus, and the epidemiology, diagnosis, and treatment of Pott's puffy tumor. The patient was a 23-month-old boy who developed Pott's puffy tumor after recovery from influenza. The patient presented to the hospital with progressing edema of the unilateral eye that spread bilaterally within a few days. A CT scan demonstrated pansinusitis, developed frontal sinuses, right periorbital cellulitis, and medial forehead subperiosteal abscess. Functional endoscopic sinus surgery and transcutaneous abscess drainage were urgently performed and the patient made a full recovery following a course of ertapenem and levofloxacin. The presence of a developed frontal sinus in a 23-month-old is an unexpected radiologic finding. This case represents the youngest patient reported in the literature to develop this rare complication of frontal sinusitis.

Asunto(s)

RESUMEN

OBJECTIVE: Complications associated with intracranial vault compromise can be neurologically and systemically devastating. Primary and secondary repair of these deficits require an air and watertight barrier between the intracranial and extracranial environments. This study evaluated the outcomes and utility of using intracranial free tissue transfer as both primary and salvage surgical repair of reconstruction. METHODS: A retrospective review was performed of all subjects who underwent intracranial free tissue transfer as primary or salvage repair. RESULTS: A total of 13 intracranial free tissue transfers were performed on 11 subjects: osteocutaneous radial forearm free flaps (n = 6), partial myofascial rectus abdominis flaps (n = 5), temporoparietal fascia flap (n = 1), and serratus anterior myofascial flap (n = 1). Primary reconstruction was performed on 4 subjects with the remaining being salvage repair. Indications for surgery included neoplasm (n = 6 of 11), ballistic trauma (n = 3 of 11), motor vehicle accident (n = 1 of 11), and infection (n = 1 of 11). Three subjects required additional surgical repair for CSF leak and pneumocephalus, with 2 subjects requiring an additional free tissue transfer at a different site. CONCLUSION: In our experience, free tissue transfer is an effective primary and salvage surgical technique in the reconstruction of complex intracranial problems.

Asunto(s)

RESUMEN

OBJECTIVES: (1) Identify anatomic contributions to chronic rhinosinusitis (CRS) necessitating revision endoscopic sinus surgery (RESS). (2) Create a clinical acronym to guide imaging review prior to RESS that addresses pertinent sites of disease and potential sites of surgical morbidity. DATA SOURCES: Ovid MEDLINE, Embase and Medline via Embase.com, Web of Science Core Collection, Cochrane Central Register of Controlled Trials (CENTRAL), and Google Scholar. REVIEW METHODS: Systematic search was performed using a combination of standardized terms and keywords. Studies were included if they investigated anatomic contributions to persistent CRS requiring RESS or the relationship between anatomic landmarks and surgical morbidity. Identified studies were screened by title/abstract, followed by full-text review. Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines were strictly followed. RESULTS: In total, 599 articles met screening criteria, 89 were eligible for full-text review, and 27 studies were included in the final review. The identified anatomic sites of interests are broad; the most frequently cited anatomic region was retained anterior ethmoid cells (22/27 studies), followed by posterior ethmoid cells (14/27 studies). Using the consolidated information, a clinical acronym, REVISIONS, was created: Residual uncinate, Ethmoid cells (agger, Haller, supraorbital), Vessels (anterior and posterior ethmoid), Infundibulum, Septal deviation, I (eye) compartment, Onodi cell, Natural os, and Skull base slope and integrity. CONCLUSIONS: The REVISIONS acronym was developed as a tool to distill the unique anatomic contributions of primary endoscopic sinus surgery failure into a format that can be easily incorporated in preoperative radiologic review and surgical planning to optimize outcomes and minimize complications.

Asunto(s)

RESUMEN

BACKGROUND: Historical concerns over bone resorption and malunion of the osteocutaneous radial forearm free flap (OCRFFF) limited its widespread adoption for head and neck reconstruction, despite lack of outcomes data evaluating this notion. METHODS: A retrospective cohort study was performed including patients 18 years or older who underwent reconstruction of the mandible using an OCRFFF. Linear modeling and logistic regression were used to evaluate the change in bone volume and union over time. RESULTS: One hundred and twenty-one patients were included in the study. A mixed effects linear model incorporating age, sex, treatment type, and number of bone segments did not demonstrate a significant loss of bone volume over time. A logistic regression model identified lack of adjuvant treatment and time to be significantly associated with complete union. CONCLUSION: This study supports that the OCRFFF is a stable form of osseus reconstruction for defects of the head and neck.

Asunto(s)

RESUMEN

OBJECTIVES: Alveolar soft part sarcoma is a rare subset of soft tissue sarcomas, typically presenting in subjects 15 to 35 years of age. Usual presentation sites are the trunk, extremities, and the head and neck. Subjects younger than 5 years are rarely affected. METHODS: In this retrospective case report, we present a 16-month old male with a rapidly growing soft tissue mass of the anterior and posterior tongue, found to be alveolar soft part sarcoma. RESULTS: The subject was treated with primary surgical resection and the resulting defect was reconstructed with a radial forearm free flap. CONCLUSIONS: To our knowledge, this is the youngest subject to have been diagnosed with alveolar soft part sarcoma. Surgical extirpation and microvascular reconstruction were successful, and the patient remains disease free 4 years post-operatively.

Asunto(s)

RESUMEN

OBJECTIVES: This study seeks to (1) demonstrate how machine learning (ML) can be used for prediction modeling by predicting the treatment patients with T1-2, N0-N1 oropharyngeal squamous cell carcinoma (OPSCC) receive and (2) assess the impact patient, socioeconomic, regional, and institutional factors have in the treatment of this population. METHODS: A retrospective cohort of adults diagnosed with T1-2, N0-N1 OPSCC from 2004 to 2013 was obtained using the National Cancer Database. The data was split into 80/20 distribution for training and testing, respectively. Various ML algorithms were explored for development. Area under the curve (AUC), accuracy, precision, and recall were calculated for the final model. RESULTS: Among the 19,111 patients in the study, the mean (standard deviation) age was 61.3 (10.8) years, 14,034 (73%) were male, and 17,292 (91%) were white. Surgery was the primary treatment in 9,533 (50%) cases and radiation in 9,578 (50%) cases. The model heavily utilized T-stage, primary site, N-stage, grade, and type of treatment facility to predict the primary treatment modality. The final model yielded an AUC of 78% (95% CI, 77-79%), accuracy of 71%, precision of 72%, and recall of 71%. CONCLUSION: This study created a ML model utilizing clinical variables to predict primary treatment modality for T1-2, N0-N1 OPSCC. This study demonstrates how ML can be used for prediction modeling while also highlighting that tumor and facility realted variables impact the decision making process on a national level.

Asunto(s)

RESUMEN

OBJECTIVE: [1] review all studies utilizing SDM in the treatment of chronic rhinosinusitis (CRS) [2], increase awareness of otolaryngologists to shared decision-making, and [3] provide a framework for its incorporation into research and clinical practice. METHODS: systematic search was performed in November 2019 using PubMed/MEDLINE 1947-, CINAHL Complete 1937-, the Cochrane Library, ClinicalTrials.gov, and Web of Science Core Collection (SCI-EXPANDED, SSCI, A&HCI, ESCI) 1900-. All databases were searched from their inception through the date of search. Studies were eligible if they involved a discussion of SDM in the management of CRS. Studies were excluded if they lacked original patient data or outcomes of interest. Identified studies were screened by title/abstract, followed by full-text review. PRISMA guidelines were strictly followed. RESULTS: in total, 416 articles met screening criteria. Six were eligible for full text review. Only one study - an expert panel of the framework for the presurgical treatment of CRS - pertained to SDM. While this study mentions that SDM is a critically important piece to optimize care quality, it does not directly investigate the effects of SDM in CRS. CONCLUSION: this review represents a significant negative study that identifies a clear gap in the rhinology literature. Despite the recognized importance of SDM, there have been no interventional studies in the literature to investigate SDM in CRS. This review highlights the need for exploring the role of SDM in rhinological surgery, outlines an overview of SDM and its impact on patient outcomes, and provides a proposed framework for incorporating SDM in research and clinical practice.

Asunto(s)

RESUMEN

BACKGROUND: Machine learning (ML) algorithms may predict patients who will require salvage total laryngectomy (STL) after primary radiotherapy with or without chemotherapy for laryngeal squamous cell carcinoma (SCC). METHODS: Patients treated for T1-T3a laryngeal SCC were identified from the National Cancer Database. Multiple ML algorithms were trained to predict which patients would go on to require STL after primary nonsurgical treatment. RESULTS: A total of 16 440 cases were included. The best classification performance was achieved with a gradient boosting algorithm, which achieved accuracy of 76.0% (95% CI 74.5-77.5) and area under the curve = 0.762. The most important variables used to construct the model were distance from residence to treating facility and days from diagnosis to start of treatment. CONCLUSION: We can identify patients likely to fail primary radiotherapy with or without chemotherapy and who will go on to require STL by applying ML techniques and argue for high-quality, multidisciplinary regionalized care.

Asunto(s)

RESUMEN

Importance: Predicting survival of oral squamous cell carcinoma through the use of prediction modeling has been underused, and the development of prediction models would augment clinicians' ability to provide absolute risk estimates for individual patients. Objectives: To develop a prediction model using machine learning for 5-year overall survival among patients with oral squamous cell carcinoma and compare this model with a prediction model created from the TNM (Tumor, Node, Metastasis) clinical and pathologic stage. Design, Setting, and Participants: A retrospective cohort study was conducted of 33 065 patients with oral squamous cell carcinoma from the National Cancer Data Base between January 1, 2004, and December 31, 2011. Patients were excluded if the treatment was considered palliative, staging demonstrated T0 or Tis, or survival or staging data were missing. Patient, tumor, treatment, and outcome information were obtained from the National Cancer Data Base. The data were split into a distribution of 80% for training and 20% for testing. The model was created using 2-class decision forest architecture. Permutation feature importance scores were used to determine the variables that were used in the model's prediction and their order of significance. Statistical analysis was conducted from August 1, 2018, to January 10, 2019. Main Outcomes and Measures: Ability to predict 5-year overall survival assessed through area under the curve, accuracy, precision, and recall. Results: Among the 33 065 patients in the study, the mean (SD) age was 64.6 (14.0) years, 19 791 were men (59.9%), 13 274 were women (40.1%), and 29 783 (90.1%) were white. At 60 months, there were 16 745 deaths (50.6%). The median time of follow-up was 56.8 months (range, 0-155.6 months). Age, pathologic T stage, positive margins at the time of surgery, lymph node size, and institutional identification were identified among the most significant variables. The calculated area under the curve for this machine learning model was 0.80 (95% CI, 0.79-0.81), accuracy was 71%, precision was 71%, and recall was 68%. In comparison, the calculated area under the curve of the TNM staging system was 0.68 (95% CI, 0.67-0.70), accuracy was 65%, precision was 69%, and recall was 52%. Conclusions and Relevance: Using machine learning algorithms, a prediction model was created based on patient social, demographic, clinical, and pathologic features. The developed prediction model proved to be better than a prediction model that exclusively used TNM pathologic and clinical stage according to all performance metrics. This study highlights the role that machine learning may play in individual patient risk estimation in the era of big data.

Asunto(s)

RESUMEN

OBJECTIVES: To develop and validate an algorithm to predict occult nodal metastasis in clinically node negative oral cavity squamous cell carcinoma (OCSCC) using machine learning. To compare algorithm performance to a model based on tumor depth of invasion (DOI). MATERIALS AND METHODS: Patients who underwent primary tumor extirpation and elective neck dissection from 2007 to 2013 for clinical T1-2N0 OCSCC were identified from the National Cancer Database (NCDB). Multiple machine learning algorithms were developed to predict pathologic nodal metastasis using clinicopathologic data from 782 patients.The algorithm was internally validated using test data from 654 patients in NCDB and was then externally validated using data from 71 patients treated at a single academic institution. Performance was measured using area under the receiver operating characteristic (ROC) curve (AUC). Machine learning and DOI model performance were compared using Delong's test for two correlated ROC curves. RESULTS: The best classification performance was achieved with a decision forest algorithm (AUC = 0.840). When applied to the single-institution data, the predictive performance of machine learning exceeded that of the DOI model (AUC = 0.657, p = 0.007). Compared to the DOI model, machine learning reduced the number of neck dissections recommended while simultaneously improving sensitivity and specificity. CONCLUSION: Machine learning improves prediction of pathologic nodal metastasis in patients with clinical T1-2N0 OCSCC compared to methods based on DOI. Improved predictive algorithms are needed to ensure that patients with occult nodal disease are adequately treated while avoiding the cost and morbidity of neck dissection in patients without pathologic nodal disease.

Asunto(s)

RESUMEN

The optimal management of human papillomavirus (HPV)-positive oropharyngeal squamous cell carcinoma (OPSCC) with primary surgical versus non-surgical treatment is unclear. The objective of this systematic review was to evaluate the literature and compare survival for primary surgical versus non-surgical treatment of HPV-positive OPSCC. We performed a comprehensive literature search of multiple electronic databases for relevant articles up to February, 2017. Studies reporting mortality or hazard ratio (HR) for overall survival (OS) in primary HPV-positive OPSCC patients were eligible. Seventy-three articles were eligible, of which 66 included single-modality (19 surgical, 47 non-surgical), and 7 included both surgical and non-surgical modalities. There were no randomized studies comparing outcomes between both modalities. In a meta-analysis of both-modality studies, OS with surgical treatment was not significantly different from non-surgical treatment (pooled HR 1.12; 95% CI: 0.35, 3.57). There was significant heterogeneity between studies (I2 = 82.4%). Among single-modality studies, the mortality rate was lower with surgical [pooled proportion 0.15 (95% CI: 0.09, 0.21)] versus non-surgical treatment [0.20 (95% CI:0.15, 0.24)]. In a subgroup analysis, OS was higher for HPV-positive versus HPV-negative OPSCC, irrespective of the treatment modality. We conclude that there is an absence of high-quality studies that compare survival for HPV-positive OPSCC treated with primary surgical versus non-surgical approach. The available data suggest no statistical or clinically meaningful difference in survival between the two approaches. HPV-positivity was a key prognostic factor irrespective of treatment modality. Further high-quality studies with consistent data reporting are needed to inform the choice for optimal treatment modality for HPV-positive OPSCC.

Asunto(s)

RESUMEN

Importance: The tinnitus research literature suggests that N-methyl-d-aspartate (NMDA) receptor antagonists may be useful in reducing tinnitus. Nitrous oxide, a member of the NMDA receptor antagonist class, is a widely used general anesthetic and sedative with a proven safety record. Objective: To investigate whether nitrous oxide can reduce bothersome tinnitus. Design, Setting, and Participants: Randomized, placebo-controlled crossover trial conducted between October 15, 2016, and June 22, 2017. Participants attended 2 interventional sessions separated by at least 14 days and were randomized to receive either placebo first or nitrous oxide first. Participants were followed up through completion of the second arm of the study. The setting was a clinical research unit at an academic medical center. Adults aged 18 to 65 years with subjective, idiopathic, nonpulsatile bothersome tinnitus of 6 months' duration or longer were recruited from 2 clinical research databases. Seventy-one individuals were screened, of whom 40 were enrolled. Of those enrolled, 37 participants completed all components of the study. Interventions: The placebo session consisted of 50% nitrogen and 50% oxygen inhaled for 40 minutes, and the treatment session consisted of 50% nitrous oxide and 50% oxygen inhaled for 40 minutes. Main Outcomes and Measures: Tinnitus was assessed before and after intervention, with the change in the Tinnitus Functional Index (TFI) as the primary outcome measure. Secondary outcome measures included the Patients' Global Impression of Change score and the change in the Global Bothersome Scale score. Results: Among 40 participants in this intent-to-treat randomized clinical trial with 20 participants randomly assigned to each group, the mean (SD) age of participants was 52.9 (11.1) years, with equal numbers of male and female participants. The TFI after intervention was a mean (SD) of 1.8 (8.8) points lower than before intervention in the placebo arm and a mean (SD) of 2.5 (11.0) points lower than before intervention in the nitrous oxide arm. The within-participant mean difference in the change in the TFI of the placebo arm compared with the nitrous oxide arm was -1.1 points (95% CI, -5.6 to 3.4 points). The difference between the placebo and nitrous oxide arms was neither clinically meaningful nor statistically significant. Conclusions and Relevance: Nitrous oxide was no more effective than placebo for the treatment of subjective, idiopathic tinnitus. Trial Registration: ClinicalTrials.gov identifier: NCT03365011.

Asunto(s)