Machine Learning to Predict Treatment in Oropharyngeal Squamous Cell Carcinoma.

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.

Pott's puffy tumor in a 23-month-old: Youngest known case of a rare disease.

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.

Machine learning directed sentinel lymph node biopsy in cutaneous head and neck melanoma.

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.

Microsurgical Management of Early Onset Alveolar Soft Part Sarcoma of the Oral Tongue: Case Report and Review of the Literature.

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.

Outcomes and Utility of Intracranial Free Tissue Transfer.

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.

Creation of a Novel Preoperative Imaging Review Acronym to Aid in Revision Endoscopic Sinus Surgery.

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.

Rates of bone reabsorption and union in mandibular reconstruction using the osteocutaneous radial forearm free flap.

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.

Evaluation of the literature surrounding shared decision-making in elective rhinological surgery: A scoping review.

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.

Predicting salvage laryngectomy in patients treated with primary nonsurgical therapy for laryngeal squamous cell carcinoma using machine learning.

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.

Development and Assessment of a Machine Learning Model to Help Predict Survival Among Patients With Oral Squamous Cell Carcinoma.

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.

Survival for HPV-positive oropharyngeal squamous cell carcinoma with surgical versus non-surgical treatment approach: A systematic review and meta-analysis.

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.

A methodological assessment of studies that use voxel-based morphometry to study neural changes in tinnitus patients.

BACKGROUND: The scientific understanding of tinnitus and its etiology has transitioned from thinking of tinnitus as solely a peripheral auditory problem to an increasing awareness that cortical networks may play a critical role in tinnitus percept or bother. With this change, studies that seek to use structural brain imaging techniques to better characterize tinnitus patients have become more common. These studies include using voxel-based morphometry (VBM) to determine if there are differences in regional gray matter volume in individuals who suffer from tinnitus and those who do not. However, studies using VBM in patients with tinnitus have produced inconsistent and sometimes contradictory results. OBJECTIVE: This paper is a systematic review of all of the studies to date that have used VBM to study regional gray matter volume in people with tinnitus, and explores ways in which methodological differences in these studies may account for their heterogeneous results. We also aim to provide guidance on how to conduct future studies using VBM to produce more reproducible results to further our understanding of disease processes such as tinnitus. METHODS: Studies about tinnitus and VBM were searched for using PubMed and Embase. These returned 15 and 25 results respectively. Of these, nine met the study criteria and were included for review. An additional 5 studies were identified in the literature as pertinent to the topic at hand and were added to the review, for a total of 13 studies. RESULTS: There was significant heterogeneity among the studies in several areas, including inclusion and exclusion criteria, software programs, and statistical analysis. We were not able to find publicly shared data or code for any study. DISCUSSION: The differences in study design, software analysis, and statistical methodology make direct comparisons between the different studies difficult. Especially problematic are the differences in the inclusion and exclusion criteria of the study, and the statistical design of the studies, both of which could radically alter findings. Thus, heterogeneity has complicated efforts to explore the etiology of tinnitus using structural MRI. CONCLUSION: There is a pressing need to standardize the use of VBM when evaluating tinnitus patients. While some heterogeneity is expected given the rapid advances in the field, more can be done to ensure that there is internal validity between studies.

Reporting of Effect Size and Confidence Intervals in JAMA Otolaryngology-Head & Neck Surgery.

Importance: Effect sizes and confidence intervals (CIs) are critical for the interpretation of the results for any outcome of interest. Objective: To evaluate the frequency of reporting effect sizes and CIs in the results of analytical studies. Design, Setting, and Participants: Descriptive review of analytical studies published from January 2012 to December 2015 in JAMA Otolaryngology-Head & Neck Surgery. Methods: A random sample of 121 articles was reviewed in this study. Descriptive studies were excluded from the analysis. Seven independent reviewers participated in the evaluation of the articles, with 2 reviewers assigned per article. The review process was standardized for each article; the Methods and Results sections were reviewed for the outcomes of interest. Descriptive statistics for each outcome were calculated and reported accordingly. Main Outcomes and Measures: Primary outcomes of interest included the presence of effect size and associated CIs. Secondary outcomes of interest included a priori descriptions of statistical methodology, power analysis, and expectation of effect size. Results: There were 107 articles included for analysis. The majority of the articles were retrospective cohort studies (n = 36 [36%]) followed by cross-sectional studies (n = 18 [17%]). A total of 58 articles (55%) reported an effect size for an outcome of interest. The most common effect size used was difference of mean, followed by odds ratio and correlation coefficient, which were reported 17 (16%), 15 (13%), and 12 times (11%), respectively. Confidence intervals were associated with 29 of these effect sizes (27%), and 9 of these articles (8%) included interpretation of the CI. A description of the statistical methodology was provided in 97 articles (91%), while 5 (5%) provided an a priori power analysis and 8 (7%) provided a description of expected effect size finding. Conclusions and Relevance: Improving results reporting is necessary to enhance the reader's ability to interpret the results of any given study. This can only be achieved through increasing the reporting of effect sizes and CIs rather than relying on P values for both statistical significance and clinically meaningful results.