Clinical presentation and outcome of human papillomavirus-positive nasopharyngeal carcinoma in a North American cohort.

BACKGROUND: The objective of this study was to describe the clinical presentation and outcomes of human papillomavirus (HPV)-positive nasopharyngeal cancer (NPC) versus Epstein-Barr virus (EBV)-positive NPC and HPV-positive oropharyngeal cancer (OPC). METHODS: Clinical characteristics and presenting signs/symptoms were compared between patients who had viral-related NPC versus viral-related OPC treated with intensity-modulated radiotherapy from 2005 to 2020 and who were matched 1:1 (by tumor and lymph node categories, smoking, age, sex, histology, and year of diagnosis). Locoregional control (LRC), distant control (DC), and overall survival (OS) were compared using the 2005-2018 cohort to maintain 2 years of minimum follow-up. Multivariable analysis was used to evaluate the cohort effect. RESULTS: Similar to HPV-positive OPC (n = 1531), HPV-positive NPC (n = 29) occurred mostly in White patients compared with EBV-positive NPC (n = 422; 86% vs. 15%; p < .001). Primary tumor volumes were larger in HPV-positive NPC versus EBV-positive NPC (median volume, 51 vs. 23 cm3 ; p = .002), with marginally more Level IB nodal involvement. More patients with HPV-positive NPC complained of local pain (38% vs. 3%; p = .002). The median follow-up for the 2005-2018 cohort was 5.3 years. Patients who had HPV-positive NPC (n = 20) had rates of 3-year LRC (95% vs. 90%; p = .360), DC (75% vs. 87%; p = .188), and OS (84% vs. 89%; p = .311) similar to the rates in those who had EBV-positive NPC (n = 374). Patients who had HPV-positive NPC also had rates of LRC (95% vs. 94%; p = .709) and OS (84% vs. 87%; p = .440) similar to the rates in those who had HPV-positive OPC (n = 1287). The DC rate was lower in patients who had HPV-positive disease (75% vs. 90%; p = .046), but the difference became nonsignificant (p = .220) when the analysis was adjusted for tumor and lymph node categories, smoking, and chemotherapy. CONCLUSIONS: HPV-positive NPC and EBV-positive NPC seem to be mutually exclusive diseases. Patients who have HPV-positive NPC have greater local symptom burden and larger primary tumors but have similar outcomes compared with patients who have EBV-positive NPC or HPV-positive OPC.

Transitions in oral and gut microbiome of HPV+ oropharyngeal squamous cell carcinoma following definitive chemoradiotherapy (ROMA LA-OPSCC study).

BACKGROUND: Oral and gut microbiomes have emerged as potential biomarkers in cancer. We characterised the oral and gut microbiomes in a prospective observational cohort of HPV+ oropharyngeal squamous cell carcinoma (OPSCC) patients and evaluated the impact of chemoradiotherapy (CRT). METHODS: Saliva, oropharyngeal swabs over the tumour site and stool were collected at baseline and post-CRT. 16S RNA and shotgun metagenomic sequencing were used to generate taxonomic profiles, including relative abundance (RA), bacterial density, α-diversity and ß-diversity. RESULTS: A total of 132 samples from 22 patients were analysed. Baseline saliva and swabs had similar taxonomic composition (R2 = 0.006; p = 0.827). Oropharyngeal swabs and stool taxonomic composition varied significantly by stage, with increased oral RA of Fusobacterium nucleatum observed in stage III disease (p < 0.05). CRT significantly reduced the species richness and increased the RA of gut-associated taxa in oropharyngeal swabs (p < 0.05), while it had no effect in stool samples. These findings remained significant when adjusted by stage, smoking status and antibiotic use. CONCLUSIONS: Baseline oral and gut microbiomes differ by stage in this HPV+ cohort. CRT caused a shift towards a gut-like microbiome composition in oropharyngeal swabs. Stage-specific features and the transitions in oral microbiome might have prognostic and therapeutic implications.

Awareness of the Harms of Continued Smoking Among Cancer Survivors.

BACKGROUND: Smoking cessation is an integral part of cancer survivorship. To help improve survivorship education, clinicians need an understanding of patient awareness of the harms of continued smoking. METHODS: Cancer survivors from Princess Margaret Cancer Centre (Toronto, ON) were surveyed on their awareness of the harms of continued smoking on cancer-related outcomes. Multivariable logistic regression models assessed factors associated with awareness and whether awareness was associated with subsequent cessation among smokers at diagnosis. RESULTS: Among 1118 patients, 23% were current smokers pre-diagnosis and 54% subsequently quit; 25% had lung and 30% head and neck cancers. Many patients reported being unaware that continued smoking results in greater cancer surgical complications (53%), increased radiation side effects (62%), decreased quality of life during chemotherapy (51%), decreased chemotherapy or radiation efficacy (57%), increased risk of death (40%), and increased development of second primaries (38%). Being a current smoker was associated with greater lack of awareness of some of these smoking harms (aORs = 1.53-2.20, P < 0.001-0.02), as was exposure to any second-hand smoke (aORs = 1.45-1.53, P = 0.006-0.04) and being diagnosed with early stage cancer (aORs = 1.38-2.31, P < 0.001-0.06). Among current smokers, those with fewer pack-years, being treated for cure, or had a non-tobacco-related cancer were more likely unaware. Awareness that continued tobacco use worsen quality of life after chemotherapy was associated with subsequent cessation (aOR = 2.26, P = 0.006). CONCLUSIONS: Many cancer survivors are unaware that continued smoking can negatively impact cancer-related outcomes. The impact of educating patients about the potential harms of continued smoking when discussing treatment plans should be further evaluated.

Development and Evaluation of Patient Education Materials for Elderly Lung Cancer Patients.

Patients treated for lung cancer are often elderly presenting a unique challenge for developing patient education materials. This study developed and evaluated a patient education pamphlet on lung stereotactic body radiotherapy (SBRT) designed specifically for an elderly population. The SBRT pamphlet was developed using a participatory design involving a convenience sample of patients. This prospective study assessed patient's opinions of pamphlet effectiveness through self-report questionnaires. The pamphlet was deemed "effective" if patients rated 16/18 evaluation statements as "strongly agree" or "agree." Demographic data and health literacy (Rapid Estimate of Adult Literacy in Medicine short-form (REALM-SF)) were also assessed. Patient opinion of pamphlet "effectiveness" was compared between patients with REALM-SF scores of 7 versus <7 using Fisher's exact test. The overall EQ-5D-5L score was compared for patients who did and did not find the pamphlet effective using the Wilcoxon-Mann-Whitney test. Thirty-seven patients participated. The median age was 76 years (range 56-93) and 22 patients (59 %) had ≤high school education. Most patients preferred to have verbal (65 %) or written (78 %) educational materials as opposed to online information or educational classes. Thirty-two patients (86 %) rated the pamphlet as effective. The proportion of patients who found the pamphlet effective was 85.7 versus 86.7 % (p = 1.00) in those with REALM 7 versus <7. The mean EQ-5D score was 67.5 (SD 19.1) versus 71.8 (SD 8.7) (p = 0.84) in those who found the pamphlet effective versus not. Participatory design is an effective method for developing education materials for challenging patient groups such as elderly patients. Despite advanced age and comorbidity, this patient group had adequate health literacy.

RADIATION-INDUCED MUCOSITIS IN PATIENTS WITH HEAD AND NECK CANCER: SHOULD THE SIGNS OR THE SYMPTOMS BE MEASURED?

OBJECTIVE: To improve understanding of how patient-reported outcomes following radiation therapy for head and neck cancer may be influenced by factors beyond the local effects of the radiotherapy. METHODS: Initially, 50 patients with head and neck cancer who were scheduled to undergo radiation therapy consented to participate in this prospective observational study. The participants underwent an oral examination before commencement of therapy and twice weekly over the therapy period. The 33 participants who finished the therapy underwent one more examination 4 to 6 weeks after its completion. At each session, clinical signs of oral mucositis were recorded with clinician-based scoring tools, and participants completed a questionnaire based on a visual analogue scale to record the perceived degree of impairment of common oral functions caused by oral mucositis. The strength of the correlation between these signs and symptoms at various points throughout the study period was appraised using a linear mixed model with robust repeated measures. The study participants with the most extensive manifestations of oral mucositis but only minor pain and limited adverse effects on oral functions (n=6) were contrasted with those who had limited mucositis but more severe pain and adverse effects (n=7). In addition, study participants with poor to moderate correlations between signs and symptoms (n=5) were contrasted with those who had very good correlations (n=10). Simple bivariate tests were used for these comparisons. RESULTS: Correlations between various signs and symptoms at all time points varied markedly at the individual level. The characteristics of study participants in the 2 subcohorts defined by poor to moderate and very good correlations between signs and symptoms were comparable, except perhaps in terms of age (p<0.05, t test). Similarly, the participants in the 2 subcohorts defined by high manifestation with minor complaints and vice versa did not differ with regard to the variables recorded. CONCLUSION: Patients with head and neck cancer often report adverse effects of radiation-related oral mucositis on daily oral functions that are discordant with objective clinical findings. Patient-reported outcomes should be included in any interventional studies of oral mucositis, and trends over time should be analyzed within individuals, rather than between individuals.

Predictors of High eHealth Literacy in Primary Lung Cancer Survivors.

Lung cancer survivors are likely to have low health literacy which is an independent risk factor for poorer health outcomes. The eHealth literacy in lung cancer survivors has not been reported. The purposes of this study were to determine self-perceived eHealth literacy levels in lung cancer survivors and to explore predictors of higher eHealth literacy. A cross-sectional study was conducted at the Princess Margaret Cancer Centre in Toronto, Canada. Survivors completed a survey that collected demographic, self-perceived eHealth literacy (using the eHealth Literacy Scale), and quality of life information. Tumor and treatment details were extracted from medical records. Demographic data was summarized using descriptive statistics and compared against those with high and low eHealth literacy using Fisher's exact test. Eighty-three survivors were enrolled over 7 months. Median age was 71 years (range 44-89); 41 survivors (49%) were male. Forty-six (55%) survivors had some college education or higher. Most had access to eResources (78%) via computer, Internet, or smartphone. Fifty-seven (69%) scored 5 or greater (7=excellent) on the overall health scale. Twenty-eight (33.7%) perceived themselves to have high eHealth literacy. There was no statistically significant correlation between eHealth literacy groups and age (p=1.00), gender (p=0.82), living situation (p=1.00), overall health (p=1.00), overall quality of life (QoL) (p=1.00), or histology (p=0.74). High eHealth literacy correlated with the level of education received (p=0.003) and access to eResources (p=0.004). The self-perceived eHealth literacy of lung cancer survivors is generally low.

Exploring the Language Used to Describe Older Patients at Multidisciplinary Cancer Conferences.

Older adults with cancer often present with distinct complexities that complicate their care, yet the language used to discuss their management at multidisciplinary cancer conferences (MCCs) remains poorly understood. A mixed methods study was conducted at a tertiary cancer centre in Toronto, Canada, where MCCs spanning five tumour sites were attended over six months. For presentations pertaining to a patient aged 75 or older, a standardized data collection form was used to record their demographic, cancer-related, and non-cancer-related information, as well as the presenter's specialty and training level. Descriptive statistics and thematic analysis were employed to explore MCC depictions of older patients (n = 75). Frailty status was explicitly mentioned in 20.0% of presentations, but discussions more frequently referenced comorbidity burden (50.7%), age (33.3%), and projected treatment tolerance (30.7%) as surrogate measures. None of the presentations included mentions of formal geriatric assessment (GA) or validated frailty tools; instead, presenters tended to feature select GA domains and subjective descriptions of appearance ("looks to be fit") or overall health ("relatively healthy"). In general, MCCs appeared to rely on age-focused language that may perpetuate ageism. Further work is needed to investigate how frailty and geriatric considerations can be objectively incorporated into discussions in geriatric oncology.

RADCURE: An open-source head and neck cancer CT dataset for clinical radiation therapy insights.

PURPOSE: This manuscript presents RADCURE, one of the most extensive head and neck cancer (HNC) imaging datasets accessible to the public. Initially collected for clinical radiation therapy (RT) treatment planning, this dataset has been retrospectively reconstructed for use in imaging research. ACQUISITION AND VALIDATION METHODS: RADCURE encompasses data from 3346 patients, featuring computed tomography (CT) RT simulation images with corresponding target and organ-at-risk contours. These CT scans were collected using systems from three different manufacturers. Standard clinical imaging protocols were followed, and contours were manually generated and reviewed at weekly RT quality assurance rounds. RADCURE imaging and structure set data was extracted from our institution's radiation treatment planning and oncology information systems using a custom-built data mining and processing system. Furthermore, images were linked to our clinical anthology of outcomes data for each patient and includes demographic, clinical and treatment information based on the 7th edition TNM staging system (Tumor-Node-Metastasis Classification System of Malignant Tumors). The median patient age is 63, with the final dataset including 80% males. Half of the cohort is diagnosed with oropharyngeal cancer, while laryngeal, nasopharyngeal, and hypopharyngeal cancers account for 25%, 12%, and 5% of cases, respectively. The median duration of follow-up is five years, with 60% of the cohort surviving until the last follow-up point. DATA FORMAT AND USAGE NOTES: The dataset provides images and contours in DICOM CT and RT-STRUCT formats, respectively. We have standardized the nomenclature for individual contours-such as the gross primary tumor, gross nodal volumes, and 19 organs-at-risk-to enhance the RT-STRUCT files' utility. Accompanying demographic, clinical, and treatment data are supplied in a comma-separated values (CSV) file format. This comprehensive dataset is publicly accessible via The Cancer Imaging Archive. POTENTIAL APPLICATIONS: RADCURE's amalgamation of imaging, clinical, demographic, and treatment data renders it an invaluable resource for a broad spectrum of radiomics image analysis research endeavors. Researchers can utilize this dataset to advance routine clinical procedures using machine learning or artificial intelligence, to identify new non-invasive biomarkers, or to forge prognostic models.

Causes and impact of delays during the COVID-19 pandemic on head and neck cancer diagnosis.

BACKGROUND: The causes for delays during the COVID19 pandemic and their impact on head and neck cancer (HNC) diagnosis and staging are not well described. METHODS: Two cohorts were defined a priori for review and analysis-a Pre-Pandemic cohort (June 1 to December 31, 2019) and a Pandemic cohort (June 1 to December 31, 2020). Delays were categorized as COVID-19 related or not, and as clinician, patient, or policy related. RESULTS: A total of 638 HNC patients were identified including 327 in the Pre-Pandemic Cohort and 311 in the Pandemic Cohort. Patients in the Pandemic cohort had more N2-N3 category (41% vs. 33%, p = 0.03), T3-T4 category (63% vs. 50%, p = 0.002), and stage III-IV (71% vs. 58%, p < 0.001) disease. Several intervals in the diagnosis to treatment pathway were significantly longer in the pandemic cohort as compared to the Pre-Pandemic cohort. Among the pandemic cohort, 146 (47%) experienced a delay, with 112 related to the COVID-19 pandemic; 80 (71%) were clinician related, 15 (13%) were patient related, and 17 (15%) were policy related. CONCLUSIONS: Patients in the Pandemic cohort had higher stage disease at diagnosis and longer intervals along the diagnostic pathway, with COVID-19 related clinician factors being the most common cause of delay.

Development and Standardization of an Osteoradionecrosis Classification System in Head and Neck Cancer: Implementation of a Risk-Based Model.

PURPOSE: Osteoradionecrosis of the jaw (ORN) can manifest in varying severity. The aim of this study is to identify ORN risk factors and develop a novel classification to depict the severity of ORN. METHODS: Consecutive patients with head and neck cancer (HNC) treated with curative-intent intensity-modulated radiation therapy (IMRT) (≥45 Gy) from 2011 to 2017 were included. Occurrence of ORN was identified from in-house prospective dental and clinical databases and charts. Multivariable logistic regression model was used to identify risk factors and stratify patients into high-risk and low-risk groups. A novel ORN classification system was developed to depict ORN severity by modifying existing systems and incorporating expert opinion. The performance of the novel system was compared with 15 existing systems for their ability to identify and predict serious ORN event (jaw fracture or requiring jaw resection). RESULTS: ORN was identified in 219 of 2,732 (8%) consecutive patients with HNC. Factors associated with high risk of ORN were oral cavity or oropharyngeal primaries, received IMRT dose ≥60 Gy, current/ex-smokers, and/or stage III to IV periodontal condition. The ORN rate for high-risk versus low-risk patients was 12.7% versus 3.1% (P < .001) with an AUC of 0.71. Existing ORN systems overclassified serious ORN events and failed to recognize maxillary ORN. A novel ORN classification system, ClinRad, was proposed on the basis of vertical extent of bone necrosis and presence/absence of exposed bone/fistula. This system detected serious ORN events in 5.7% of patients and statistically outperformed existing systems. CONCLUSION: We identified risk factors for ORN and proposed a novel ORN classification system on the basis of vertical extent of bone necrosis and presence/absence of exposed bone/fistula. It outperformed existing systems in depicting the seriousness of ORN and may facilitate clinical care and clinical trials.

Telemedicine-enabled biofeedback electropalatography rehabilitation (TEBER): A pilot study for patients treated with surgery for oral cavity carcinoma.

BACKGROUND: To address the rehabilitative barriers to frequency and precision of care, we conducted a pilot study of a biofeedback electropalatography (EPG) device paired with telemedicine for patients who underwent primary surgery +/- adjuvant radiation for oral cavity carcinoma. We hypothesized that lingual optimization followed by telemedicine-enabled biofeedback electropalatography rehabilitation (TEBER) would further improve speech and swallowing outcomes after "standard-of-care" SOC rehabilitation. METHOD: Pilot prospective 8-week (TEBER) program following 8 weeks of (SOC) rehabilitation. RESULTS: Twenty-seven patients were included and 11 completed the protocol. When examining the benefit of TEBER independent of standard of care, "range-of-liquids" improved by +0.36 [95% CI, 0.02-0.70, p = 0.05] and "range-of-solids" improved by +0.73 [95% CI, 0.12-1.34, p = 0.03]. There was a positive trend toward better oral cavity obliteration; residual volume decreased by -1.2 [95% CI, -2.45 to 0.053, p = 0.06], and "nutritional-mode" increased by +0.55 [95% CI, -0.15 to 1.24, p = 0.08]. CONCLUSION: This pilot suggests that TEBER bolsters oral rehabilitation after 8 weeks of SOC lingual range of motion.

Head and neck cancer predictive risk estimator to determine control and therapeutic outcomes of radiotherapy (HNC-PREDICTOR): development, international multi-institutional validation, and web implementation of clinic-ready model-based risk stratification for head and neck cancer.

BACKGROUND: Personalised radiotherapy can improve treatment outcomes of patients with head and neck cancer (HNC), where currently a 'one-dose-fits-all' approach is the standard. The aim was to establish individualised outcome prediction based on multi-institutional international 'big-data' to facilitate risk-based stratification of patients with HNC. METHODS: The data of 4611 HNC radiotherapy patients from three academic cancer centres were split into four cohorts: a training (n = 2241), independent test (n = 786), and external validation cohorts 1 (n = 1087) and 2 (n = 497). Tumour- and patient-related clinical variables were considered in a machine learning pipeline to predict overall survival (primary end-point) and local and regional tumour control (secondary end-points); serially, imaging features were considered for optional model improvement. Finally, patients were stratified into high-, intermediate-, and low-risk groups. RESULTS: Performance score, AJCC8thstage, pack-years, and Age were identified as predictors for overall survival, demonstrating good performance in both the training cohort (c-index = 0.72 [95% CI, 0.66-0.77]) and in all three validation cohorts (c-indices: 0.76 [0.69-0.83], 0.73 [0.68-0.77], and 0.75 [0.68-0.80]). Excellent stratification of patients with HNC into high, intermediate, and low mortality risk was achieved; with 5-year overall survival rates of 17-46% for the high-risk group compared to 92-98% for the low-risk group. The addition of morphological image feature further improved the performance (c-index = 0.73 [0.64-0.81]). These models are integrated in a clinic-ready interactive web interface: https://uic-evl.github.io/hnc-predictor/ CONCLUSIONS: Robust model-based prediction was able to stratify patients with HNC in distinct high, intermediate, and low mortality risk groups. This can effectively be capitalised for personalised radiotherapy, e.g., for tumour radiation dose escalation/de-escalation.

The collateral impact of the COVID-19 pandemic on HPV-positive oropharyngeal cancer diagnosis.

PURPOSE: We aim to assess the potential impact of the COVID-19 pandemic on diagnostic delays in HPV-positive oropharyngeal cancer (OPC), and to describe their underlying reasons. METHODS: All HPV + OPC referred to a tertiary cancer centre and diagnosed between June-December 2019 (Pre-Pandemic cohort) vs June-December 2020 (Pandemic cohort) were reviewed. TNM classification, gross-tumor-volumes (GTV) and intervals between sign/symptom onset and treatment initiation were compared between the cohorts. Reasons for delay (>6 months from onset of signs/symptoms to a positive biopsy of the primary tumor, or a delay specifically mentioned in the patient chart) in establishing the diagnosis were recorded per clinician's documentation, and categorized as COVID-related or non-COVID-related. RESULTS: A total of 157 consecutive HPV + OPC patients were identified (Pre-Pandemic: 92; Pandemic: 65). Compared to the Pre-Pandemic cohort, Pandemic cohort patients had a higher proportion of N2-N3 (32 % vs 15 %, p = 0.019) and stage III (38 % vs 23 %, p = 0.034) disease at presentation. The differences in proportions with > 6 months delay from symptom onset to establishing the diagnosis (29 % vs 20 %, p = 0.16) or to first treatment (49 % vs 38 %, p = 0.22) were not statistically different. 47 % of diagnostic delays in the Pandemic cohort were potentially attributable to COVID-19. CONCLUSION: We observed a collateral impact of the COVID-19 pandemic on HPV + OPC care through more advanced stage at presentation and a non-significant but numerically longer interval to diagnosis. This could adversely impact patient outcomes and future resource allocation. Both COVID-19-related and unrelated factors contribute to diagnostic delays. Tailored interventions to reduce delays are warranted.

Multi-institutional Prognostic Modeling in Head and Neck Cancer: Evaluating Impact and Generalizability of Deep Learning and Radiomics.

Artificial intelligence (AI) and machine learning (ML) are becoming critical in developing and deploying personalized medicine and targeted clinical trials. Recent advances in ML have enabled the integration of wider ranges of data including both medical records and imaging (radiomics). However, the development of prognostic models is complex as no modeling strategy is universally superior to others and validation of developed models requires large and diverse datasets to demonstrate that prognostic models developed (regardless of method) from one dataset are applicable to other datasets both internally and externally. Using a retrospective dataset of 2,552 patients from a single institution and a strict evaluation framework that included external validation on three external patient cohorts (873 patients), we crowdsourced the development of ML models to predict overall survival in head and neck cancer (HNC) using electronic medical records (EMR) and pretreatment radiological images. To assess the relative contributions of radiomics in predicting HNC prognosis, we compared 12 different models using imaging and/or EMR data. The model with the highest accuracy used multitask learning on clinical data and tumor volume, achieving high prognostic accuracy for 2-year and lifetime survival prediction, outperforming models relying on clinical data only, engineered radiomics, or complex deep neural network architecture. However, when we attempted to extend the best performing models from this large training dataset to other institutions, we observed significant reductions in the performance of the model in those datasets, highlighting the importance of detailed population-based reporting for AI/ML model utility and stronger validation frameworks. We have developed highly prognostic models for overall survival in HNC using EMRs and pretreatment radiological images based on a large, retrospective dataset of 2,552 patients from our institution.Diverse ML approaches were used by independent investigators. The model with the highest accuracy used multitask learning on clinical data and tumor volume.External validation of the top three performing models on three datasets (873 patients) with significant differences in the distributions of clinical and demographic variables demonstrated significant decreases in model performance. Significance: ML combined with simple prognostic factors outperformed multiple advanced CT radiomics and deep learning methods. ML models provided diverse solutions for prognosis of patients with HNC but their prognostic value is affected by differences in patient populations and require extensive validation.

Using Recurrent Neural Networks to Extract High-Quality Information From Lung Cancer Screening Computerized Tomography Reports for Inter-Radiologist Audit and Feedback Quality Improvement.

PURPOSE: Lung cancer screening programs generate a high volume of low-dose computed tomography (LDCT) reports that contain valuable information, typically in a free-text format. High-performance named-entity recognition (NER) models can extract relevant information from these reports automatically for inter-radiologist quality control. METHODS: Using LDCT report data from a longitudinal lung cancer screening program (8,305 reports; 3,124 participants; 2006-2019), we trained a rule-based model and two bidirectional long short-term memory (Bi-LSTM) NER neural network models to detect clinically relevant information from LDCT reports. Model performance was tested using F1 scores and compared with a published open-source radiology NER model (Stanza) in an independent evaluation set of 150 reports. The top performing model was applied to a data set of 6,948 reports for an inter-radiologist quality control assessment. RESULTS: The best performing model, a Bi-LSTM NER recurrent neural network model, had an overall F1 score of 0.950, which outperformed Stanza (F1 score = 0.872) and a rule-based NER model (F1 score = 0.809). Recall (sensitivity) for the best Bi-LSTM model ranged from 0.916 to 0.991 for different entity types; precision (positive predictive value) ranged from 0.892 to 0.997. Test performance remained stable across time periods. There was an average of a 2.86-fold difference in the number of identified entities between the most and the least detailed radiologists. CONCLUSION: We built an open-source Bi-LSTM NER model that outperformed other open-source or rule-based radiology NER models. This model can efficiently extract clinically relevant information from lung cancer screening computerized tomography reports with high accuracy, enabling efficient audit and feedback to improve quality of patient care.

Development and Standardization of a Classification System for Osteoradionecrosis: Implementation of a Risk-Based Model.

Purpose: Osteoradionecrosis of the jaw (ORN) can manifest in varying severity. The aim of this study is to identify ORN risk factors and develop a novel classification to depict the severity of ORN. Methods: Consecutive head-and-neck cancer (HNC) patients treated with curative-intent IMRT (≥ 45Gy) in 2011-2018 were included. Occurrence of ORN was identified from in-house prospective dental and clinical databases and charts. Multivariable logistic regression model was used to identify risk factors and stratify patients into high-risk and low-risk groups. A novel ORN classification system was developed to depict ORN severity by modifying existing systems and incorporating expert opinion. The performance of the novel system was compared to fifteen existing systems for their ability to identify and predict serious ORN event (jaw fracture or requiring jaw resection). Results: ORN was identified in 219 out of 2732 (8%) consecutive HNC patients. Factors associated with high-risk of ORN were: oral-cavity or oropharyngeal primaries, received IMRT dose ≥60Gy, current/ex-smokers, and/or stage III-IV periodontal disease. The ORN rate for high-risk vs low-risk patients was 12.7% vs 3.1% (p<0.001) with an area-under-the-receiver-operating-curve (AUC) of 0.71. Existing ORN systems overclassified serious ORN events and failed to recognize maxillary ORN. A novel ORN classification system, RadORN, was proposed based on vertical extent of bone necrosis and presence/absence of exposed bone/fistula. This system detected serious ORN events in 5.7% of patients and statistically outperformed existing systems. Conclusion: We identified risk factors for ORN, and proposed a novel ORN classification system based on vertical extent of bone necrosis and presence/absence of exposed bone/fistula. It outperformed existing systems in depicting the seriousness of ORN, and may facilitate clinical care and clinical trials.

Determining the Impact of Thickened Liquids on Swallowing in Patients Undergoing Irradiation for Oropharynx Cancer.

The current standard for the treatment of oropharynx cancers is radiation therapy. However, patients are frequently left with dysphagia characterized by penetration-aspiration (impaired safety) and residue (impaired efficiency). Although thickened liquids are commonly used to manage dysphagia, we lack evidence to guide the modification of liquids for clinical benefit in the head and neck cancer population. The objective of this study was to assess the impact of slightly and mildly thick liquids on penetration-aspiration and residue in 12 patients with oropharyngeal cancer who displayed penetration-aspiration on thin liquid within 3 to 6 months after completion of radiotherapy. Significantly fewer instances of penetration-aspiration were seen with slightly and mildly thick liquids as compared with thin (P < .05). No differences were found across stimuli in the frequency of residue. Patients with oropharyngeal cancers who present with post-radiation therapy dysphagia involving penetration-aspiration on thin liquids may benefit from slightly and mildly thick liquids without risk of worse residue.

Heart irradiation as a risk factor for radiation pneumonitis.

PURPOSE: to investigate the potential role of incidental heart irradiation on the risk of radiation pneumonitis (RP) for patients receiving definitive radiation therapy for non-small-cell lung cancer (NSCLC). MATERIAL AND METHODS: two hundred and nine patient datasets were available for this study. Heart and lung dose-volume parameters were extracted for modeling, based on Monte Carlo-based heterogeneity corrected dose distributions. Clinical variables tested included age, gender, chemotherapy, pre-treatment weight-loss, performance status, and smoking history. The risk of RP was modeled using logistic regression. RESULTS: the most significant univariate variables were heart related, such as heart heart V65 (percent volume receiving at least 65 Gy) (Spearman Rs = 0.245, p < 0.001). The best-performing logistic regression model included heart D10 (minimum dose to the hottest 10% of the heart), lung D35, and maximum lung dose (Spearman Rs = 0.268, p < 0.0001). When classified by predicted risk, the RP incidence ratio between the most and least risky 1/3 of treatments was 4.8. The improvement in risk modeling using lung and heart variables was better than using lung variables alone. CONCLUSIONS: these results suggest a previously unsuspected role of heart irradiation in many cases of RP.

Validating impact of pretreatment tumor growth rate on outcome of early-stage lung cancer treated with stereotactic body radiation therapy.

BACKGROUND: To assess correlation of pretreatment specific growth rate (SGR) value of 0.43 × 10-2 with overall and failure-free survival of patients with early-stage non-small cell lung cancer (NSCLC) treated with stereotactic body radiation therapy (SBRT). METHODS: A retrospective chart review of 160 patients with pathologically confirmed stage I NSCLC treated with SBRT between June 2010 and December 2012 in a large, tertiary cancer institute was undertaken. Both diagnostic and archived planning CT were uploaded to the treatment planning system to determine tumor volume at diagnosis (GTV1) and planning time (GTV2). The time (t) between both CTs was recorded. SGR was calculated using GTV1, GTV2, and t. The median SGR (0.43 × 10-2 ) from our previous data was used to group patients into low and high SGR cohorts. Log-rank test was used to compare overall (OS) and failure-free survivals (FFS) of SGR groups. RESULTS: The median time interval between diagnostic and planning CT scans was 87 days. The median OS was 38 and 66 months for high and low SGR cohorts, respectively (P = 0.03). The median FFS was 27 and 55 months for high and low SGR cohorts, respectively (P = 0.005). High SGR (P < 0.05), male gender (P = <0.01), and GTV2 (P = <0.05) were associated with poorer FFS. CONCLUSIONS: High SGR was associated with poorer outcome in patients with early-stage NSCLC treated with SBRT. SGR can be used in conjunction with other well-known predictive factors to formulate a practical predictive model to identify subgroups of the patient at higher risk of recurrence after SBRT.