Inter-hospital variation in data collection, radiotherapy treatment, and survival in patients with head and neck cancer: A multisite study.

BACKGROUND AND PURPOSE: Inter-hospital inequalities in head and neck cancer (HNC) survival may exist due to variation in radiotherapy treatment-related factors. This study investigated inter-hospital variation in data collection, primary radiotherapy treatment, and survival in HNC patients from an Australian setting. MATERIALS AND METHODS: Data collected in oncology information systems (OIS) from seven Australian hospitals was extracted for 3,182 adults treated with curative radiotherapy, with or without surgery or chemotherapy, for primary, non-metastatic squamous cell carcinoma of the head and neck (2000-2017). Death data was sourced from the National Death Index using record linkage. Multivariable Cox regression was used to assess the association between survival and hospital. RESULTS: Inter-hospital variation in data collection, primary radiotherapy dose, and five-year HNC-related death was detected. Completion of eleven fields ranged from 66%-98%. Primary radiotherapy treated Tis-T1N0 glottic and any stage oral cavity and oropharynx cancers received significantly different time-corrected biologically equivalent dose in two gray fractions (EQD2T) by hospital, with observed deviation from Australian radiotherapy guidelines. Increased EQD2T dose was associated with a reduced risk of five-year HNC-related death in all patients and those treated with primary radiotherapy. Hospital, tumour site, and T and N classification were also identified as independent prognostic factors for five-year HNC-related death in all patients treated with radiotherapy. CONCLUSION: Unexplained variation exists in HNC-related death in patients treated at Australian hospitals. Available routinely collected data in OIS are insufficient to explain variation in survival. Innovative data collection, extraction, and classification practices are needed to inform clinical practice.

The Utility of Oncology Information Systems for Prognostic Modelling in Head and Neck Cancer.

Cancer centres rely on electronic information in oncology information systems (OIS) to guide patient care. We investigated the completeness and accuracy of routinely collected head and neck cancer (HNC) data sourced from an OIS for suitability in prognostic modelling and other research. Three hundred and fifty-three adults diagnosed from 2000 to 2017 with head and neck squamous cell carcinoma, treated with radiotherapy, were eligible. Thirteen clinically relevant variables in HNC prognosis were extracted from a single-centre OIS and compared to that compiled separately in a research dataset. These two datasets were compared for agreement using Cohen's kappa coefficient for categorical variables, and intraclass correlation coefficients for continuous variables. Research data was 96% complete compared to 84% for OIS data. Agreement was perfect for gender (κ = 1.000), high for age (κ = 0.993), site (κ = 0.992), T (κ = 0.851) and N (κ = 0.812) stage, radiotherapy dose (κ = 0.889), fractions (κ = 0.856), and duration (κ = 0.818), and chemotherapy treatment (κ = 0.871), substantial for overall stage (κ = 0.791) and vital status (κ = 0.689), moderate for grade (κ = 0.547), and poor for performance status (κ = 0.110). Thirty-one other variables were poorly captured and could not be statistically compared. Documentation of clinical information within the OIS for HNC patients is routine practice; however, OIS data was less correct and complete than data collected for research purposes. Substandard collection of routine data may hinder advancements in patient care. Improved data entry, integration with clinical activities and workflows, system usability, data dictionaries, and training are necessary for OIS data to generate robust research. Data mining from clinical documents may supplement structured data collection.

Machine Learning and Nomogram Prognostic Modeling for 2-Year Head and Neck Cancer-Specific Survival Using Electronic Health Record Data: A Multisite Study.

PURPOSE: There is limited knowledge of the prediction of 2-year cancer-specific survival (CSS) in the head and neck cancer (HNC) population. The aim of this study is to develop and validate machine learning models and a nomogram for the prediction of 2-year CSS in patients with HNC using real-world data collected by major teaching and tertiary referral hospitals in New South Wales (NSW), Australia. MATERIALS AND METHODS: Data collected in oncology information systems at multiple NSW Cancer Centres were extracted for 2,953 eligible adults diagnosed between 2000 and 2017 with squamous cell carcinoma of the head and neck. Death data were sourced from the National Death Index using record linkage. Machine learning and Cox regression/nomogram models were developed and internally validated in Python and R, respectively. RESULTS: Machine learning models demonstrated highest performance (C-index) in the larynx and nasopharynx cohorts (0.82), followed by the oropharynx (0.79) and the hypopharynx and oral cavity cohorts (0.73). In the whole HNC population, C-indexes of 0.79 and 0.70 and Brier scores of 0.10 and 0.27 were reported for the machine learning and nomogram model, respectively. Cox regression analysis identified age, T and N classification, and time-corrected biologic equivalent dose in two gray fractions as independent prognostic factors for 2-year CSS. N classification was the most important feature used for prediction in the machine learning model followed by age. CONCLUSION: Machine learning and nomogram analysis predicted 2-year CSS with high performance using routinely collected and complete clinical information extracted from oncology information systems. These models function as visual decision-making tools to guide radiotherapy treatment decisions and provide insight into the prediction of survival outcomes in patients with HNC.

Empirical comparison of routinely collected electronic health record data for head and neck cancer-specific survival in machine-learnt prognostic models.

BACKGROUND: Knowledge of the prognostic factors and performance of machine learning predictive models for 2-year cancer-specific survival (CSS) is limited in the head and neck cancer (HNC) population. METHODS: Data from our facilities' oncology information system (OIS) collected for routine practice (OIS dataset, n = 430 patients) and research purposes (research dataset, n = 529 patients) were extracted on adults diagnosed between 2000 and 2017 with squamous cell carcinoma of the head and neck. RESULTS: Machine learning demonstrated excellent performance (area under the curve, AUC) in the whole cohort (AUC = 0.97, research dataset), larynx cohort (AUC = 0.98, both datasets), and oropharynx cohort (AUC = 0.99, both datasets). Tumor site and T classification were identified as predictors of 2-year CSS in both datasets. Hypothyroidism and fitness for operation were further identified in the research dataset. CONCLUSIONS: Datasets extracted from an OIS for routine clinical practice and research purposes demonstrated high utility for informing 2-year head and neck CSS.

Evaluation of an automated Presidio anonymisation model for unstructured radiation oncology electronic medical records in an Australian setting.

BACKGROUND: Electronic medical records (EMRs) contain valuable information for clinical research, however, the presence of personally identifying information (PII) restricts their use. Anonymisation of PII from EMRs enables clinical information to be shared for research purposes. Since there is limited research relating to the anonymisation of Australian EMRs, the performance of Microsoft Presidio with customisation on clinical documents from an Australian radiation oncology information system (OIS) was evaluated. METHODS: A random sample of 300 unstructured free-text clinical documents were extracted from the Prince of Wales Cancer Centre OIS on patients diagnosed with cancer of the head and neck between 2000 and 2017. Anonymisation of clinical text was performed using Microsoft Presidio, implemented in Python programming language. Each clinical document was manually compared pre- and post-anonymisation for the identification and redaction of 13 PII. Model performance was evaluated using three classification criteria; correct, partial, and missed classification, to determine recall, precision, and F1-score. These three metrics were performed under relaxed conditions, where partial classifications were considered correct, and under strict conditions, where only correct classifications were considered correct. RESULTS: A total of 8,713 PII were identified, of which 7,026 (81%) were classified as correct, 850 (10%) as partial, and 837 (9%) as missed. There were 245 instances of incorrect classifications. Evaluation of the model demonstrated an average precision of 0.8921, recall (strict) of 0.8064, F1-score (strict) of 0.8471, recall (relaxed) of 0.9039, and F1-score (relaxed) of 0.8980. CONCLUSION: This is the first example of an open-source anonymisation model to be customised and tested on clinical documents from an Australian radiation oncology EMR. These findings support the use of Presidio for the safe use and sharing of cancer data within Australia for certain PII, however, additional checks are required to ensure person names are successfully anonymised.

The Impact of Critical Weight Loss and Reactive Feeding Tubes on Cancer-Specific Survival in Head and Neck Cancer.

Critical weight loss (CWL) continues to be a major issue in head and neck cancer (HNC) and many patients require tube feeding. We investigated the use of reactive feeding tubes (RFTs), associated CWL, and the impact on cancer-specific survival (CSS). A single-institution, retrospective audit was conducted on 460 adult HNC patients who received radiotherapy ± chemotherapy between 2005 and 2017. CSS in patients with CWL and RFTs was compared to those with no tube. Prediction analysis for RFT insertion was also performed. CWL occurred in 53% of patients, and in 88% of those with a RFT (p < 0.001). In patients with CWL, those with a RFT had worse 5 and 10-year CSS compared to those with no tube (68% and 65% vs 83% and 80% respectively, p = 0.040) in multivariate Cox regression analysis. Concurrent chemoradiotherapy combined with CWL was the strongest predictor for RFT insertion (p = 0.003). CWL, combined with having a RFT, impacts negatively on CSS. CWL may be one of the triggers for RFT insertion, however those with no tube have better CSS. This may be due to higher weight loss levels seen in those who have a RFT, and earlier insertion to prevent such losses seems indicated.

Epidemiology of lymphogranuloma venereum in New South Wales, 2006-2015.

AIM: To describe the epidemiology of lymphogranuloma venereum (LGV) in New South Wales (NSW) from 2006 to 2015. METHODS: LGV notification data between 2006 and 2015 from New South Wales were analysed to describe time trends in counts and rates by gender, age group and area of residence, as well as anatomical sites of infection. A positivity ratio was calculated using the number of LGV notifications per 100 anorectal chlamydia notifications per year. Data linkage was used to ascertain the proportion of LGV cases that were co-infected with HIV. RESULTS: There were 208 notifications of LGV in NSW from 2006 to 2015; all were among men, with a median age of 42 years, and half were residents of inner-city Sydney. Annual notifications peaked at 57 (1.6 per 100,000 males) in 2010, declined to 16 (0.4 per 100,000 males) in 2014, and then increased to 34 (0.9 per 100,000 males) in 2015. Just under half (47.4%) of LGV cases were determined to be co-infected with HIV. CONCLUSION: The number of LGV notifications each year has not returned to the low levels seen prior to the peak in 2010. Continued public health surveillance is important for the management and control of LGV.

Surgery is not the only determinant of an outcome in patients with hypopharyngeal carcinoma.

BACKGROUND: The aim of this study was to evaluate the outcomes in patients treated for hypopharyngeal carcinoma in a single-center and the importance of considering how patient factors influence outcomes. METHODS: A retrospective review was conducted on patients who were seen at the Prince of Wales Hospital from 1968 to 2015. Kaplan-Meier and Cox regression analyses were performed for each patient and treatment factor to investigate outcomes of local control, cancer-specific survival (CSS), and ultimate local control. RESULTS: Three hundred thirty patients were analyzed. Significant multivariate predictors for improved local control and CSS were fitness for surgery, cancer operability, surgery with adjuvant radiotherapy, no treatment interruptions (P < .05). Five-year local control (84%), CSS (50%), and ultimate local control (84%) rates were significantly higher in patients treated surgically with adjuvant radiotherapy, compared to single modality treatment (P < .05). CONCLUSION: Patient factors influence the outcomes experienced by patients with hypopharyngeal carcinoma.

The impact of HPV status on weight loss and feeding tube use in oropharyngeal carcinoma.

OBJECTIVES: It has been well established that patients with oropharyngeal carcinoma are at high nutritional risk, with significant weight loss and tube feeding common. Human papillomavirus (HPV)-associated disease has led to a change in the "typical" presentation and nutritional profile of this population. The aim of our study was to determine whether the need for a feeding tube, and weight loss during radiotherapy (RT) in patients with oropharyngeal carcinoma differed with HPV status. MATERIALS AND METHODS: Patients who received curative RT ±â€¯chemotherapy from January 2011 to January 2016 were included (n = 100). We retrospectively evaluated feeding tube use and timing of insertion (prophylactic vs reactive), percentage weight loss during RT and the prevalence of critical weight loss (CWL) ≥5%. RESULTS: HPV-positive patients had significantly higher weight loss during RT compared to the rest of the cohort (8.4% vs 6.1%, 95%CI 0.8-3.9, p = 0.003). CWL was observed in 86% and in a higher proportion with HPV-positive disease (93%, p = 0.011). Conditional probability modelling analysis revealed, with 74% accuracy, concurrent chemoradiotherapy and HPV-positive status were predictors of CWL when comparing HPV-positive patients to HPV-negative (96%, p = 0.001 and 98%, p = 0.012 respectively). More HPV-positive patients required feeding tubes (n = 43, 63%, p = 0.05), most being reactive (n = 27, 63%). All patients with reactive tubes experienced CWL. CONCLUSION: The high incidence of CWL in patients with HPV-positive oropharyngeal carcinoma is of concern. Tube feeding continues to be a necessary nutritional intervention in this population and predicting who will require a tube is challenging. Larger, prospective cohort studies are required.