Federated Learning Survival Model and Potential Radiotherapy Decision Support Impact Assessment for Non-small Cell Lung Cancer Using Real-World Data

AIMS

The objective of this study was to develop a two-year overall survival model for inoperable stage I-III non-small cell lung cancer (NSCLC) patients using routine radiation oncology data over a federated (distributed) learning network and evaluate the potential of decision support for curative versus palliative radiotherapy.

METHODS

A federated infrastructure of data extraction, de-identification, standardisation, image analysis, and modelling was installed for seven clinics to obtain clinical and imaging features and survival information for patients treated in 2011-2019. A logistic regression model was trained for the 2011-2016 curative patient cohort and validated for the 2017-2019 cohort. Features were selected with univariate and model-based analysis and optimised using bootstrapping. System performance was assessed by the receiver operating characteristic (ROC) and corresponding area under curve (AUC), C-index, calibration metrics and Kaplan-Meier survival curves, with risk groups defined by model probability quartiles. Decision support was evaluated using a case-control analysis using propensity matching between treatment groups.

RESULTS

1655 patient datasets were included. The overall model AUC was 0.68. Fifty-eight percent of patients treated with palliative radiotherapy had a low-to-moderate risk prediction according to the model, with survival times not significantly different (p = 0.87 and 0.061) from patients treated with curative radiotherapy classified as high-risk by the model. When survival was simulated by risk group and model-indicated treatment, there was an estimated 11% increase in survival rate at two years (p < 0.01).

CONCLUSION

Federated learning over multiple institution data can be used to develop and validate decision support systems for lung cancer while quantifying the potential impact of their use in practice. This paves the way for personalised medicine, where decisions can be based more closely on individual patient details from routine care.

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.

Rift-induced disruption of cratonic keels drives kimberlite volcanism

Kimberlites are volatile-rich, occasionally diamond-bearing magmas that have erupted explosively at Earth's surface in the geologic past1-3. These enigmatic magmas, originating from depths exceeding 150 km in Earth's mantle1, occur in stable cratons and in pulses broadly synchronous with supercontinent cyclicity4. Whether their mobilization is driven by mantle plumes5 or by mechanical weakening of cratonic lithosphere4,6 remains unclear. Here we show that most kimberlites spanning the past billion years erupted about 30 million years (Myr) after continental breakup, suggesting an association with rifting processes. Our dynamical and analytical models show that physically steep lithosphere-asthenosphere boundaries (LABs) formed during rifting generate convective instabilities in the asthenosphere that slowly migrate many hundreds to thousands of kilometres inboard of rift zones. These instabilities endure many tens of millions of years after continental breakup and destabilize the basal tens of kilometres of the cratonic lithosphere, or keel. Displaced keel is replaced by a hot, upwelling mixture of asthenosphere and recycled volatile-rich keel in the return flow, causing decompressional partial melting. Our calculations show that this process can generate small-volume, low-degree, volatile-rich melts, closely matching the characteristics expected of kimberlites1-3. Together, these results provide a quantitative and mechanistic link between kimberlite episodicity and supercontinent cycles through progressive disruption of cratonic keels.

Automated detection, delineation and quantification of whole-body bone metastasis using FDG-PET/CT images

Non-small cell lung cancer (NSCLC) patients with the metastatic spread of disease to the bone have high morbidity and mortality. Stereotactic ablative body radiotherapy increases the progression free survival and overall survival of these patients with oligometastases. FDG-PET/CT, a functional imaging technique combining positron emission tomography (PET) with 18 F-fluorodeoxyglucose (FDG) and computer tomography (CT) provides improved staging and identification of treatment response. It is also associated with reduction in size of the radiotherapy tumour volume delineation compared with CT based contouring in radiotherapy, thus allowing for dose escalation to the target volume with lower doses to the surrounding organs at risk. FDG-PET/CT is increasingly being used for the clinical management of NSCLC patients undergoing radiotherapy and has shown high sensitivity and specificity for the detection of bone metastases in these patients. Here, we present a software tool for detection, delineation and quantification of bone metastases using FDG-PET/CT images. The tool extracts standardised uptake values (SUV) from FDG-PET images for auto-segmentation of bone lesions and calculates volume of each lesion and associated mean and maximum SUV. The tool also allows automatic statistical validation of the auto-segmented bone lesions against the manual contours of a radiation oncologist. A retrospective review of FDG-PET/CT scans of more than 30 candidate NSCLC patients was performed and nine patients with one or more metastatic bone lesions were selected for the present study. The SUV threshold prediction model was designed by splitting the cohort of patients into a subset of 'development' and 'validation' cohorts. The development cohort yielded an optimum SUV threshold of 3.0 for automatic detection of bone metastases using FDG-PET/CT images. The validity of the derived optimum SUV threshold on the validation cohort demonstrated that auto-segmented and manually contoured bone lesions showed strong concordance for volume of bone lesion (r = 0.993) and number of detected lesions (r = 0.996). The tool has various applications in radiotherapy, including but not limited to studies determining optimum SUV threshold for accurate and standardised delineation of bone lesions and in scientific studies utilising large patient populations for instance for investigation of the number of metastatic lesions that can be treated safety with an ablative dose of radiotherapy without exceeding the normal tissue toxicity.

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.

What is the evidence that advertising policies could have an impact on gambling-related harms? A systematic umbrella review of the literature

OBJECTIVE

To summarise the evidence on the impacts of gambling-related advertising that could lead to gambling-related harm, including impacts on vulnerable individuals and inequalities in the distribution of harms.

STUDY DESIGN

An umbrella review of studies investigating the impact of gambling advertising.

METHODS

A review was undertaken of systematic reviews of qualitative, quantitative and mixed method studies reporting outcomes associated with gambling advertising and marketing. The search strategy included database searches (Web of Science, PsycInfo) and website searches. The quality of the included reviews was determined using A MeaSurement Tool to Assess systematic Reviews 2.

RESULTS

1024 papers were identified by database searches. Eight systematic reviews, including 74 unique studies, met inclusion criteria. Included studies, using quantitative and qualitative methods, consistently support the existence of a causal relationship between exposure to advertising of gambling products/brands and more positive attitudes to gambling, greater intentions to gamble and increased gambling activity at both individual and population level. There is evidence of a 'dose-response' effect; greater advertising exposure increases participation which leads to a greater risk of harm. There was more evidence for the impact on children and young people and for those already at risk from current gambling activity with those most vulnerable more likely to be influenced.

CONCLUSION

Gambling advertising restrictions could reduce overall harm and mitigate the impact of advertising on gambling-related inequalities. Public health harm prevention strategies should include policies which limit exposure to advertising, particularly among children and vulnerable groups.

Standardising Breast Radiotherapy Structure Naming Conventions: A Machine Learning Approach

In progressing the use of big data in health systems, standardised nomenclature is required to enable data pooling and analyses. In many radiotherapy planning systems and their data archives, target volumes (TV) and organ-at-risk (OAR) structure nomenclature has not been standardised. Machine learning (ML) has been utilised to standardise volumes nomenclature in retrospective datasets. However, only subsets of the structures have been targeted. Within this paper, we proposed a new approach for standardising all the structures nomenclature by using multi-modal artificial neural networks. A cohort consisting of 1613 breast cancer patients treated with radiotherapy was identified from Liverpool & Macarthur Cancer Therapy Centres, NSW, Australia. Four types of volume characteristics were generated to represent each target and OAR volume: textual features, geometric features, dosimetry features, and imaging data. Five datasets were created from the original cohort, the first four represented different subsets of volumes and the last one represented the whole list of volumes. For each dataset, 15 sets of combinations of features were generated to investigate the effect of using different characteristics on the standardisation performance. The best model reported 99.416% classification accuracy over the hold-out sample when used to standardise all the nomenclatures in a breast cancer radiotherapy plan into 21 classes. Our results showed that ML based automation methods can be used for standardising naming conventions in a radiotherapy plan taking into consideration the inclusion of multiple modalities to better represent each volume.

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.

Larynx cancer survival model developed through open-source federated learning

INTRODUCTION

Federated learning has the potential to perfrom analysis on decentralised data; however, there are some obstacles to survival analyses as there is a risk of data leakage. This study demonstrates how to perform a stratified Cox regression survival analysis specifically designed to avoid data leakage using federated learning on larynx cancer patients from centres in three different countries.

METHODS

Data were obtained from 1821 larynx cancer patients treated with radiotherapy in three centres. Tumour volume was available for all 786 of the included patients. Parameter selection among eleven clinical and radiotherapy parameters were performed using best subset selection and cross-validation through the federated learning system, AusCAT. After parameter selection, β regression coefficients were estimated using bootstrap. Calibration plots were generated at 2 and 5-years survival, and inner and outer risk groups' Kaplan-Meier curves were compared to the Cox model prediction.

RESULTS

The best performing Cox model included log(GTV), performance status, age, smoking, haemoglobin and N-classification; however, the simplest model with similar statistical prediction power included log(GTV) and performance status only. The Harrell C-indices for the simplest model were for Odense, Christie and Liverpool 0.75[0.71-0.78], 0.65[0.59-0.71], and 0.69[0.59-0.77], respectively. The values are slightly higher for the full model with C-index 0.77[0.74-0.80], 0.67[0.62-0.73] and 0.71[0.61-0.80], respectively. Smoking during treatment has the same hazard as a ten-years older nonsmoking patient.

CONCLUSION

Without any patient-specific data leaving the hospitals, a stratified Cox regression model based on data from centres in three countries was developed without data leakage risks. The overall survival model is primarily driven by tumour volume and performance status.

Infrastructure platform for privacy-preserving distributed machine learning development of computer-assisted theragnostics in cancer

INTRODUCTION

Emerging evidence suggests that data-driven support tools have found their way into clinical decision-making in a number of areas, including cancer care. Improving them and widening their scope of availability in various differing clinical scenarios, including for prognostic models derived from retrospective data, requires co-ordinated data sharing between clinical centres, secondary analyses of large multi-institutional clinical trial data, or distributed (federated) learning infrastructures. A systematic approach to utilizing routinely collected data across cancer care clinics remains a significant challenge due to privacy, administrative and political barriers.

METHODS

An information technology infrastructure and web service software was developed and implemented which uses machine learning to construct clinical decision support systems in a privacy-preserving manner across datasets geographically distributed in different hospitals. The infrastructure was deployed in a network of Australian hospitals. A harmonized, international ontology-linked, set of lung cancer databases were built with the routine clinical and imaging data at each centre. The infrastructure was demonstrated with the development of logistic regression models to predict major cardiovascular events following radiation therapy.

RESULTS

The infrastructure implemented forms the basis of the Australian computer-assisted theragnostics (AusCAT) network for radiation oncology data extraction, reporting and distributed learning. Four radiation oncology departments (across seven hospitals) in New South Wales (NSW) participated in this demonstration study. Infrastructure was deployed at each centre and used to develop a model predicting for cardiovascular admission within a year of receiving curative radiotherapy for non-small cell lung cancer. A total of 10417 lung cancer patients were identified with 802 being eligible for the model. Twenty features were chosen for analysis from the clinical record and linked registries. After selection, 8 features were included and a logistic regression model achieved an area under the receiver operating characteristic (AUROC) curve of 0.70 and C-index of 0.65 on out-of-sample data.

CONCLUSION

The infrastructure developed was demonstrated to be usable in practice between clinical centres to harmonize routinely collected oncology data and develop models with federated learning. It provides a promising approach to enable further research studies in radiation oncology using real world clinical data.

Open-source distributed learning validation for a larynx cancer survival model following radiotherapy

INTRODUCTION

Prediction models are useful to design personalised treatment. However, safe and effective implementation relies on external validation. Retrospective data are available in many institutions, but sharing between institutions can be challenging due to patient data sensitivity and governance or legal barriers. This study validates a larynx cancer survival model performed using distributed learning without any sensitive data leaving the institution.

METHODS

Open-source distributed learning software based on a stratified Cox proportional hazard model was developed and used to validate the Egelmeer et al. MAASTRO survival model across two hospitals in two countries. The validation optimised a single scaling parameter multiplied by the original predicted prognostic index. All analyses and figures were based on the distributed system, ensuring no information leakage from the individual centres. All applied software is provided as freeware to facilitate distributed learning in other institutions.

RESULTS

1745 patients received radiotherapy for larynx cancer in the two centres from Jan 2005 to Dec 2018. Limiting to a maximum of one missing value in the parameters of the survival model reduced the cohort to 1095 patients. The Harrell C-index was 0.74 (CI95%, 0.71-0.76) and 0.70 (0.66-0.75) for the two centres. However, the model needed a scaling update. In addition, it was found that survival predictions of patients undergoing hypofractionation were less precise.

CONCLUSION

Open-source distributed learning software was able to validate, and suggest a minor update to the original survival model without central access to patient sensitive information. Even without the update, the original MAASTRO survival model of Egelmeer et al. performed reasonably well, providing similar results in this validation as in its original validation.

Newly Discovered Peptides from the Coral Heliofungia actiniformis Show Structural and Functional Diversity

Scleractinian corals are crucially important to the health of some of the world's most biodiverse, productive, and economically important marine habitats. Despite this importance, analysis of coral peptidomes is still in its infancy. Here we show that the tentacle extract from the stony coral Heliofungia actiniformis is rich in peptides with diverse and novel structures. We have characterized the sequences and three-dimensional structures of four new peptides, three of which have no known homologues. We show that a 2 kDa peptide, Hact-2, promotes significant cell proliferation on human cells and speculate this peptide may be involved in the remarkable regenerative capacity of corals. We found a 3 kDa peptide, Hact-3, encoded within a fascin-like domain, and homologues of Hact-3 are present in the genomes of other coral species. Two additional peptides, Hact-4 and Hact-SCRiP1, with limited sequence similarity, both contain a beta-defensin-like fold and highlight a structural link with the small cysteine-rich proteins (SCRiP) family of proteins found predominantly in corals. Our results provide a first glimpse into the remarkable and unexplored structural diversity of coral peptides, providing insight into their diversity and putative functions and, given the ancient lineage of corals, potential insight into the evolution of structural motifs.

Unclassified white matter disorders: A diagnostic journey requiring close collaboration between clinical and laboratory services

BACKGROUND

Next generation sequencing studies have revealed an ever-increasing number of causes for genetic disorders of central nervous system white matter. A substantial number of disorders are identifiable from their specific pattern of biochemical and/or imaging findings for which single gene testing may be indicated. Beyond this group, the causes of genetic white matter disorders are unclear and a broader approach to genomic testing is recommended.

AIM

This study aimed to identify the genetic causes for a group of individuals with unclassified white matter disorders with suspected genetic aetiology and highlight the investigations required when the initial testing is non-diagnostic.

METHODS

Twenty-six individuals from 22 families with unclassified white matter disorders underwent deep phenotyping and genome sequencing performed on trio, or larger, family groups. Functional studies and transcriptomics were used to resolve variants of uncertain significance with potential clinical relevance.

RESULTS

Causative or candidate variants were identified in 15/22 (68.2%) families. Six of the 15 implicated genes had been previously associated with white matter disease (COL4A1, NDUFV1, SLC17A5, TUBB4A, BOLA3, DARS2). Patients with variants in the latter two presented with an atypical phenotype. The other nine genes had not been specifically associated with white matter disease at the time of diagnosis and included genes associated with monogenic syndromes, developmental disorders, and developmental and epileptic encephalopathies (STAG2, LSS, FIG4, GLS, PMPCA, SPTBN1, AGO2, SCN2A, SCN8A). Consequently, only 46% of the diagnoses would have been made via a current leukodystrophy gene panel test.

DISCUSSION

These results confirm the importance of broad genomic testing for patients with white matter disorders. The high diagnostic yield reflects the integration of deep phenotyping, whole genome sequencing, trio analysis, functional studies, and transcriptomic analyses.

CONCLUSIONS

Genetic white matter disorders are genetically and phenotypically heterogeneous. Deep phenotyping together with a range of genomic technologies underpin the identification of causes of unclassified white matter disease. A molecular diagnosis is essential for prognostication, appropriate management, and accurate reproductive counseling.

Predicting 2-year survival in stage I-III non-small cell lung cancer: the development and validation of a scoring system from an Australian cohort

Background

There are limited data on survival prediction models in contemporary inoperable non-small cell lung cancer (NSCLC) patients. The objective of this study was to develop and validate a survival prediction model in a cohort of inoperable stage I-III NSCLC patients treated with radiotherapy.

Methods

Data from inoperable stage I-III NSCLC patients diagnosed from 1/1/2016 to 31/12/2017 were collected from three radiation oncology clinics. Patient, tumour and treatment-related variables were selected for model inclusion using univariate and multivariate analysis. Cox proportional hazards regression was used to develop a 2-year overall survival prediction model, the South West Sydney Model (SWSM) in one clinic (n = 117) and validated in the other clinics (n = 144). Model performance, assessed internally and on one independent dataset, was expressed as Harrell’s concordance index (c-index).

Results

The SWSM contained five variables: Eastern Cooperative Oncology Group performance status, diffusing capacity of the lung for carbon monoxide, histological diagnosis, tumour lobe and equivalent dose in 2 Gy fractions. The SWSM yielded a c-index of 0.70 on internal validation and 0.72 on external validation. Survival probability could be stratified into three groups using a risk score derived from the model.

Conclusions

A 2-year survival model with good discrimination was developed. The model included tumour lobe as a novel variable and has the potential to guide treatment decisions. Further validation is needed in a larger patient cohort.

Optimal and actual rates of Stereotactic Ablative Body Radiotherapy (SABR) utilisation for primary lung cancer in Australia

•

Stereotactic Ablative Body Radiotherapy (SABR) plays a major role in the management of early-stage non-small cell lung cancer (NSCLC).

•

An evidence-based model is developed to estimate optimal rates of lung SABR utilisation within the Australian population.

•

Optimal utilisation rates are compared against actual utilisation rates to evaluate service provision.

Background and purpose

Radiotherapy utilisation rates considerably vary across different countries and service providers, highlighting the need to establish reliable benchmarks against which utilisation rates can be assessed. Here, optimal utilisation rates of Stereotactic Ablative Body Radiotherapy (SABR) for lung cancer are estimated and compared against actual utilisation rates to identify potential shortfalls in service provision.

Materials and Methods

An evidence-based optimal utilisation model was constructed after reviewing practice guidelines and identifying indications for lung SABR based on the best available evidence. The proportions of patients likely to develop each indication were obtained, whenever possible, from Australian population-based studies. Sensitivity analysis was performed to account for variations in epidemiological data. Practice pattern studies were reviewed to obtain actual utilisation rates.

Results

A total of 6% of all lung cancer patients were estimated to optimally require SABR at least once during the course of their illness (95% CI: 4–6%). Optimal utilisation rates were estimated to be 32% for stage I and 10% for stage II NSCLC. Actual utilisation rates for stage I NSCLC varied between 6 and 20%. For patients with inoperable stage I, 27–74% received SABR compared to the estimated optimal rate of 82%.

Conclusion

The estimated optimal SABR utilisation rates for lung cancer can serve as useful benchmarks to highlight gaps in service delivery and help plan for more adequate and efficient provision of care. The model can be easily modified to determine optimal utilisation rates in other populations or updated to reflect any changes in practice guidelines or epidemiological data.

Assessing adherence and exploring barriers to provision of prescribed texture modifications for dysphagia in a residential aged care facility in rural Australia

PURPOSE

Purpose: Between 55-65% of residents living in residential aged care facilities (RACFs) experience dysphagia and are prescribed texture-modified diets by a speech-language pathologist (SLP). The aim of this study was to assess current adherence to prescribed texture modification for people with dysphagia; and explore barriers to implementation in a rural aged care setting.

METHOD

Method: Meal texture audits (N = 42) were completed with residents with dysphagia in a rural RACF who were prescribed texture-modified diets or fluids by a SLP. Semi-structured focus groups were conducted with nursing and food preparation staff (N = 11) to identify barriers to implementation.

RESULT

Result: Mealtime texture audits identified that 54.8% (n = 23) of residents' food modification requirements were incorrectly documented in the manual entry database (kitchen form) and 64.3% (n = 27) of meal trays contained foods that did not meet residents' dysphagia management plans. Focus group data revealed seven main themes impacting on the ability of staff to implement prescribed texture-modified diets. Complicated processes and communication between nursing, food services and SLP staff were identified as major barriers. These were complicated further by time pressures experienced by staff as well as staffing issues, resourcing of the kitchen, accommodating individual dietary preferences and the variety/presentation of dietary options at the aged care facility.Conclusion: There was low adherence to SLP prescribed texture-modified diets and fluids in the participating rural RACF. This study identified major barriers to implementing SLP prescribed texture-modified diets including complicated processes, communication breakdowns, time pressures and limited staffing. Implementation of an online menu management system and regular dysphagia-specific training may address barriers to communication and complicated paper-based menu systems and should be a priority for health services to ensure adequate dysphagia management.

Training radiomics-based CNNs for clinical outcome prediction: Challenges, strategies and findings

Radiological images play a central role in radiotherapy, especially in target volume delineation. Radiomic feature extraction has demonstrated its potential for predicting patient outcome and cancer risk assessment prior to treatment. However, inherent methodological challenges such as severe class imbalance, small training sample size, multi-centre data and weak correlation of image representations to outcomes are yet to be addressed adequately. Current radiomic analysis relies on segmented images (e.g., of tumours) for feature extraction, leading to loss of important context information in surrounding tissue. In this work, we examine the correlation between radiomics and clinical outcomes by combining two data modalities: pre-treatment computerized tomography (CT) imaging data and contours of segmented gross tumour volumes (GTVs). We focus on a clinical head & neck cancer dataset and design an efficient convolutional neural network (CNN) architecture together with appropriate machine learning strategies to cope with the challenges. During the training process on two cohorts, our algorithm learns to produce clinical outcome predictions by automatically extracting radiomic features. Test results on two other cohorts show state-of-the-art performance in predicting different clinical endpoints (i.e., distant metastasis: AUC = 0.91; loco-regional failure: AUC = 0.78; overall survival: AUC = 0.70 on segmented CT data) compared to prior studies. Furthermore, we also conduct extensive experiments both on the whole CT dataset and a combination of CT and GTV contours to investigate different learning strategies for this task. For example, further experiments indicate that overall survival prediction significantly improves to 0.83 AUC by combining CT and GTV contours as inputs, and the combination provides more intuitive visual explanations for patient outcome predictions.

Deletions in VANGL1 are a risk factor for antibody-mediated kidney disease

We identify an intronic deletion in VANGL1 that predisposes to renal injury in high risk populations through a kidney-intrinsic process. Half of all SLE patients develop nephritis, yet the predisposing mechanisms to kidney damage remain poorly understood. There is limited evidence of genetic contribution to specific organ involvement in SLE.1,2 We identify a large deletion in intron 7 of Van Gogh Like 1 (VANGL1), which associates with nephritis in SLE patients. The same deletion occurs at increased frequency in an indigenous population (Tiwi Islanders) with 10-fold higher rates of kidney disease compared with non-indigenous populations. Vangl1 hemizygosity in mice results in spontaneous IgA and IgG deposition within the glomerular mesangium in the absence of autoimmune nephritis. Serum transfer into B cell-deficient Vangl1+/- mice results in mesangial IgG deposition indicating that Ig deposits occur in a kidney-intrinsic fashion in the absence of Vangl1. These results suggest that Vangl1 acts in the kidney to prevent Ig deposits and its deficiency may trigger nephritis in individuals with SLE.

Implementation of the Australian Computer-Assisted Theragnostics (AusCAT) network for radiation oncology data extraction, reporting and distributed learning

INTRODUCTION

There is significant potential to analyse and model routinely collected data for radiotherapy patients to provide evidence to support clinical decisions, particularly where clinical trials evidence is limited or non-existent. However, in practice there are administrative, ethical, technical, logistical and legislative barriers to having coordinated data analysis platforms across radiation oncology centres.

METHODS

A distributed learning network of computer systems is presented, with software tools to extract and report on oncology data and to enable statistical model development. A distributed or federated learning approach keeps data in the local centre, but models are developed from the entire cohort.

RESULTS

The feasibility of this approach is demonstrated across six Australian oncology centres, using routinely collected lung cancer data from oncology information systems. The infrastructure was used to validate and develop machine learning for model-based clinical decision support and for one centre to assess patient eligibility criteria for two major lung cancer radiotherapy clinical trials (RTOG-9410, RTOG-0617). External validation of a 2-year overall survival model for non-small cell lung cancer (NSCLC) gave an AUC of 0.65 and C-index of 0.62 across the network. For one centre, 65% of Stage III NSCLC patients did not meet eligibility criteria for either of the two practice-changing clinical trials, and these patients had poorer survival than eligible patients (10.6 m vs. 15.8 m, P = 0.024).

CONCLUSION

Population-based studies on routine data are possible using a distributed learning approach. This has the potential for decision support models for patients for whom supporting clinical trial evidence is not applicable.

Deep learning for segmentation in radiation therapy planning: a review

Segmentation of organs and structures, as either targets or organs-at-risk, has a significant influence on the success of radiation therapy. Manual segmentation is a tedious and time-consuming task for clinicians, and inter-observer variability can affect the outcomes of radiation therapy. The recent hype over deep neural networks has added many powerful auto-segmentation methods as variations of convolutional neural networks (CNN). This paper presents a descriptive review of the literature on deep learning techniques for segmentation in radiation therapy planning. The most common CNN architecture across the four clinical sub sites considered was U-net, with the majority of deep learning segmentation articles focussed on head and neck normal tissue structures. The most common data sets were CT images from an inhouse source, along with some public data sets. N-fold cross-validation was commonly employed; however, not all work separated training, test and validation data sets. This area of research is expanding rapidly. To facilitate comparisons of proposed methods and benchmarking, consistent use of appropriate metrics and independent validation should be carefully considered.

Machine learning applications in radiation oncology

Machine learning technology has a growing impact on radiation oncology with an increasing presence in research and industry. The prevalence of diverse data including 3D imaging and the 3D radiation dose delivery presents potential for future automation and scope for treatment improvements for cancer patients. Harnessing this potential requires standardization of tools and data, and focused collaboration between fields of expertise. The rapid advancement of radiation oncology treatment technologies presents opportunities for machine learning integration with investments targeted towards data quality, data extraction, software, and engagement with clinical expertise. In this review, we provide an overview of machine learning concepts before reviewing advances in applying machine learning to radiation oncology and integrating these techniques into the radiation oncology workflows. Several key areas are outlined in the radiation oncology workflow where machine learning has been applied and where it can have a significant impact in terms of efficiency, consistency in treatment and overall treatment outcomes. This review highlights that machine learning has key early applications in radiation oncology due to the repetitive nature of many tasks that also currently have human review. Standardized data management of routinely collected imaging and radiation dose data are also highlighted as enabling engagement in research utilizing machine learning and the ability integrate these technologies into clinical workflow to benefit patients. Physicists need to be part of the conversation to facilitate this technical integration.

A netrin domain-containing protein secreted by the human hookworm Necator americanus protects against CD4 T cell transfer colitis

The symbiotic relationships shared between humans and their gastrointestinal parasites present opportunities to discover novel therapies for inflammatory diseases. A prime example of this phenomenon is the interaction of humans and roundworms such as the hookworm, Necator americanus. Epidemiological observations, animal studies and clinical trials using experimental human hookworm infection show that hookworms can suppress inflammation in a safe and well-tolerated way, and that the key to their immunomodulatory properties lies within their secreted proteome. Herein we describe the identification of 2 netrin domain-containing proteins from the N. americanus secretome, and explore their potential in treating intestinal inflammation in mouse models of ulcerative colitis. One of these proteins, subsequently named Na-AIP-1, was effective at suppressing disease when administered prophylactically in the acute TNBS-induced model of colitis. This protective effect was validated in the more robust CD4 T cell transfer model of chronic colitis, where prophylactic Na-AIP-1 reduced T-cell-dependent type-1 cytokine responses in the intestine and the associated intestinal pathology. Mechanistic studies revealed that depletion of CD11c+ cells abrogated the protective anticolitic effect of Na-AIP-1. Next generation sequencing of colon tissue in the T-cell transfer model of colitis revealed that Na-AIP-1 induced a transcriptomic profile associated with the downregulation of metabolic and signaling pathways involved in type-1 inflammation, notably TNF. Finally, co-culture of Na-AIP-1 with a human monocyte-derived M1 macrophage cell line resulted in significantly reduced secretion of TNF. Na-AIP-1 is now a candidate for clinical development as a novel therapeutic for the treatment of human inflammatory bowel diseases.

Impact of age on catheter ablation of premature ventricular contractions

Funding Acknowledgements

Type of funding sources: None.

Introduction

Catheter ablation (CA) of frequent premature ventricular contractions (PVC) is increasingly performed in older patients as the population ages.

Purpose

The purpose of this study was to assess the impact of age on procedural characteristics, safety and efficacy on PVC ablations.

Methods

Consecutive patients with symptomatic PVCs undergoing CA between 2015 and 2020 were evaluated. Acute ablation success was defined as the elimination of PVCs at the end of the procedure. Sustained success was defined as an elimination of symptoms, and  ≥80% reduction of PVC burden determined by Holter-ECG during long-term follow. Patients were sub-grouped based on age (&lt; 65 years vs. ≥ 65 years).

Results

A total of 114 patients were enrolled (median age 64 years, 71% males) and followed up for a median duration of 228 days. Baseline and procedural data were similar in both age groups. A left-sided origin of PVCs was more frequently observed in the elderly patient group compared to younger patients (83% vs. 67%, p = 0.04, Figure 1). The median procedure time was significantly shorter in elderly patients (160 min vs. 193 min, p = 0.02). The rates of both acute (86% vs. 92%, p = 0.32) and sustained success (70% vs. 71%, p = 0.90) were similar between groups. Complications rates (3.7%) did not differ between the two groups.

Conclusion

In a large series of patients with a variety of underlying arrhythmia substrates, similar rates of acute procedural success, complications, and ventricular arrhythmia-free-survival were observed after CA of PVCs. Older age alone should not be a reason to withhold CA of PVCs. Abstract Figure 1

Comprehensive analysis of the secreted proteome of adult Necator americanus hookworms

The human hookworm Necator americanus infects more than 400 million people worldwide, contributing substantially to the poverty in these regions. Adult stage N. americanus live in the small intestine of the human host where they inject excretory/secretory (ES) products into the mucosa. ES products have been characterized at the proteome level for a number of animal hookworm species, but until now, the difficulty in obtaining sufficient live N. americanus has been an obstacle in characterizing the secretome of this important human pathogen. Herein we describe the ES proteome of N. americanus and utilize this information along with RNA Seq data to conduct the first proteogenomic analysis of a parasitic helminth, significantly improving the available genome and thereby generating a robust description of the parasite secretome. The genome annotation resulted in a revised prediction of 3,425 fewer genes than initially reported, accompanied by a significant increase in the number of exons and introns, total gene length and the percentage of the genome covered by genes. Almost 200 ES proteins were identified by LC-MS/MS with SCP/TAPS proteins, ‘hypothetical’ proteins and proteases among the most abundant families. These proteins were compared to commonly used model species of human parasitic infections, including Ancylostoma caninum, Nippostrongylus brasiliensis and Heligmosomoides polygyrus. SCP/TAPS proteins are immunogenic in nematode infections, so we expressed four of those identified in this study in recombinant form and showed that they are all recognized to varying degrees by serum antibodies from hookworm-infected subjects from a disease-endemic area of Brazil. Our findings provide valuable information on important families of proteins with both known and unknown functions that could be instrumental in host-parasite interactions, including protein families that might be key for parasite survival in the onslaught of robust immune responses, as well as vaccine and diagnostic targets.

Hookworms infect hundreds of millions of people in tropical regions of the world. Adult worms reside in the small bowel where they feed on blood, causing iron-deficiency anemia when present in large numbers and contributing substantially to the poverty in these regions. Hookworms inject excretory/secretory (ES) products into the gut tissue when they feed, and while the protein constituents of ES products have been characterized for a number of animal hookworm species, difficulty in obtaining sufficient live human hookworms has thus far precluded characterization of the secreted proteome. Herein we describe the ES proteins of the major human hookworm, Necator americanus, and utilize this information to significantly improve the available genome sequence. Almost 200 ES proteins were identified and compared to the secreted proteomes of other parasitic roundworms to provide a molecular snapshot of the host-parasite interface. We produced recombinant forms of some of the identified proteins and showed that they are all recognized to varying degrees by antibodies from hookworm-infected subjects. Our work sheds light on important families of proteins that might be key for parasite survival in the human host, and presents a dataset that can now be mined in the search for vaccine, drug and diagnostic targets.

Multicenter evaluation of MRI-based radiomic features: A phantom study

INTRODUCTION

This work describes the development of a novel radiomics phantom designed for magnetic resonance imaging (MRI) that can be used in a multicenter setting. The purpose of this study is to assess the stability and reproducibility of MRI-based radiomic features using this phantom across different MRI scanners.

METHODS & MATERIALS

A set of phantoms were three-dimensional (3D) printed using MRI visible materials. One set of phantoms were imaged on seven MRI scanners and one was imaged on one MRI scanner. Radiomics analysis of the phantoms, which included first-order features, shape and texture features was performed. Intraclass correlation coefficient (ICC) was used to assess the stability of radiomic features across eight scanners and the reproducibility of two printed models on one scanner. Coefficient of variation (COV) was used to assess the reproducibility of radiomics measurements in the phantom on a single scanner.

RESULTS

The phantom models provide sufficient signal-to-noise and contrast in all the tumor models permitting robust automatic segmentation. During a 12-month period of monitoring, the phantom material was stable with T1 and T2 of 150.7 ± 6.7 ms and 56.1 ± 3.9 ms, respectively. Of all the radiomic features computed, 34 of 69 had COV < 10%. Features from first-order statistics were the most robust in stability across the eight scanners with eight of 12 (67%) having high stability. About 29 of 50 (58%) texture features had high stability and no shape features had high stability features across the eight scanners.

CONCLUSION

A novel MRI radiomics phantom has been developed to assess the reproducibility and stability of MRI-based radiomic features across multiple institutions. The variation in radiomic feature stability demonstrates the need for caution when interpreting these features for clinical studies.

The Rise of Non-Tuberculosis Mycobacterial Lung Disease

The incidence and number of deaths from non-tuberculous mycobacterial (NTM) disease have been steadily increasing globally. These lesser known “cousins” of Mycobacterium tuberculosis (TB) were once thought to be harmless environmental saprophytics and only dangerous to individuals with defective lung structure or the immunosuppressed. However, NTM are now commonly infecting seemingly immune competent children and adults at increasing rates through pulmonary infection. This is of concern as the pathology of NTM is difficult to treat. Indeed, NTM have become extremely antibiotic resistant, and now have been found to be internationally dispersed through person-to-person contact. The reasons behind this NTM increase are only beginning to be elucidated. Solutions to the problem are needed given NTM disease is more common in the tropics. Importantly, 40% of the world's population live in the tropics and due to climate change, the Tropics are expanding which will increase NTM infection regions. This review catalogs the global and economic disease burden, at risk populations, treatment options, host-bacterial interaction, immune dynamics, recent developments and research priorities for NTM disease.

The vascular access questionnaire: a single centre UK experience

Background

Haemodialysis is capable of prolonging life in patients with end stage renal disease, however this therapy comes with significant negative impact on quality of life. For patients requiring haemodialysis, the need for an adequately functioning vascular access (VA) is an everyday concern. The Vascular Access Questionnaire (VAQ) provides a mechanism for identifying and scoring factors in haemodialysis that impact on patients’ quality of life and perception of their therapy.

Methods

Between April 2017–18 the VAQ was administered to prevalent haemodialysis patients at 10 units in the West Midlands via structured interviews.

Results

749 of 920 potentially eligible patients completed the survey. The mean VAQ score was seen to improve significantly with age (7.7 in < 55 vs. 3.8 in 75+) and the duration of access (8.9 if less than 1 month old vs. 5.0 at a year). Better average scores were demonstrated for Arteriovenous fistulas (AVF) than other modalities (AVF 5.1 vs. AVG (arteriovenous grafts) 7.2 vs. CVC (central venous catheter) 6.6). There was no significant difference in scores between fistulas on non-dominant or dominant arms, with both having a mean of 5.2 (p = 0.341).

Conclusions

Overall, better satisfaction scores were seen in AVF. The presence of an AVF on the non-dominant arm was not a concern for the majority of patients and did not affect the VAQ score. A number of factors were identified that can influence VAQ satisfaction score.

Electronic supplementary material

The online version of this article (10.1186/s12882-019-1493-9) contains supplementary material, which is available to authorized users.

Primary Patency Rates of AV Fistulae and the Effect of Patient Variables

Background

DOQI (The Dialysis Outcomes Quality Initiative) recommend 40% of prevalent renal failure patients should be undergoing hemodialysis (HD) using autogenous arteriovenous fistulae (AVF). The aim of this study is to assess the primary patency rates of wrist and elbow fistulae, and to examine how patient variables influence the success of a fistula. In addition, an attempt has been made to address the main issue of survival rates in this high risk patient population.

Methods

A retrospective study was performed on all patients in the University Hospital of North Staffordshire who underwent creation of a wrist or elbow fistula for HD. During the study period 289 primary AVFs were created. In all, 210 AVF were sited at the wrist and 79 at the elbow. Follow-up ranged from 3 months to 4 yrs. Primary patency and patient death, transplant and transfer were taken as end points. Patient survival was defined as time of fistula creation to patient death. Actuarial survival was calculated using Kaplan-Meier survival analyses, with differences between groups determined using log rank analysis, and statistical significance obtained using X2 tests.

Results

Primary patency for wrist fistulae was 49, 41 and 32% at 6, 12 and 24 months, respectively, and 57, 51 and 38% for elbow fistulae. Regression analysis showed fistula survival to be significantly greater in males than in females (p=0.023). Fistula survival rates in non-diabetics patients were higher than in patients with diabetes however, this was not significant (p=0.11); (54, 48 and 34% in diabetics compared to 45, 35 and 26% in non-diabetics at 6, 12 and 24 months, respectively). Age did not influence fistula survival; however, it did affect patient survival. Patient survival was 90, 74 and 56% at 1, 2 and 3 yrs, respectively, and in >60s fell to 86, 71 and 50%. Overall 74/245 (30%) patients died.

Conclusion

These results suggest that overall primary patency rates for wrist and elbow fistulae are comparable to similar studies at 6, 12 and 24 months. Fistula survival after this period is dictated by poor patient survival. Our findings suggest that creation of primary vascular access at the elbow in older females and diabetics may be associated with better results.

A Stuck Hemodialysis Central venous Catheter

Background

A growing number of hemodialysis patients are dependent upon central venous catheters (CVCs) for long-term vascular access. Although many complications of CVCs have been documented, the phenomenon of the stuck catheter is described relatively infrequently.

Case report

We describe a case where attempts to remove the line by exploration of the jugular insertion site in theater were unsuccessful and the line was internalized.

Discussion

The case is then discussed with all available cases in the literature to suggest principles of managing and preventing the stuck catheter phenomenon.

MED13L-related intellectual disability: involvement of missense variants and delineation of the phenotype

Molecular anomalies in MED13L, leading to haploinsufficiency, have been reported in patients with moderate to severe intellectual disability (ID) and distinct facial features, with or without congenital heart defects. Phenotype of the patients was referred to "MED13L haploinsufficiency syndrome." Missense variants in MED13L were already previously described to cause the MED13L-related syndrome, but only in a limited number of patients. Here we report 36 patients with MED13L molecular anomaly, recruited through an international collaboration between centers of expertise for developmental anomalies. All patients presented with intellectual disability and severe language impairment. Hypotonia, ataxia, and recognizable facial gestalt were frequent findings, but not congenital heart defects. We identified seven de novo missense variations, in addition to protein-truncating variants and intragenic deletions. Missense variants clustered in two mutation hot-spots, i.e., exons 15-17 and 25-31. We found that patients carrying missense mutations had more frequently epilepsy and showed a more severe phenotype. This study ascertains missense variations in MED13L as a cause for MED13L-related intellectual disability and improves the clinical delineation of the condition.

A prediction model for early death in non-small cell lung cancer patients following curative-intent chemoradiotherapy

BACKGROUND

Early death after a treatment can be seen as a therapeutic failure. Accurate prediction of patients at risk for early mortality is crucial to avoid unnecessary harm and reducing costs. The goal of our work is two-fold: first, to evaluate the performance of a previously published model for early death in our cohorts. Second, to develop a prognostic model for early death prediction following radiotherapy.

MATERIAL AND METHODS

Patients with NSCLC treated with chemoradiotherapy or radiotherapy alone were included in this study. Four different cohorts from different countries were available for this work (N = 1540). The previous model used age, gender, performance status, tumor stage, income deprivation, no previous treatment given (yes/no) and body mass index to make predictions. A random forest model was developed by learning on the Maastro cohort (N = 698). The new model used performance status, age, gender, T and N stage, total tumor volume (cc), total tumor dose (Gy) and chemotherapy timing (none, sequential, concurrent) to make predictions. Death within 4 months of receiving the first radiotherapy fraction was used as the outcome.

RESULTS

Early death rates ranged from 6 to 11% within the four cohorts. The previous model performed with AUC values ranging from 0.54 to 0.64 on the validation cohorts. Our newly developed model had improved AUC values ranging from 0.62 to 0.71 on the validation cohorts.

CONCLUSIONS

Using advanced machine learning methods and informative variables, prognostic models for early mortality can be developed. Development of accurate prognostic tools for early mortality is important to inform patients about treatment options and optimize care.