Prognostic factors analysis for oral cavity cancer survival in the Netherlands and Taiwan using a privacy-preserving federated infrastructure

Advancing healthcare through data: the BETTER project's vision for distributed analytics

Introduction

Data-driven medicine is essential for enhancing the accessibility and quality of the healthcare system. The availability of data plays a crucial role in achieving this goal.

Methods

We propose implementing a robust data infrastructure of FAIRification and data fusion for clinical, genomic, and imaging data. This will be embedded within the framework of a distributed analytics platform for healthcare data analysis, utilizing the Personal Health Train paradigm.

Results

This infrastructure will ensure the findability, accessibility, interoperability, and reusability of data, metadata, and results among multiple medical centers participating in the BETTER Horizon Europe project. The project focuses on studying rare diseases, such as intellectual disability and inherited retinal dystrophies.

Conclusion

The anticipated impacts will benefit a wide range of healthcare practitioners and potentially influence health policymakers.

An Overview of Real-World Data Infrastructure for Cancer Research

AIMS

There is increasing interest in the opportunities offered by Real World Data (RWD) to provide evidence where clinical trial data does not exist, but access to appropriate data sources is frequently cited as a barrier to RWD research. This paper discusses current RWD resources and how they can be accessed for cancer research.

MATERIALS AND METHODS

There has been significant progress on facilitating RWD access in the last few years across a range of scales, from local hospital research databases, through regional care records and national repositories, to the impact of federated learning approaches on internationally collaborative studies. We use a series of case studies, principally from the UK, to illustrate how RWD can be accessed for research and healthcare improvement at each of these scales.

RESULTS

For each example we discuss infrastructure and governance requirements with the aim of encouraging further work in this space that will help to fill evidence gaps in oncology.

CONCLUSION

There are challenges, but real-world data research across a range of scales is already a reality. Taking advantage of the current generation of data sources requires researchers to carefully define their research question and the scale at which it would be best addressed.

Factors influencing the 5-year survival rate of oral cancer patients in the Mongolian population: a retrospective cohort study

Introduction

The high mortality rate of head and neck cancers, particularly oral cancer, poses a significant health challenge in developing nations such as Mongolia. This retrospective survival analysis study was conducted to identify factors influencing the 5-year survival rate of oral squamous cell carcinoma patients.

Methods

The study analyzed data from 173 patients diagnosed with oral squamous cell carcinoma, including multiple variables such as age, gender, residence, education, tobacco and alcohol consumption, oral health indicators, family history, precancerous conditions, cancer characteristics, treatment, rehabilitation, cancer recurrence, and 5-year survival. Survival analysis was conducted using the Kaplan-Meier method, and STATA was used for statistical analysis.

Results

The study revealed a 5-year survival rate of 50.3% for oral cancer patients, with a survival rate of 38% for tongue cancer patients. Age, residence, cancer stage, and cancer recurrence were identified as significant survival predictors. Compared to those aged 60 or younger, the hazard ratio (HR) for patients aged 61 or older was 1.52. Survival was associated with female gender (HR = 0.47, CI = 0.29-0.77). Urban residence was associated with decreased survival (HR = 1.92, CI = 1.22-3.05). Significantly worse survival was associated with the presence of cancer recurrence (HR = 1.99, CI = 1.15-3.04). Oral cancer patients in stage IV had a fourfold higher risk of mortality compared to those in stage I (HR = 4.08, CI = 1.2-13.84).

Conclusion

This research highlights the influence of age, urban habitation, and cancer recurrence on oral cancer survival. Age, urban residence, and cancer recurrence were all associated with decreased survival, whereas cancer at stage IV substantially increased the risk of death. The significance of early detection, treatment, and active surveillance to identify oral cancer at an early stage is highlighted by these findings. Compared to industrialized nations, Mongolia's lower oral cancer survival rates emphasize the need to increase public awareness and education. A comprehensive approach is required to improve oral cancer patient survival rates and quality of life, including emphasizing early detection through active surveillance, implementing preventive measures, and advancing cancer education initiatives.

Federated and distributed learning applications for electronic health records and structured medical data: a scoping review

OBJECTIVES

Federated learning (FL) has gained popularity in clinical research in recent years to facilitate privacy-preserving collaboration. Structured data, one of the most prevalent forms of clinical data, has experienced significant growth in volume concurrently, notably with the widespread adoption of electronic health records in clinical practice. This review examines FL applications on structured medical data, identifies contemporary limitations, and discusses potential innovations.

MATERIALS AND METHODS

We searched 5 databases, SCOPUS, MEDLINE, Web of Science, Embase, and CINAHL, to identify articles that applied FL to structured medical data and reported results following the PRISMA guidelines. Each selected publication was evaluated from 3 primary perspectives, including data quality, modeling strategies, and FL frameworks.

RESULTS

Out of the 1193 papers screened, 34 met the inclusion criteria, with each article consisting of one or more studies that used FL to handle structured clinical/medical data. Of these, 24 utilized data acquired from electronic health records, with clinical predictions and association studies being the most common clinical research tasks that FL was applied to. Only one article exclusively explored the vertical FL setting, while the remaining 33 explored the horizontal FL setting, with only 14 discussing comparisons between single-site (local) and FL (global) analysis.

CONCLUSIONS

The existing FL applications on structured medical data lack sufficient evaluations of clinically meaningful benefits, particularly when compared to single-site analyses. Therefore, it is crucial for future FL applications to prioritize clinical motivations and develop designs and methodologies that can effectively support and aid clinical practice and research.

Mapping the Scientific Landscape of Bacterial Influence on Oral Cancer: A Bibliometric Analysis of the Last Decade's Medical Progress

The research domain investigating bacterial factors in the development of oral cancer from January 2013 to December 2022 was examined with a bibliometric analysis. A bibliometric analysis is a mathematical and statistical method used to examine extensive datasets. It assesses the connections between prolific authors, journals, institutions, and countries while also identifying commonly used keywords. A comprehensive search strategy identified 167 relevant articles, revealing a progressive increase in publications and citations over time. China and the United States were the leading countries in research productivity, while Harvard University and the University of Helsinki were prominent affiliations. Prolific authors such as Nezar Al-Hebshi, Tsute Chen, and Yaping Pan were identified. The analysis also highlights the contributions of different journals and identifies the top 10 most cited articles in the field, all of which focus primarily on molecular research. The article of the highest citation explored the role of a Fusobacterium nucleatum surface protein in tumor immune evasion. Other top-cited articles investigated the correlation between the oral bacteriome and cancer using 16S rRNA amplicon sequencing, showing microbial shifts associated with oral cancer development. The functional prediction analysis used by recent studies has further revealed an inflammatory bacteriome associated with carcinogenesis. Furthermore, a keyword analysis reveals four distinct research themes: cancer mechanisms, periodontitis and microbiome, inflammation and Fusobacterium, and risk factors. This analysis provides an objective assessment of the research landscape, offers valuable information, and serves as a resource for researchers to advance knowledge and collaboration in the search for the influence of bacteria on the prevention, diagnosis, and treatment of oral cancer.

Head and neck cancers survival in Europe, Taiwan, and Japan: results from RARECAREnet Asia based on a privacy-preserving federated infrastructure

Background

The head and neck cancers (HNCs) incidence differs between Europe and East Asia. Our objective was to determine whether survival of HNC also differs between European and Asian countries.

Methods

We used population-based cancer registry data to calculate 5-year relative survival (RS) for the oral cavity, hypopharynx, larynx, nasal cavity, and major salivary gland in Europe, Taiwan, and Japan. We modeled RS with a generalized linear model adjusting for time since diagnosis, sex, age, subsite, and histological grouping. Analyses were performed using federated learning, which enables analyses without sharing sensitive data.

Findings

Five-year RS for HNC varied between geographical areas. For each HNC site, Europe had a lower RS than both Japan and Taiwan. HNC subsites and histologies distribution and survival differed between the three areas. Differences between Europe and both Asian countries persisted even after adjustments for all HNC sites but nasal cavity and paranasal sinuses, when comparing Europe and Taiwan.

Interpretation

Survival differences can be attributed to different factors including different period of diagnosis, more advanced stage at diagnosis, or different availability/access of treatment. Cancer registries did not have stage and treatment information to further explore the reasons of the observed survival differences. Our analyses have confirmed federated learning as a feasible approach for data analyses that addresses the challenges of data sharing and urge for further collaborative studies including relevant prognostic factors.

Federated benchmarking of medical artificial intelligence with MedPerf

Medical artificial intelligence (AI) has tremendous potential to advance healthcare by supporting and contributing to the evidence-based practice of medicine, personalizing patient treatment, reducing costs, and improving both healthcare provider and patient experience. Unlocking this potential requires systematic, quantitative evaluation of the performance of medical AI models on large-scale, heterogeneous data capturing diverse patient populations. Here, to meet this need, we introduce MedPerf, an open platform for benchmarking AI models in the medical domain. MedPerf focuses on enabling federated evaluation of AI models, by securely distributing them to different facilities, such as healthcare organizations. This process of bringing the model to the data empowers each facility to assess and verify the performance of AI models in an efficient and human-supervised process, while prioritizing privacy. We describe the current challenges healthcare and AI communities face, the need for an open platform, the design philosophy of MedPerf, its current implementation status and real-world deployment, our roadmap and, importantly, the use of MedPerf with multiple international institutions within cloud-based technology and on-premises scenarios. Finally, we welcome new contributions by researchers and organizations to further strengthen MedPerf as an open benchmarking platform.

Being Bayesian in the 2020s: opportunities and challenges in the practice of modern applied Bayesian statistics

Building on a strong foundation of philosophy, theory, methods and computation over the past three decades, Bayesian approaches are now an integral part of the toolkit for most statisticians and data scientists. Whether they are dedicated Bayesians or opportunistic users, applied professionals can now reap many of the benefits afforded by the Bayesian paradigm. In this paper, we touch on six modern opportunities and challenges in applied Bayesian statistics: intelligent data collection, new data sources, federated analysis, inference for implicit models, model transfer and purposeful software products. This article is part of the theme issue 'Bayesian inference: challenges, perspectives, and prospects'.

A federated approach to identify women with early-stage cervical cancer at low risk of lymph node metastases

OBJECTIVE

Lymph node metastases (pN+) in presumed early-stage cervical cancer negatively impact prognosis. Using federated learning, we aimed to develop a tool to identify a group of women at low risk of pN+, to guide the shared decision-making process concerning the extent of lymph node dissection.

METHODS

Women with cervical cancer between 2005 and 2020 were identified retrospectively from population-based registries: the Danish Gynaecological Cancer Database, Swedish Quality Registry for Gynaecologic Cancer and Netherlands Cancer Registry. Inclusion criteria were: squamous cell carcinoma, adenocarcinoma or adenosquamous carcinoma; The International Federation of Gynecology and Obstetrics 2009 IA2, IB1 and IIA1; treatment with radical hysterectomy and pelvic lymph node assessment. We applied privacy-preserving federated logistic regression to identify risk factors of pN+. Significant factors were used to stratify the risk of pN+.

RESULTS

We included 3606 women (pN+ 11%). The most important risk factors of pN+ were lymphovascular space invasion (LVSI) (odds ratio [OR] 5.16, 95% confidence interval [CI], 4.59-5.79), tumour size 21-40 mm (OR 2.14, 95% CI, 1.89-2.43) and depth of invasion>10 mm (OR 1.81, 95% CI, 1.59-2.08). A group of 1469 women (41%)-with tumours without LVSI, tumour size ≤20 mm, and depth of invasion ≤10 mm-had a very low risk of pN+ (2.4%, 95% CI, 1.7-3.3%).

CONCLUSION

Early-stage cervical cancer without LVSI, a tumour size ≤20 mm and depth of invasion ≤10 mm, confers a low risk of pN+. Based on an international privacy-preserving analysis, we developed a useful tool to guide the shared decision-making process regarding lymph node dissection.

Speech and Swallowing Rehabilitation Potentially Decreases Body Weight Loss and Improves Survival in Head and Neck Cancer Survivors

This retrospective observational cohort study aims to assess the outcomes and associated factors in head and neck cancer (HNC) survivors with dysphagia, and to investigate the relationship between outcomes and speech and swallowing rehabilitation (SSR). We enrolled patients who were diagnosed with HNC between October 2016 and July 2018; we included 393 patients who developed dysphagia after definite treatment and were referred to speech-language pathologists (SLPs). We then classified patients into groups according to whether they received SSR. We used the clinical variables-including age, sex, site of malignancy, cancer stage, treatment modality, SSR, initial ECOG score, initial KPS, initial body weight (BW), and initial BMI-to evaluate the association between the percentage of BW change and overall survival (OS). There were 152 (39%) and 241 (61%) patients who received and did not receive SSR, respectively. In multivariate linear regression, SSR was significantly associated with percentage change in BW at 3 months post-treatment. Having SSR was positively associated with the percentage change in BW and decreased the BW loss [β coefficient (95% CIs) = 2.53 (0.92 to 4.14)] compared to having no SSR. In the multivariate Cox regression, SSR was an independent factor for OS. Compared to no SSR, the hazard ratio (95% CIs) for patients who received SSR was 0.48 (0.31 to 0.74). SSR helps to avoid BW loss and increases overall survival. HNC patients who develop dysphagia after treatment should be encouraged to participate in SSR.

Immunity-related long noncoding RNA WDFY3-AS2 inhibited cell proliferation and metastasis through Wnt/β-catenin signaling in oral squamous cell carcinoma

OBJECTIVE

Long noncoding RNA WDFY3-AS2 has been shown to play dual roles in the modulation of cancer progression. This study aimed at clarifying the biological role of WDFY3-AS2 as well as the association between WDFY3-AS2 expression, β-catenin expression, and OSCC immunity in oral squamous cell carcinoma (OSCC).

DESIGN

Bioinformatics analyses, CCK8, EdU, wound healing, transwell, RT-qPCR, western blot, immunofluorescence, in situ hybridization, and immunohistochemistry assays were adopted for exploring the role of WDFY3-AS2 in OSCC.

RESULTS

Bioinformatics analyses showed that WDFY3-AS2 conferred a poor prognosis for OSCC patients. Further analyses identified WDFY3-AS2 as an independent prognostic indicator for OSCC. Moreover, silencing WDFY3-AS2 inhibits OSCC cell proliferation, migration and invasion. Gene set enrichment analysis indicated that WDFY3-AS2 participated in the regulation of Wnt signaling. In addition, WDFY3-AS2 expression was positively associated with β-catenin mRNA levels, the key component of Wnt signaling. Interestingly, WDFY3-AS2 knockdown inhibited β-catenin expression and nuclear translocation, thus suppressing OSCC progression through Wnt signaling. Furthermore, WDFY3-AS2 expression correlated with an immunosuppressive phenotype in the tumor immune microenvironment. In situ hybridization and immunohistochemistry verified that WDFY3-AS2 was positively associated with total and nuclear β-catenin protein levels and negatively associated with CD4 expression.

CONCLUSIONS

This study demonstrates that the immunity-associated WDFY3-AS2 augments OSCC proliferation and metastasis through Wnt/β-catenin signaling and may serve as a novel treatment target and a new prognostic factor for OSCC.

A Comparative Study of Multiple Deep Learning Models Based on Multi-Input Resolution for Breast Ultrasound Images

Purpose

The purpose of this study was to explore the performance of different parameter combinations of deep learning (DL) models (Xception, DenseNet121, MobileNet, ResNet50 and EfficientNetB0) and input image resolutions (REZs) (224 × 224, 320 × 320 and 488 × 488 pixels) for breast cancer diagnosis.

Methods

This multicenter study retrospectively studied gray-scale ultrasound breast images enrolled from two Chinese hospitals. The data are divided into training, validation, internal testing and external testing set. Three-hundreds images were randomly selected for the physician-AI comparison. The Wilcoxon test was used to compare the diagnose error of physicians and models under P=0.05 and 0.10 significance level. The specificity, sensitivity, accuracy, area under the curve (AUC) were used as primary evaluation metrics.

Results

A total of 13,684 images of 3447 female patients are finally included. In external test the 224 and 320 REZ achieve the best performance in MobileNet and EfficientNetB0 respectively (AUC: 0.893 and 0.907). Meanwhile, 448 REZ achieve the best performance in Xception, DenseNet121 and ResNet50 (AUC: 0.900, 0.883 and 0.871 respectively). In physician-AI test set, the 320 REZ for EfficientNetB0 (AUC: 0.896, P < 0.1) is better than senior physicians. Besides, the 224 REZ for MobileNet (AUC: 0.878, P < 0.1), 448 REZ for Xception (AUC: 0.895, P < 0.1) are better than junior physicians. While the 448 REZ for DenseNet121 (AUC: 0.880, P < 0.05) and ResNet50 (AUC: 0.838, P < 0.05) are only better than entry physicians.

Conclusion

Based on the gray-scale ultrasound breast images, we obtained the best DL combination which was better than the physicians.

Accurate training of the Cox proportional hazards model on vertically-partitioned data while preserving privacy

BACKGROUND

Analysing distributed medical data is challenging because of data sensitivity and various regulations to access and combine data. Some privacy-preserving methods are known for analyzing horizontally-partitioned data, where different organisations have similar data on disjoint sets of people. Technically more challenging is the case of vertically-partitioned data, dealing with data on overlapping sets of people. We use an emerging technology based on cryptographic techniques called secure multi-party computation (MPC), and apply it to perform privacy-preserving survival analysis on vertically-distributed data by means of the Cox proportional hazards (CPH) model. Both MPC and CPH are explained.

METHODS

We use a Newton-Raphson solver to securely train the CPH model with MPC, jointly with all data holders, without revealing any sensitive data. In order to securely compute the log-partial likelihood in each iteration, we run into several technical challenges to preserve the efficiency and security of our solution. To tackle these technical challenges, we generalize a cryptographic protocol for securely computing the inverse of the Hessian matrix and develop a new method for securely computing exponentiations. A theoretical complexity estimate is given to get insight into the computational and communication effort that is needed.

RESULTS

Our secure solution is implemented in a setting with three different machines, each presenting a different data holder, which can communicate through the internet. The MPyC platform is used for implementing this privacy-preserving solution to obtain the CPH model. We test the accuracy and computation time of our methods on three standard benchmark survival datasets. We identify future work to make our solution more efficient.

CONCLUSIONS

Our secure solution is comparable with the standard, non-secure solver in terms of accuracy and convergence speed. The computation time is considerably larger, although the theoretical complexity is still cubic in the number of covariates and quadratic in the number of subjects. We conclude that this is a promising way of performing parametric survival analysis on vertically-distributed medical data, while realising high level of security and privacy.

Federated Networks for Distributed Analysis of Health Data

Access to health data, important for population health planning, basic and clinical research and health industry utilization, remains problematic. Legislation intended to improve access to personal data across national borders has proven to be a double-edged sword, where complexity and implications from misinterpretations have paradoxically resulted in data becoming more siloed. As a result, the potential for development of health specific AI and clinical decision support tools built on real-world data have yet to be fully realized. In this perspective, we propose federated networks as a solution to enable access to diverse data sets and tackle known and emerging health problems. The perspective draws on experience from the World Economic Forum Breaking Barriers to Health Data project, the Personal Health Train and Vantage6 infrastructures, and industry insights. We first define the concept of federated networks in a healthcare context, present the value they can bring to multiple stakeholders, and discuss their establishment, operation and implementation. Challenges of federated networks in healthcare are highlighted, as well as the resulting need for and value of an independent orchestrator for their safe, sustainable and scalable implementation.