Breast Cancer Symptom Clusters Derived from Social Media and Research Study Data Using Improved K-Medoid Clustering

Identification and validation of KIF23 as a hypoxia-regulated lactate metabolism-related oncogene in uterine corpus endometrial carcinoma

AIMS

The "Warburg effect" has been developed from the discovery that hypoxia-inducible factor 1α (HIF-1α) could promote the conversion of pyruvate to lactate. However, no studies have linked hypoxia and lactate metabolism to uterine corpus endometrial carcinoma (UCEC).

MAIN METHODS

Sequencing and clinical data of patients with UCEC were extracted from The Cancer Genome Atlas (TCGA) database. Hypoxia-related lactate metabolism genes (HRLGs) were screened using Spearman's correlation analysis. A prognostic signature based on HRLGs was developed using the least absolute shrinkage and selection operator (LASSO) algorithm. A comprehensive analysis was conducted on the molecular features, immune environment, mutation patterns, and response to drugs between different risk groups. In vitro and in vivo experiments were performed to verify the function of KIF23.

KEY FINDINGS

A five HRLG-based prognostic signature was identified. The prognostic outcome was unfavorable for the high-risk subgroup. Observation of increased pathway activities associated with cell proliferation and DNA damage repair was noted in the high-risk subgroup. Additionally, notable correlations were observed between risk score and immune microenvironment, mutational features, and drug responsiveness. Further, we confirmed KIF23 as a novel oncogene in UCEC, whose silencing decreased proliferation and promoted apoptosis of cancer cells. KIF23 knockdown reduced tumor growth in nude mice. We demonstrated that KIF23 was upregulated under hypoxic stress in a HIF-1α dependent manner. Moreover, KIF23 regulated lactate dehydrogenase A expression.

SIGNIFICANCE

The developed HRLG-related signature was associated with prognosis, immune microenvironment, and drug sensitivity in UCEC. We also revealed KIF23 as a hypoxia-regulated lactate metabolism-related oncogene.

Patient listening on social media for patient-focused drug development: a synthesis of considerations from patients, industry and regulators

Patients, life science industry and regulatory authorities are united in their goal to reduce the disease burden of patients by closing remaining unmet needs. Patients have, however, not always been systematically and consistently involved in the drug development process. Recognizing this gap, regulatory bodies worldwide have initiated patient-focused drug development (PFDD) initiatives to foster a more systematic involvement of patients in the drug development process and to ensure that outcomes measured in clinical trials are truly relevant to patients and represent significant improvements to their quality of life. As a source of real-world evidence (RWE), social media has been consistently shown to capture the first-hand, spontaneous and unfiltered disease and treatment experience of patients and is acknowledged as a valid method for generating patient experience data by the Food and Drug Administration (FDA). While social media listening (SML) methods are increasingly applied to many diseases and use cases, a significant piece of uncertainty remains on how evidence derived from social media can be used in the drug development process and how it can impact regulatory decision making, including legal and ethical aspects. In this policy paper, we review the perspectives of three key stakeholder groups on the role of SML in drug development, namely patients, life science companies and regulators. We also carry out a systematic review of current practices and use cases for SML and, in particular, highlight benefits and drawbacks for the use of SML as a way to identify unmet needs of patients. While we find that the stakeholders are strongly aligned regarding the potential of social media for PFDD, we identify key areas in which regulatory guidance is needed to reduce uncertainty regarding the impact of SML as a source of patient experience data that has impact on regulatory decision making.

Recent advancements in machine learning and deep learning-based breast cancer detection using mammograms

OBJECTIVE

Mammogram-based automatic breast cancer detection has a primary role in accurate cancer diagnosis and treatment planning to save valuable lives. Mammography is one basic yet efficient test for screening breast cancer. Very few comprehensive surveys have been presented to briefly analyze methods for detecting breast cancer with mammograms. In this article, our objective is to give an overview of recent advancements in machine learning (ML) and deep learning (DL)-based breast cancer detection systems.

METHODS

We give a structured framework to categorize mammogram-based breast cancer detection techniques. Several publicly available mammogram databases and different performance measures are also mentioned.

RESULTS

After deliberate investigation, we find most of the works classify breast tumors either as normal-abnormal or malignant-benign rather than classifying them into three classes. Furthermore, DL-based features are more significant than hand-crafted features. However, transfer learning is preferred over others as it yields better performance in small datasets, unlike classical DL techniques.

SIGNIFICANCE AND CONCLUSION

In this article, we have made an attempt to give recent advancements in artificial intelligence (AI)-based breast cancer detection systems. Furthermore, a number of challenging issues and possible research directions are mentioned, which will help researchers in further scopes of research in this field.

Symptom clusters among breast cancer patients in relation to chemotherapy cycles: a longitudinal study

PURPOSE

The aim of this study was to identify symptom clusters in breast cancer patients undergoing adjuvant chemotherapy.

METHODS

A prospective longitudinal study was conducted. And a sample of 620 breast cancer patients receiving adjuvant chemotherapy was recruited using convenience sampling from May 20, 2020, to March 31, 2021. Data were collected eight times: the first chemotherapy cycle (T1) to the eighth cycle of chemotherapy (T8). Exploratory factor analysis was used to explore the composition of symptom clusters.

RESULTS

Symptoms with an incidence of less than 20% were deleted and the remaining symptoms were included in the factor analysis. Three common factors were extracted in T1, including gastrointestinal symptom cluster, emotional and psychological symptom cluster, and menopausal symptom cluster. Five common factors were extracted from T2 to T7, including gastrointestinal symptom cluster, emotional and psychological symptom cluster, neurological symptom cluster, menopausal symptom cluster, and self-image disorder symptom cluster. Four common factors were extracted at T8, including gastrointestinal symptom cluster, emotional and psychological symptom cluster, neurological symptom cluster, and menopausal symptom cluster.

CONCLUSION

Breast cancer patients undergoing adjuvant chemotherapy experience multiple symptoms and different symptom clusters in different chemotherapy cycles. It is a benefit for health care providers to better understand and care for breast cancer patients. It will also help such women to manage concurrent symptoms ahead to promote their quality of life.

Breast tumor localization and segmentation using machine learning techniques: Overview of datasets, findings, and methods

The Global Cancer Statistics 2020 reported breast cancer (BC) as the most common diagnosis of cancer type. Therefore, early detection of such type of cancer would reduce the risk of death from it. Breast imaging techniques are one of the most frequently used techniques to detect the position of cancerous cells or suspicious lesions. Computer-aided diagnosis (CAD) is a particular generation of computer systems that assist experts in detecting medical image abnormalities. In the last decades, CAD has applied deep learning (DL) and machine learning approaches to perform complex medical tasks in the computer vision area and improve the ability to make decisions for doctors and radiologists. The most popular and widely used technique of image processing in CAD systems is segmentation which consists of extracting the region of interest (ROI) through various techniques. This research provides a detailed description of the main categories of segmentation procedures which are classified into three classes: supervised, unsupervised, and DL. The main aim of this work is to provide an overview of each of these techniques and discuss their pros and cons. This will help researchers better understand these techniques and assist them in choosing the appropriate method for a given use case.

A Thin Line Between Helpful and Harmful Internet Usage: Embodied Research on Internet Experiences Among Adolescent and Young Adult Cancer Patients

Purpose: The purpose of this study was to expand upon findings from a prior Delphi study of adolescent and young adults' (AYAs') preferences for cancer resources. Utilizing an embodied approach, this study intended to elucidate a deeper and nuanced understanding of the expressed benefits and risks of engaging in cancer-related online interactions. Methods: Using Gale et al.'s framework method for qualitative, multidisciplinary health research and Thanem and Knights's embodied research methods for the social sciences, an investigative team of embodied researchers (AYA cancer patients turned researchers) conducted semistructured in-depth interviews with AYA cancer patients (n = 10) diagnosed between ages 15 and 39 years. To generate themes, researchers identified commonalities and differences within the qualitative data, and indexed codes according to the agreed analytic framework. Furthermore, by fully engaging with personal reflexivity, bracketing, and analytic memos across data collection and analysis, the investigative team elucidated benefits and risks of embodied research. Results: Findings impart evidence on AYAs' needs for internet-based content at the time of cancer diagnosis, use of the internet to fulfill cancer-related needs, perception of gaps in online cancer resources, and advice to other AYA cancer patients accessing internet-based information and support. Content analysis of interview data on participants' descriptions of personal engagement with the internet revealed beneficial themes of empowerment and harmful themes of fear-inducing consequences. Conclusions: In our rapidly evolving context of postpandemic internet reliance, developers of online cancer content should prioritize and respond to the nuanced vulnerabilities of AYAs. Future research must include socioeconomically disadvantaged participants to better understand practical challenges and promote health equity.

Analyzing the gene regulatory network in hepatitis B patients by single-cell ATAC sequencing

OBJECTIVE

This study aims to provide a new perspective of determining the pathophysiology of chronic hepatitis B (CHB) development by analyzing the gene regulatory network in CHB patients using single-cell ATAC sequencing.

BACKGROUND

Hepatitis B virus (HBV)-related liver disease induces liver damage by hepatic immune and inflammatory responses. The exact mechanism is unknown. As such, there is an urgent need to address this problem and study the relationship between aberrant peripheral blood mononuclear cell (PBMC) immune response and progression of liver disease.

METHOD

The sequencing of the chromatin accessibility of 8016 cells from the whole venous blood of normal control (NC) individuals and CHB patients was performed through assay for transposase-accessible chromatin in single-cell sequencing (ScATAC-seq). Unsupervised clustering and annotation analyses were performed by Signac (version 1.7.0) and Seurat clustering to identify different cell types. Then, TF motif enrichment analysis and differentially expressed peak analysis were performed to identify cell-type-specific candidate open chromatins related to CHB.

RESULT

We identified 12 leukocytic clusters corresponding to five cell types. The specific cell types associated with CHB were found to be located in B-0 and T-3. We have drawn the regulatory network of the hepatitis B signal pathway composed of genes linked to the differentially expressed peaks of these two CHB disease-specific cell types. Further, we profoundly explored the potential mechanisms of B-0-associated TF motif IRF2 and T-3-associated TF motif FOXC2 in the occurrence of CHB.

CONCLUSION

We have drawn a systematic and distinguishing gene regulatory network of CHB-related PBMCs. Key Points • Peripheral blood mononuclear cells were robustly clustered based on their types without using antibodies. • We draw a systematic and distinctive gene regulatory network of CHB-related PBMC through ScATAC-seq.

Deciphering Diversity of Mental Models in Neurodevelopmental Disorders: Knowledge Graph Representation of Public Data Using Natural Language Processing (Preprint)

Background

Understanding how individuals think about a topic, known as the mental model, can significantly improve communication, especially in the medical domain where emotions and implications are high. Neurodevelopmental disorders (NDDs) represent a group of diagnoses, affecting up to 18% of the global population, involving differences in the development of cognitive or social functions. In this study, we focus on 2 NDDs, attention deficit hyperactivity disorder (ADHD) and autism spectrum disorder (ASD), which involve multiple symptoms and interventions requiring interactions between 2 important stakeholders: parents and health professionals. There is a gap in our understanding of differences between mental models for each stakeholder, making communication between stakeholders more difficult than it could be.

Objective

We aim to build knowledge graphs (KGs) from web-based information relevant to each stakeholder as proxies of mental models. These KGs will accelerate the identification of shared and divergent concerns between stakeholders. The developed KGs can help improve knowledge mobilization, communication, and care for individuals with ADHD and ASD.

Methods

We created 2 data sets by collecting the posts from web-based forums and PubMed abstracts related to ADHD and ASD. We utilized the Unified Medical Language System (UMLS) to detect biomedical concepts and applied Positive Pointwise Mutual Information followed by truncated Singular Value Decomposition to obtain corpus-based concept embeddings for each data set. Each data set is represented as a KG using a property graph model. Semantic relatedness between concepts is calculated to rank the relation strength of concepts and stored in the KG as relation weights. UMLS disorder-relevant semantic types are used to provide additional categorical information about each concept’s domain.

Results

The developed KGs contain concepts from both data sets, with node sizes representing the co-occurrence frequency of concepts and edge sizes representing relevance between concepts. ADHD- and ASD-related concepts from different semantic types shows diverse areas of concerns and complex needs of the conditions. KG identifies converging and diverging concepts between health professionals literature (PubMed) and parental concerns (web-based forums), which may correspond to the differences between mental models for each stakeholder.

Conclusions

We show for the first time that generating KGs from web-based data can capture the complex needs of families dealing with ADHD or ASD. Moreover, we showed points of convergence between families and health professionals’ KGs. Natural language processing–based KG provides access to a large sample size, which is often a limiting factor for traditional in-person mental model mapping. Our work offers a high throughput access to mental model maps, which could be used for further in-person validation, knowledge mobilization projects, and basis for communication about potential blind spots from stakeholders in interactions about NDDs. Future research will be needed to identify how concepts could interact together differently for each stakeholder.

Correlation Between Symptom Clusters and Quality of Life in Children With Acute Leukemia During Chemotherapy

BACKGROUND

Children with acute leukemia experience various distressing symptoms due to the disease and its treatment during chemotherapy. These symptoms cluster together and have negative impacts on patient outcomes.

OBJECTIVE

The aim of this study was to examine symptom clusters that children with acute leukemia undergoing chemotherapy are experiencing and the impact of these symptom clusters on their quality of life.

METHODS

A cross-sectional study design was used, and 184 Chinese children with acute leukemia who were undergoing chemotherapy were invited to participate in the study. Memorial Symptom Assessment Scale 10-18 and Pediatric Quality of Life Inventory General Core Module version 4.0 were applied. Exploratory factor analysis and multiple regression were used to identify symptom clusters and their influence on the quality of life.

RESULTS

Six symptom clusters were identified as gastrointestinal, emotional, neurological, skin mucosal, self-image disorder, and somatic cluster. The severity of each symptom cluster was negatively correlated with quality of life. Among them, gastrointestinal, emotional, and somatic clusters were significant predictors of quality of life.

CONCLUSIONS

There are multiple symptom clusters in children with acute leukemia, which seriously affect children's quality of life. To relieve symptom burden and improve quality of life, nursing and medical staff should pay attention to the symptom management and control in a symptom cluster perspective.

IMPLICATIONS FOR PRACTICE

The results of this study will provide suggestions for the healthcare provider to plan for these symptoms and manage any concurrent symptoms for the successful promotion of children's quality of life.

A systematic literature review of machine learning in online personal health data

OBJECTIVE

User-generated content (UGC) in online environments provides opportunities to learn an individual's health status outside of clinical settings. However, the nature of UGC brings challenges in both data collecting and processing. The purpose of this study is to systematically review the effectiveness of applying machine learning (ML) methodologies to UGC for personal health investigations.

MATERIALS AND METHODS

We searched PubMed, Web of Science, IEEE Library, ACM library, AAAI library, and the ACL anthology. We focused on research articles that were published in English and in peer-reviewed journals or conference proceedings between 2010 and 2018. Publications that applied ML to UGC with a focus on personal health were identified for further systematic review.

RESULTS

We identified 103 eligible studies which we summarized with respect to 5 research categories, 3 data collection strategies, 3 gold standard dataset creation methods, and 4 types of features applied in ML models. Popular off-the-shelf ML models were logistic regression (n = 22), support vector machines (n = 18), naive Bayes (n = 17), ensemble learning (n = 12), and deep learning (n = 11). The most investigated problems were mental health (n = 39) and cancer (n = 15). Common health-related aspects extracted from UGC were treatment experience, sentiments and emotions, coping strategies, and social support.

CONCLUSIONS

The systematic review indicated that ML can be effectively applied to UGC in facilitating the description and inference of personal health. Future research needs to focus on mitigating bias introduced when building study cohorts, creating features from free text, improving clinical creditability of UGC, and model interpretability.