The "Know Your Lemons" Tools: A strategy to improve breast cancer warning signs recognition in Malaysia.

BACKGROUND: Breast cancer (BC) is the most common cancer in Malaysia, with many diagnosed at late stages. The "Know Your Lemons" (KYL) visual educational tools were developed by KYL Foundation. This study aimed to evaluate participants' confidence levels and perceived knowledge in identifying BC symptoms before and after exposure to KYL tools. MATERIALS AND METHODS: A cross-sectional study was carried out among 788 participants in three KYL health campaigns from 2017 to 2020. Perceived knowledge (a 5-item Likert scale was used, zero means "very poor" and 4 means "excellent knowledge") and confidence in identifying BC symptoms were studied. A Wilcoxon Matched-Paired Signed-Rank Test was performed to assess the perceived knowledge. RESULTS: There was a significant improvement in the perceived knowledge Mean (±SD) score (2.84 ± 1.02) versus (4.31 ± 0.66) before and after the campaign (P < 0.01). About 95.6% agreed that the language used in KYL materials was clear and understandable, 89.8% agreed it is acceptable in Malaysian culture, and 80% felt more confident in identifying BC symptoms. Therefore, 90.8% had the intention of breast self-examination and 90.8% would consult a doctor if symptomatic. The majority (92.7%) agreed that the KYL tools clarified the BC tests needed. CONCLUSION: The KYL tools enhanced perceived BC symptom recognition knowledge and confidence levels.

Natural language processing in narrative breast radiology reporting in University Malaya Medical Centre.

Radiology reporting is narrative, and its content depends on the clinician's ability to interpret the images accurately. A tertiary hospital, such as anonymous institute, focuses on writing reports narratively as part of training for medical personnel. Nevertheless, free-text reports make it inconvenient to extract information for clinical audits and data mining. Therefore, we aim to convert unstructured breast radiology reports into structured formats using natural language processing (NLP) algorithm. This study used 327 de-identified breast radiology reports from the anonymous institute. The radiologist identified the significant data elements to be extracted. Our NLP algorithm achieved 97% and 94.9% accuracy in training and testing data, respectively. Henceforth, the structured information was used to build the predictive model for predicting the value of the BIRADS category. The model based on random forest generated the highest accuracy of 92%. Our study not only fulfilled the demands of clinicians by enhancing communication between medical personnel, but it also demonstrated the usefulness of mineable structured data in yielding significant insights.

Theory and Practice of Integrating Machine Learning and Conventional Statistics in Medical Data Analysis.

The practice of medical decision making is changing rapidly with the development of innovative computing technologies. The growing interest of data analysis with improvements in big data computer processing methods raises the question of whether machine learning can be integrated with conventional statistics in health research. To help address this knowledge gap, this paper presents a review on the conceptual integration between conventional statistics and machine learning, focusing on the health research. The similarities and differences between the two are compared using mathematical concepts and algorithms. The comparison between conventional statistics and machine learning methods indicates that conventional statistics are the fundamental basis of machine learning, where the black box algorithms are derived from basic mathematics, but are advanced in terms of automated analysis, handling big data and providing interactive visualizations. While the nature of both these methods are different, they are conceptually similar. Based on our review, we conclude that conventional statistics and machine learning are best to be integrated to develop automated data analysis tools. We also strongly believe that machine learning could be explored by health researchers to enhance conventional statistics in decision making for added reliable validation measures.

Automated Generation of Synoptic Reports from Narrative Pathology Reports in University Malaya Medical Centre Using Natural Language Processing.

Pathology reports represent a primary source of information for cancer registries. University Malaya Medical Centre (UMMC) is a tertiary hospital responsible for training pathologists; thus narrative reporting becomes important. However, the unstructured free-text reports made the information extraction process tedious for clinical audits and data analysis-related research. This study aims to develop an automated natural language processing (NLP) algorithm to summarize the existing narrative breast pathology report from UMMC to a narrower structured synoptic pathology report with a checklist-style report template to ease the creation of pathology reports. The development of the rule-based NLP algorithm was based on the R programming language by using 593 pathology specimens from 174 patients provided by the Department of Pathology, UMMC. The pathologist provides specific keywords for data elements to define the semantic rules of the NLP. The system was evaluated by calculating the precision, recall, and F1-score. The proposed NLP algorithm achieved a micro-F1 score of 99.50% and a macro-F1 score of 98.97% on 178 specimens with 25 data elements. This achievement correlated to clinicians' needs, which could improve communication between pathologists and clinicians. The study presented here is significant, as structured data is easily minable and could generate important insights.

Classification of Breast Cancer Lesions in Ultrasound Images by Using Attention Layer and Loss Ensemble in Deep Convolutional Neural Networks.

The reliable classification of benign and malignant lesions in breast ultrasound images can provide an effective and relatively low-cost method for the early diagnosis of breast cancer. The accuracy of the diagnosis is, however, highly dependent on the quality of the ultrasound systems and the experience of the users (radiologists). The use of deep convolutional neural network approaches has provided solutions for the efficient analysis of breast ultrasound images. In this study, we propose a new framework for the classification of breast cancer lesions with an attention module in a modified VGG16 architecture. The adopted attention mechanism enhances the feature discrimination between the background and targeted lesions in ultrasound. We also propose a new ensembled loss function, which is a combination of binary cross-entropy and the logarithm of the hyperbolic cosine loss, to improve the model discrepancy between classified lesions and their labels. This combined loss function optimizes the network more quickly. The proposed model outperformed other modified VGG16 architectures, with an accuracy of 93%, and also, the results are competitive with those of other state-of-the-art frameworks for the classification of breast cancer lesions. Our experimental results show that the choice of loss function is highly important and plays a key role in breast lesion classification tasks. Additionally, by adding an attention block, we could improve the performance of the model.

An Artificial Intelligence-Enabled Pipeline for Medical Domain: Malaysian Breast Cancer Survivorship Cohort as a Case Study.

Automated artificial intelligence (AI) systems enable the integration of different types of data from various sources for clinical decision-making. The aim of this study is to propose a pipeline to develop a fully automated clinician-friendly AI-enabled database platform for breast cancer survival prediction. A case study of breast cancer survival cohort from the University Malaya Medical Centre was used to develop and evaluate the pipeline. A relational database and a fully automated system were developed by integrating the database with analytical modules (machine learning, automated scoring for quality of life, and interactive visualization). The developed pipeline, iSurvive has helped in enhancing data management as well as to visualize important prognostic variables and survival rates. The embedded automated scoring module demonstrated quality of life of patients whereas the interactive visualizations could be used by clinicians to facilitate communication with patients. The pipeline proposed in this study is a one-stop center to manage data, to automate analytics using machine learning, to automate scoring and to produce explainable interactive visuals to enhance clinician-patient communication along the survivorship period to modify behaviours that relate to prognosis. The pipeline proposed can be modelled on any disease not limited to breast cancer.

Pairwise correlation of genes involved in glucose metabolism: a potential diagnostic marker of cancer?

Cancer is a highly malignant disease, killing approximately 10 million people worldwide in 2020. Cancer patient survival substantially relies on early diagnosis. In this study, we evaluated whether genes involved in glucose metabolism could be used as potential diagnostic markers for cancer. In total, 127 genes were examined for their gene expression levels and pairwise gene correlations. Genes ADH1B and PDHA2 were differentially expressed in most of the 12 types of cancer and five pairs of genes exhibited consistent correlation changes (from strong correlations in normal controls to weak correlations in cancer patients) across all types of cancer. Thus, the two differentially expressed genes and five gene pairs could be potential diagnostic markers for cancer. Further preclinical and clinical studies are warranted to prove whether these genes and/or gene pairs would indeed aid in early diagnosis of cancer.

Key drug-targeting genes in pancreatic ductal adenocarcinoma.

Pancreatic ductal adenocarcinoma (PDAC) is a highly lethal type of cancer. In this study, we undertook a pairwise comparison of gene expression pattern between tumor tissue and its matching adjacent normal tissue for 45 PDAC patients and identified 22 upregulated and 32 downregulated genes. PPI network revealed that fibronectin 1 and serpin peptidase inhibitor B5 were the most interconnected upregulated-nodes. Virtual screening identified bleomycin exhibited reasonably strong binding to both proteins. Effect of bleomycin on cell viability was examined against two PDAC cell lines, AsPC-1 and MIA PaCa-2. AsPC-1 did not respond to bleomycin, however, MIA PaCa-2 responded to bleomycin with an IC50 of 2.6 µM. This implicates that bleomycin could be repurposed for the treatment of PDAC, especially in combination with other chemotherapy agents. In vivo mouse xenograft studies and patient clinical trials are warranted to understand the functional mechanism of bleomycin towards PDAC and optimize its therapeutic efficacy. Furthermore, we will evaluate the antitumor activity of the other identified drugs in our future studies.

Identifying kinase targets of PPARγ in human breast cancer.

Breast cancer is the most common cancer in women. Despite advances in screening women for genetic predisposition to breast cancer and risk stratification, a majority of women carriers remain undetected until they become affected. Thus, there is a need to develop a cost-effective, rapid, sensitive and non-invasive early-stage diagnostic method. Kinases are involved in all fundamental cellular processes and mutations in kinases have been reported as drivers of cancer. PPARγ is a ligand-activated transcription factor that plays important roles in cell proliferation and metabolism. However, the complete set of kinases modulated by PPARγ is still unknown. In this study, we identified human kinases that are potential PPARγ targets and evaluated their differential expression and gene pair correlations in human breast cancer patient dataset TCGA-BRCA. We further confirmed the findings in human breast cancer cell lines MCF7 and SK-BR-3 using a kinome array. We observed that gene pair correlations are lost in tumours as compared to healthy controls and could be used as a supplement strategy for diagnosis and prognosis of breast cancer.

Alteration in Gene Pair Correlations in Tryptophan Metabolism as a Hallmark in Cancer Diagnosis.

Tryptophan metabolism plays essential roles in both immunomodulation and cancer development. Indoleamine 2,3-dioxygenase, a rate-limiting enzyme in the metabolic pathway, is overexpressed in different types of cancer. To get a better understanding of the involvement of tryptophan metabolism in cancer development, we evaluated the expression and pairwise correlation of 62 genes in the metabolic pathway across 12 types of cancer. Only gene AOX1, encoding aldehyde oxidase 1, was ubiquitously downregulated, Furthermore, we observed that the 62 genes were widely and strongly correlated in normal controls, however, the gene pair correlations were significantly lost in tumor patients for all 12 types of cancer. This implicated that gene pair correlation coefficients of the tryptophan metabolic pathway could be applied as a prognostic and/or diagnostic biomarker for cancer.

An automated 3D modeling pipeline for constructing 3D models of MONOGENEAN HARDPART using machine learning techniques.

BACKGROUND: Studying structural and functional morphology of small organisms such as monogenean, is difficult due to the lack of visualization in three dimensions. One possible way to resolve this visualization issue is to create digital 3D models which may aid researchers in studying morphology and function of the monogenean. However, the development of 3D models is a tedious procedure as one will have to repeat an entire complicated modelling process for every new target 3D shape using a comprehensive 3D modelling software. This study was designed to develop an alternative 3D modelling approach to build 3D models of monogenean anchors, which can be used to understand these morphological structures in three dimensions. This alternative 3D modelling approach is aimed to avoid repeating the tedious modelling procedure for every single target 3D model from scratch. RESULT: An automated 3D modeling pipeline empowered by an Artificial Neural Network (ANN) was developed. This automated 3D modelling pipeline enables automated deformation of a generic 3D model of monogenean anchor into another target 3D anchor. The 3D modelling pipeline empowered by ANN has managed to automate the generation of the 8 target 3D models (representing 8 species: Dactylogyrus primaries, Pellucidhaptor merus, Dactylogyrus falcatus, Dactylogyrus vastator, Dactylogyrus pterocleidus, Dactylogyrus falciunguis, Chauhanellus auriculatum and Chauhanellus caelatus) of monogenean anchor from the respective 2D illustrations input without repeating the tedious modelling procedure. CONCLUSIONS: Despite some constraints and limitation, the automated 3D modelling pipeline developed in this study has demonstrated a working idea of application of machine learning approach in a 3D modelling work. This study has not only developed an automated 3D modelling pipeline but also has demonstrated a cross-disciplinary research design that integrates machine learning into a specific domain of study such as 3D modelling of the biological structures.

Predicting factors for survival of breast cancer patients using machine learning techniques.

BACKGROUND: Breast cancer is one of the most common diseases in women worldwide. Many studies have been conducted to predict the survival indicators, however most of these analyses were predominantly performed using basic statistical methods. As an alternative, this study used machine learning techniques to build models for detecting and visualising significant prognostic indicators of breast cancer survival rate. METHODS: A large hospital-based breast cancer dataset retrieved from the University Malaya Medical Centre, Kuala Lumpur, Malaysia (n = 8066) with diagnosis information between 1993 and 2016 was used in this study. The dataset contained 23 predictor variables and one dependent variable, which referred to the survival status of the patients (alive or dead). In determining the significant prognostic factors of breast cancer survival rate, prediction models were built using decision tree, random forest, neural networks, extreme boost, logistic regression, and support vector machine. Next, the dataset was clustered based on the receptor status of breast cancer patients identified via immunohistochemistry to perform advanced modelling using random forest. Subsequently, the important variables were ranked via variable selection methods in random forest. Finally, decision trees were built and validation was performed using survival analysis. RESULTS: In terms of both model accuracy and calibration measure, all algorithms produced close outcomes, with the lowest obtained from decision tree (accuracy = 79.8%) and the highest from random forest (accuracy = 82.7%). The important variables identified in this study were cancer stage classification, tumour size, number of total axillary lymph nodes removed, number of positive lymph nodes, types of primary treatment, and methods of diagnosis. CONCLUSION: Interestingly the various machine learning algorithms used in this study yielded close accuracy hence these methods could be used as alternative predictive tools in the breast cancer survival studies, particularly in the Asian region. The important prognostic factors influencing survival rate of breast cancer identified in this study, which were validated by survival curves, are useful and could be translated into decision support tools in the medical domain.

Development of electronic medical records for clinical and research purposes: the breast cancer module using an implementation framework in a middle income country- Malaysia.

BACKGROUND: Advances in medical domain has led to an increase of clinical data production which offers enhancement opportunities for clinical research sector. In this paper, we propose to expand the scope of Electronic Medical Records in the University Malaya Medical Center (UMMC) using different techniques in establishing interoperability functions between multiple clinical departments involving diagnosis, screening and treatment of breast cancer and building automatic systems for clinical audits as well as for potential data mining to enhance clinical breast cancer research in the future. RESULTS: Quality Implementation Framework (QIF) was adopted to develop the breast cancer module as part of the in-house EMR system used at UMMC, called i-Pesakit©. The completion of the i-Pesakit© Breast Cancer Module requires management of clinical data electronically, integration of clinical data from multiple internal clinical departments towards setting up of a research focused patient data governance model. The 14 QIF steps were performed in four main phases involved in this study which are (i) initial considerations regarding host setting, (ii) creating structure for implementation, (iii) ongoing structure once implementation begins, and (iv) improving future applications. The architectural framework of the module incorporates both clinical and research needs that comply to the Personal Data Protection Act. CONCLUSION: The completion of the UMMC i-Pesakit© Breast Cancer Module required populating EMR including management of clinical data access, establishing information technology and research focused governance model and integrating clinical data from multiple internal clinical departments. This multidisciplinary collaboration has enhanced the quality of data capture in clinical service, benefited hospital data monitoring, quality assurance, audit reporting and research data management, as well as a framework for implementing a responsive EMR for a clinical and research organization in a typical middle-income country setting. Future applications include establishing integration with external organization such as the National Registration Department for mortality data, reporting of institutional data for national cancer registry as well as data mining for clinical research. We believe that integration of multiple clinical visit data sources provides a more comprehensive, accurate and real-time update of clinical data to be used for epidemiological studies and audits.

Fish Ontology framework for taxonomy-based fish recognition.

Life science ontologies play an important role in Semantic Web. Given the diversity in fish species and the associated wealth of information, it is imperative to develop an ontology capable of linking and integrating this information in an automated fashion. As such, we introduce the Fish Ontology (FO), an automated classification architecture of existing fish taxa which provides taxonomic information on unknown fish based on metadata restrictions. It is designed to support knowledge discovery, provide semantic annotation of fish and fisheries resources, data integration, and information retrieval. Automated classification for unknown specimens is a unique feature that currently does not appear to exist in other known ontologies. Examples of automated classification for major groups of fish are demonstrated, showing the inferred information by introducing several restrictions at the species or specimen level. The current version of FO has 1,830 classes, includes widely used fisheries terminology, and models major aspects of fish taxonomy, grouping, and character. With more than 30,000 known fish species globally, the FO will be an indispensable tool for fish scientists and other interested users.

Automated identification of Monogeneans using digital image processing and K-nearest neighbour approaches.

BACKGROUND: Monogeneans are flatworms (Platyhelminthes) that are primarily found on gills and skin of fishes. Monogenean parasites have attachment appendages at their haptoral regions that help them to move about the body surface and feed on skin and gill debris. Haptoral attachment organs consist of sclerotized hard parts such as hooks, anchors and marginal hooks. Monogenean species are differentiated based on their haptoral bars, anchors, marginal hooks, reproductive parts' (male and female copulatory organs) morphological characters and soft anatomical parts. The complex structure of these diagnostic organs and also their overlapping in microscopic digital images are impediments for developing fully automated identification system for monogeneans (LNCS 7666:256-263, 2012), (ISDA; 457-462, 2011), (J Zoolog Syst Evol Res 52(2): 95-99. 2013;). In this study images of hard parts of the haptoral organs such as bars and anchors are used to develop a fully automated identification technique for monogenean species identification by implementing image processing techniques and machine learning methods. RESULT: Images of four monogenean species namely Sinodiplectanotrema malayanus, Trianchoratus pahangensis, Metahaliotrema mizellei and Metahaliotrema sp. (undescribed) were used to develop an automated technique for identification. K-nearest neighbour (KNN) was applied to classify the monogenean specimens based on the extracted features. 50% of the dataset was used for training and the other 50% was used as testing for system evaluation. Our approach demonstrated overall classification accuracy of 90%. In this study Leave One Out (LOO) cross validation is used for validation of our system and the accuracy is 91.25%. CONCLUSIONS: The methods presented in this study facilitate fast and accurate fully automated classification of monogeneans at the species level. In future studies more classes will be included in the model, the time to capture the monogenean images will be reduced and improvements in extraction and selection of features will be implemented.

Automated identification of copepods using digital image processing and artificial neural network.

BACKGROUND: Copepods are planktonic organisms that play a major role in the marine food chain. Studying the community structure and abundance of copepods in relation to the environment is essential to evaluate their contribution to mangrove trophodynamics and coastal fisheries. The routine identification of copepods can be very technical, requiring taxonomic expertise, experience and much effort which can be very time-consuming. Hence, there is an urgent need to introduce novel methods and approaches to automate identification and classification of copepod specimens. This study aims to apply digital image processing and machine learning methods to build an automated identification and classification technique. RESULTS: We developed an automated technique to extract morphological features of copepods' specimen from captured images using digital image processing techniques. An Artificial Neural Network (ANN) was used to classify the copepod specimens from species Acartia spinicauda, Bestiolina similis, Oithona aruensis, Oithona dissimilis, Oithona simplex, Parvocalanus crassirostris, Tortanus barbatus and Tortanus forcipatus based on the extracted features. 60% of the dataset was used for a two-layer feed-forward network training and the remaining 40% was used as testing dataset for system evaluation. Our approach demonstrated an overall classification accuracy of 93.13% (100% for A. spinicauda, B. similis and O. aruensis, 95% for T. barbatus, 90% for O. dissimilis and P. crassirostris, 85% for O. similis and T. forcipatus). CONCLUSIONS: The methods presented in this study enable fast classification of copepods to the species level. Future studies should include more classes in the model, improving the selection of features, and reducing the time to capture the copepod images.

A deformable generic 3D model of haptoral anchor of Monogenean.

In this paper, a digital 3D model which allows for visualisation in three dimensions and interactive manipulation is explored as a tool to help us understand the structural morphology and elucidate the functions of morphological structures of fragile microorganisms which defy live studies. We developed a deformable generic 3D model of haptoral anchor of dactylogyridean monogeneans that can subsequently be deformed into different desired anchor shapes by using direct manipulation deformation technique. We used point primitives to construct the rectangular building blocks to develop our deformable 3D model. Point primitives are manually marked on a 2D illustration of an anchor on a Cartesian graph paper and a set of Cartesian coordinates for each point primitive is manually extracted from the graph paper. A Python script is then written in Blender to construct 3D rectangular building blocks based on the Cartesian coordinates. The rectangular building blocks are stacked on top or by the side of each other following their respective Cartesian coordinates of point primitive. More point primitives are added at the sites in the 3D model where more structural variations are likely to occur, in order to generate complex anchor structures. We used Catmull-Clark subdivision surface modifier to smoothen the surface and edge of the generic 3D model to obtain a smoother and more natural 3D shape and antialiasing option to reduce the jagged edges of the 3D model. This deformable generic 3D model can be deformed into different desired 3D anchor shapes through direct manipulation deformation technique by aligning the vertices (pilot points) of the newly developed deformable generic 3D model onto the 2D illustrations of the desired shapes and moving the vertices until the desire 3D shapes are formed. In this generic 3D model all the vertices present are deployed for displacement during deformation.

Hybrid-drug design targeting Pseudomonas aeruginosa dihydropteroate synthase and dihydrofolate reductase

In this study, we successfully present the dual-target design hypothesis to inhibit both dihydropteroate synthase (DHPS) and dihydrofolate reductase (DHFR) enzymes using a novel scheme that integrates our previous antibiotic-phytochemical interaction data, fragment combination and knowledge-based methods. Both the enzymes are well established antibacterial targets from folate biosynthesis pathway and their synergistic modulation by a single hybrid entity may have profound therapeutic benefits. Evaluation of the designed hybrid compounds based on their physico-chemical properties has indicated them as promising drug candidates with drug-like pharmacotherapeutic profiles. In addition, the stereo-electronic properties such as HOMO, LUMO and MEP maps calculated by quantum chemical methods gave a good correlation with the common pharmacophoric features required for dual-site interactions. Furthermore, docking and dynamics simulation studies reveal that the designed hybrid compounds have favorable binding affinity and stability in both pterin-binding site of DHPS and folate-binding site of DHFR by forming strong hydrogen bonds and hydrophobic interactions with key active-site residues. Looking forward this study could serve as a prospective lead in the process of new natural-product based hybrid-drugs development.

Semantic representation of monogenean haptoral Bar image annotation.

BACKGROUND: Digitised monogenean images are usually stored in file system directories in an unstructured manner. In this paper we propose a semantic representation of these images in the form of a Monogenean Haptoral Bar Image (MHBI) ontology, which are annotated with taxonomic classification, diagnostic hard part and image properties. The data we used are basically of the monogenean species found in fish, thus we built a simple Fish ontology to demonstrate how the host (fish) ontology can be linked to the MHBI ontology. This will enable linking of information from the monogenean ontology to the host species found in the fish ontology without changing the underlying schema for either of the ontologies. RESULTS: In this paper, we utilized the Taxonomic Data Working Group Life Sciences Identifier (TDWG LSID) vocabulary to represent our data and defined a new vocabulary which is specific for annotating monogenean haptoral bar images to develop the MHBI ontology and a merged MHBI-Fish ontologies. These ontologies are successfully evaluated using five criteria which are clarity, coherence, extendibility, ontology commitment and encoding bias. CONCLUSIONS: In this paper, we show that unstructured data can be represented in a structured form using semantics. In the process, we have come up with a new vocabulary for annotating the monogenean images with textual information. The proposed monogenean image ontology will form the basis of a monogenean knowledge base to assist researchers in retrieving information for their analysis.