An enhanced version of Harris Hawks Optimization by dimension learning-based hunting for Breast Cancer Detection

Swarm intelligence techniques have a vast range of real world applications.Some applications are in the domain of medical data mining where, main attention is on structure models for the classification and expectation of numerous diseases. These biomedical applications have grabbed the interest of numerous researchers because these are most serious and prevalent causes of death among the human whole world out of which breast cancer is the most serious issue. Mammography is the initial screening assessment of breast cancer. In this study, an enhanced version of Harris Hawks Optimization (HHO) approach has been developed for biomedical databases, known as DLHO. This approach has been introduced by integrating the merits of dimension learning-based hunting (DLH) search strategy with HHO. The main objective of this study is to alleviate the lack of crowd diversity, premature convergence of the HHO and the imbalance amid the exploration and exploitation. DLH search strategy utilizes a dissimilar method to paradigm a neighborhood for each search member in which the neighboring information can be shared amid search agents. This strategy helps in maintaining the diversity and the balance amid global and local search. To evaluate the DLHO lot of experiments have been taken such as (i) the performance of optimizers have analysed by using 29-CEC -2017 test suites, (ii) to demonstrate the effectiveness of the DLHO it has been tested on different biomedical databases out of which we have used two different databases for Breast i.e. MIAS and second database has been taken from the University of California at Irvine (UCI) Machine Learning Repository.Also to test the robustness of the proposed method its been tested on two other databases of such as Balloon and Heart taken from the UCI Machine Learning Repository. All the results are in the favour of the proposed technique.

Using Machine Learning to Collect and Facilitate Remote Access to Biomedical Databases: Development of the Biomedical Database Inventory

Background Currently, existing biomedical literature repositories do not commonly provide users with specific means to locate and remotely access biomedical databases. Objective To address this issue, we developed the Biomedical Database Inventory (BiDI), a repository linking to biomedical databases automatically extracted from the scientific literature. BiDI provides an index of data resources and a path to access them seamlessly. Methods We designed an ensemble of deep learning methods to extract database mentions. To train the system, we annotated a set of 1242 articles that included mentions of database publications. Such a data set was used along with transfer learning techniques to train an ensemble of deep learning natural language processing models targeted at database publication detection. Results The system obtained an F1 score of 0.929 on database detection, showing high precision and recall values. When applying this model to the PubMed and PubMed Central databases, we identified over 10,000 unique databases. The ensemble model also extracted the weblinks to the reported databases and discarded irrelevant links. For the extraction of weblinks, the model achieved a cross-validated F1 score of 0.908. We show two use cases: one related to “omics” and the other related to the COVID-19 pandemic. Conclusions BiDI enables access to biomedical resources over the internet and facilitates data-driven research and other scientific initiatives. The repository is openly available online and will be regularly updated with an automatic text processing pipeline. The approach can be reused to create repositories of different types (ie, biomedical and others).

Deciphering Chinese herbal medicine's efficacy and mechanisms for diabetic kidney disease: integrating web-based biochemical databases to the real-world clinical data. (Preprint)

BACKGROUND Diabetic kidney disease (DKD) is one of the most crucial causes of chronic kidney disease (CKD). However, the efficacy and biomedical mechanisms of using CHM for DKD in clinical settings remain unclear. OBJECTIVE This study aims to analyze the outcome of DKD patients with CHM-only management and the possible molecular pathways of CHM by integrating web-based biomedical databases and the real-world clinical database. METHODS A total of 152,357 patients with incident DKD from 2004 to 2012 were identified from the National Health Insurance Research Database (NHIRD) in Taiwan. The risk of mortality was estimated with the Kaplan–Meier method and Cox regression considering demographic covariates. The inverse probability of treatment weighting was used for confounding bias between CHM users and nonusers. Furthermore, to decipher the CHM used for DKD, we analyzed all CHM prescriptions using the Chinese herbal medicine network (CMN), which combined association rule mining and social network analysis among all CHM prescriptions. Further, web-based biomedical databases, including STITCH, STRING, BindingDB, TCMSP, TCM@Taiwan, DisGeNET, were integrated into the CMN and commonly used western medicine (WM) to explore the differences in possible target proteins and molecular pathways between CHM and WM. The application programming interface (API) was used to assess these online databases to obtain the latest biomedical information. RESULTS About 13.7% of patients were classified as CHM users among eligible DKD patients. The median follow-up duration of all patients was 2.49 years. The cumulative incidence of mortality among the CHM cohort was significantly lower than the WM cohort (28% versus 48%, P < .001). The risk of mortality was 0.41 among the CHM cohort with covariates adjustment (99% CI: 0.38-0.43, P < .001). A total of 173,525 CHM prescriptions were used to construct CMN with eleven CHM clusters. CHM covered more DKD-related proteins and pathways than WM; nevertheless, WM aimed at DKD more specifically. From the overrepresentation tests carried by the online website Reactome, the molecular pathways covered by the CHM clusters in CMN and WM seemed distinctive but complementary. The complementary effects were also found among DKD patients with concurrent WM and CHM use. The risks of mortality among CHM users under renin-angiotensin-aldosterone system (RAAS) inhibition therapy were lower than CHM nonusers among DKD patients with hypertension (adjusted HR: 0.47, 99%CI: 0.45-0.51, P < .001), chronic heart failure (adjusted HR: 0.43, 99%CI: 0.37-0.51, P < .001), and ischemic heart disease (adjusted HR: 0.46, 99%CI: 0.41-0.51, P < .001) CONCLUSIONS CHM users among DKD patients seemed to have a lower risk of mortality, which may benefit from potentially synergistic renoprotection effects. The framework of integrating real-world clinical databases and web-based biomedical databases could help explore the role of treatments for diseases.

BiDI: Using Machine Learning to collect and facilitate remote access to biomedical databases (Preprint)

BACKGROUND Currently, existing biomedical literature repositories do not commonly provide users with specific means to locate and remotely access biomedical databases. OBJECTIVE To address this issue we developed BiDI (Biomedical Database Inventory), a repository linking to biomedical databases automatically extracted from the scientific literature. BiDI provides an index of data resources and a path to access them in a seamless manner. METHODS We designed an ensemble of Deep Learning methods to extract database mentions. To train the system we annotated a set of 1,242 articles that included mentions to database publications. Such a dataset was used along with transfer learning techniques to train an ensemble of deep learning NLP models based on the task of database publication detection. RESULTS The system obtained an f1-score of 0.929 on database detection, showing high precision and recall values. Applying this model to the PubMed and PubMed Central databases we identified over 10,000 unique databases. The ensemble also extracts the web links to the reported databases, discarding the irrelevant links. For the extraction of web links the model achieved a cross-validated f1-score of 0.908. We show two use cases, related to “omics” and the COVID-19 pandemia. CONCLUSIONS BiDI enables the access of biomedical resources over the Internet and facilitates data-driven research and other scientific initiatives. The repository is available at (http://gib.fi.upm.es/bidi/) and will be regularly updated with an automatic text processing pipeline. The approach can be reused to create repositories of different types (biomedical and others).