User:ExpRoi2804/Disease informatics
 | This is the sandbox page where you will draft your initial Wikipedia contribution.
If you're starting a new article, you can develop it here until it's ready to go live. If you're working on improvements to an existing article, copy only one section at a time of the article to this sandbox to work on, and be sure to use an edit summary linking to the article you copied from. Do not copy over the entire article. You can find additional instructions here. Remember to save your work regularly using the "Publish page" button. (It just means 'save'; it will still be in the sandbox.) You can add bold formatting to your additions to differentiate them from existing content. |
Infectious Disease Informatics
[edit]Infectious Disease Informatics (also called Disease informatics) addresses some major challenges to global public health, demanding solid medical interference, but also credible data centric strategies. With rapid advancement of genetic technology tools that analyze the DNA and RNA of pathogens to identify, track, and characterize them, alongside artificial intelligence and the field of Infectious Disease Informatics (IDI) has emerged as area of expertise. IDI is well familiar from past years but is studied more nowadays as the constant increase of bioinformatics and medical health data available broadly, with integration of all these systems with public health data is then used to enable early detection, tracking, and informed decision-making during major outbreaks [1].In addition to decisions of policymaker, the detection of biomarkers for improving vaccine development, while gaining insights into pathogen-host to optimize the antimicrobial development is the goal of infectious disease informatics[1]. In parallel, recent insights of the COVID-19 pandemic emphasize some essential of involvement of data science for epidemic forecasting, risk modeling, and policy support. Acknowledging how infectious disease plays a role in numerous amounts of deaths each year, the need to recognize the disease transmission is pivotal for prevention and societal safeguard [2]. Together, these approaches mark a paradigm shift; where managing infectious diseases no longer relies solely on biological knowledge, but equally on computational insights and collaborative information systems.
Background
[edit]Throughout most of history, human viewpoint towards epidemics or outbreaks had a combination of false theories and surprising extent of practical sense [3]. Eventually, detection and administration of infectious disease outbreaks relied mostly on manual reporting, clinical observation, and delayed laboratory confirmations. A reportable condition of infectious disease is where timely informing of individual cases is studied for the management and prevention of an outbreak or condition[4].The traditional methods, often suffered from slow response times and limited scalability, factors that proved critical during fast-moving outbreaks such as SARS in 2003[5] or H1N1 in 2009.This need gave rise to Infectious Disease Informatics a field that blends epidemiology, computer science, bioinformatics, and bio surveillance to enhance the management of infectious diseases.
Case study of HIV and SARs: A Network Analysis of comorbidity risk at the time of outbreak.
[edit]The rate of mortality and morbidity co-exist to a term "comorbidity" that is associated to the increase possibility of health conditions due to infections [6]. In simple term this word relates to the existence of diverse diseases and their caused disorders in an individual[7].So comorbidity occurs when it shows the relation between co-existence of two disease simultaneously in an individual or a patient. Similarly, viruses imposing risk on respiratory system of an individual has been emerging a threat to global medical security, severe acute respiratory syndrome (SARS) is a pandemic disease, along with coronavirus (CoV), has been termed as SARs associated coronavirus (SARS-CoV) [8].This case study shows an approach towards quantitative discovery of societal disease comorbidities considering various techniques of accessible mRNA expression, disease to gene relation, protein mapping, relation among two co existing diseases and the relation of drug to disease data[6].
Connection to broader Health Informatics domain
[edit]Disease Informatics is a branch within the broader aspect of Health Informatics, which focuses on collection of information and communication machinery in medical facilities. It comprise of diverse domains which serve a foundation for disease focused applications such as telemedicine, including Electronic health records (EHRs) which refers to how clinical systems are designed to for storing, retrieval and display of electronic data which is collected over the time a patient is under care[9].
IDI systems success rate depends on how well it can access and process clinical data from hospital information systems. As modern health informatics infrastructures facilitate real time data sharing, integration of diverse information systems, and the application of international standards such as HL7 FHIR (Fast Healthcare Interoperability Resources),these capabilities are essential for enabling timely and accurate infectious disease surveillance[10].
The Emerging role of Informatics in Public health practice
[edit]Control of infectious disease is the cornerstone of public health. Emerging informatics in public health shows a radical alteration in how health data is collected, monitored, analyzed and utilized to improve public/population health outcomes [11].
Essential services in public health practice
[edit]Public health practice is grounded based on three core functions: assessment, assurance and policy development. These show few essential services aimed at improving public health [11].
- By monitoring health status, diagnosing, educating and empowering communities to overcome medical issues.
- Enforce goverment regulations and laws to prioritize safety of societal health.
- Assure capable health service workforce.
- Continuous study/research for innovative techniques [11].
Syndromic surveillance as a tool for early detection
[edit]Infectious Disease Informatics (IDI) plays a vital role in enabling early detection and rapid response to outbreaks, particularly through tools like syndromic surveillance[12]. Syndromic surveillance (relates to public health surveillance) focuses on how a contagious disease can be identified and studied, while monitoring the current public health data.[12] These tools are progressively used for effective detection and response to any infectious disease, though it is a natural outbreak or a result of some lab experiment.
The approach of how this surveillance system works by implementing natural language processing to identify the potential primary factors of an epidemic.
- Patients encounter while seeking medical care at any healthcare facilities.
- Data collection is done by sending de-identifiable data such as symptoms and patients characteristics.
- Data is then shared with state or local health departments or HIEs.
- To enable early detection of public health risk, (NSSP) National Syndromic Surveillance Program hosted by CDC aggregates this information via Bio Sense platform.
- CDC supports surveillance by providing fundings, training to health departments, technical and project assistance and analytical tools for data analysis.
- This NSSP network of public health professionals collaborates to build capacity through training, live webinars, and joint efforts to improve surveillance methods and emergency responses.
Computational Methods in Disease Informatics
[edit]Machine learning
[edit]The role of Machine learning algorithm can play a pivotal role to control the downside of any infectious disease over time by predicting the cause and further spread[2].In recent years, machine learning techniques have been applied in multiple studies for forecasting case count of a specific disease within a specified location based on previous formulated data, the most common sources of an epidemic are identified with help of gene formulation of microbial agents and its pattern to understand the chances of a person contracting it[2].Other factors like livelihood and particular behavior of an individual is taken into consideration as well. For analyzing large, complex data sets to identify trends, techniques like Support vector machine, Ensemble learning, Conditional Random Field(CRF), Decision tree and other algorithms are used.
NLP & Text Mining
[edit]Natural Language processing (NLP) and text mining are highly considered for analyzing the patient data which consists of symptoms as this information are mostly provided in online health communities. It converts unstructured information into usable data for early detection and diagnosis. Along with NLP, text mining techniques help a health care facility or an organization to navigate the whole extensive knowledge base [1].The sequences are done through similarity search or keyword search. NLP tools known as (PubTator 3.0) which identifies relation across various entities as such genetic relation, chemical, variants, various infections, discovered species and cell mapping for experimental search [13].
Limitations and challenges
[edit]Despite the significant advancements in IDI, several challenges persist that hinder its optimal application, the accuracy of computational tools rely on it's accuracy and decision making. One concern is the lack of accessibility, most of the data collected isn't in standardized format, noisy and such practices lead to inconsistent data integration and potential impact on public health decisions [14]. As most of the times tools are prone to overfitting, bias, unaccurate predictions as trained incorrectly.
Another significant concern focuses on, these computational algorithms need to access huge amount of public health data, concerning the confidentiality and protection of the critical health information[15].This medical documents consist of sensitive information which needs to be protected for patient privacy. As such any computational work techniques need to follow the goverment enforced regulations, for instance in United States its HIPAA[14], similarly, in Europe Health Technology Assessment Regulation (HTAR), are for the evaluation of various medical trial benefits and the consequences of a new medical technology[15].These laws are applied when a computational medical experiment or tool such as robotic surgery or a software for diagnosis needs to demonstrate their safety and potential effective impact in the medical area[15] by undergoing data anonymization for de-identification.
References
[edit]- ^ a b c Sintchenko, Vitali, ed. (2010). "Infectious Disease Informatics". SpringerLink. doi:10.1007/978-1-4419-1327-2.
- ^ a b c Santangelo, Omar Enzo; Gentile, Vito; Pizzo, Stefano; Giordano, Domiziana; Cedrone, Fabrizio (2023-02-01). "Machine Learning and Prediction of Infectious Diseases: A Systematic Review". Machine Learning and Knowledge Extraction. 5 (1): 175–198. doi:10.3390/make5010013. ISSN 2504-4990.
{{cite journal}}: CS1 maint: unflagged free DOI (link) - ^ Burnet, Macfarlane; White, David O. (1972-08-24). Natural History of Infectious Disease. CUP Archive. ISBN 978-0-521-08389-8.
- ^ Adams, Deborah A.; Thomas, Kimberly R.; Jajosky, Ruth Ann; Foster, Loretta; Baroi, Gitangali; Sharp, Pearl; Onweh, Diana H.; Schley, Alan W.; Anderson, Willie J. (2017-08-11). "Summary of Notifiable Infectious Diseases and Conditions — United States, 2015". MMWR. Morbidity and Mortality Weekly Report. 64 (53): 1–143. doi:10.15585/mmwr.mm6453a1. ISSN 0149-2195.
- ^ Cherry, James D.; Krogstad, Paul (2004-07). "SARS: the first pandemic of the 21st century". Pediatric Research. 56 (1): 1–5. doi:10.1203/01.PDR.0000129184.87042.FC. ISSN 0031-3998. PMC 7086556. PMID 15152053.
{{cite journal}}: Check date values in:|date=(help) - ^ a b Moni, Mohammad Ali; Liò, Pietro (2014-12). "Network-based analysis of comorbidities risk during an infection: SARS and HIV case studies". BMC Bioinformatics. 15 (1). doi:10.1186/1471-2105-15-333. ISSN 1471-2105. PMC 4363349. PMID 25344230.
{{cite journal}}: Check date values in:|date=(help)CS1 maint: unflagged free DOI (link) - ^ Park, Juyong; Lee, Deok‐Sun; Christakis, Nicholas A; Barabási, Albert‐László (2009-01). "The impact of cellular networks on disease comorbidity". Molecular Systems Biology. 5 (1). doi:10.1038/msb.2009.16. ISSN 1744-4292.
{{cite journal}}: Check date values in:|date=(help) - ^ Tillett, Richard L; Sevinsky, Joel R; Hartley, Paul D; Kerwin, Heather; Crawford, Natalie; Gorzalski, Andrew; Laverdure, Chris; Verma, Subhash C; Rossetto, Cyprian C; Jackson, David; Farrell, Megan J; Van Hooser, Stephanie; Pandori, Mark (2021-01). "Genomic evidence for reinfection with SARS-CoV-2: a case study". The Lancet Infectious Diseases. 21 (1): 52–58. doi:10.1016/s1473-3099(20)30764-7. ISSN 1473-3099.
{{cite journal}}: Check date values in:|date=(help) - ^ Kim, Ellen; Rubinstein, Samuel M.; Nead, Kevin T.; Wojcieszynski, Andrzej P.; Gabriel, Peter E.; Warner, Jeremy L. (2019-10). "The Evolving Use of Electronic Health Records (EHR) for Research". Seminars in Radiation Oncology. 29 (4): 354–361. doi:10.1016/j.semradonc.2019.05.010. ISSN 1053-4296.
{{cite journal}}: Check date values in:|date=(help) - ^ Yogesh, M. J.; Karthikeyan, J. (2022-04-29). "Health Informatics: Engaging Modern Healthcare Units: A Brief Overview". Frontiers in Public Health. 10. doi:10.3389/fpubh.2022.854688. ISSN 2296-2565.
{{cite journal}}: CS1 maint: unflagged free DOI (link) - ^ a b c Lombardo, Joseph S.; Buckeridge, David L. (2012-11-09). Disease Surveillance: A Public Health Informatics Approach. John Wiley & Sons. ISBN 978-1-118-56905-4.
- ^ a b Chen, Hsinchun; Zeng, Daniel; Yan, Ping (2010), "Infectious Disease Informatics: An Introduction and An Analysis Framework", Infectious Disease Informatics, vol. 21, New York, NY: Springer US, pp. 3–8, doi:10.1007/978-1-4419-1278-7_1. pmcid: pmc7498878., ISBN 978-1-4419-1277-0, retrieved 2025-04-16
{{citation}}: Check|doi=value (help) - ^ Wei, Chih-Hsuan; Allot, Alexis; Lai, Po-Ting; Leaman, Robert; Tian, Shubo; Luo, Ling; Jin, Qiao; Wang, Zhizheng; Chen, Qingyu; Lu, Zhiyong (2024-07-05). "PubTator 3.0: an AI-powered literature resource for unlocking biomedical knowledge". Nucleic Acids Research. 52 (W1): W540 – W546. doi:10.1093/nar/gkae235. ISSN 0305-1048. PMC 11223843. PMID 38572754.
- ^ a b Olawade, David B.; Wada, Ojima J.; David-Olawade, Aanuoluwapo Clement; Kunonga, Edward; Abaire, Olawale; Ling, Jonathan (2023-10-26). "Using artificial intelligence to improve public health: a narrative review". Frontiers in Public Health. 11. doi:10.3389/fpubh.2023.1196397. ISSN 2296-2565.
{{cite journal}}: CS1 maint: unflagged free DOI (link) - ^ a b c Sarantopoulos, Andreas; Mastori Kourmpani, Christina; Yokarasa, Atshaya Lily; Makamanzi, Chiedza; Antoniou, Polyna; Spernovasilis, Nikolaos; Tsioutis, Constantinos (2024-09-30). "Artificial Intelligence in Infectious Disease Clinical Practice: An Overview of Gaps, Opportunities, and Limitations". Tropical Medicine and Infectious Disease. 9 (10): 228. doi:10.3390/tropicalmed9100228. ISSN 2414-6366.
{{cite journal}}: CS1 maint: unflagged free DOI (link)