The Role of Data Science in Predictive Analytics for Healthcare

DOI : 10.17577/IJERTV13IS060073

Download Full-Text PDF Cite this Publication

Text Only Version

The Role of Data Science in Predictive Analytics for Healthcare

Naman Sanghvi

The Bishops School Pune,

Maharashtra, India

Anish Porwal

S.M Choksey Jr.College Pune, Maharashtra, India

Niev Sanghvi

The Bishops School Pune,

Maharashtra, India

Nellay Rawalh Vishwakarma Institute of Information Technology Pune,Maharashtra India

Niel Sanghvi

The Bishops School Pune,

Maharashtra, India

Arnav Chorbele

Pace University, New York

AbstractThis research paper provides an introductory exploration of the central role of data science in predictive healthcare for those new to the subject. Using simplified explanations and comparable examples, the article explains how data science facilitates the prediction of health outcomes, promotes early detection, individualized treatment and improves patient care. By describing the practical applications and potential benefits of data-driven approaches in healthcare, this article aims to increase comprehensive understanding and spark readers' curiosity about the transformative potential of data science in healthcare.

  1. INTRODUCTION

    1. Introduction to Data Science and Healthcare Analytics: Health analytics is a specialized field of data science that focuses on using data to improve health outcomes. Think of it as a way

      for doctors and healthcare professionals to use data to understand patient health, predict disease and even personalize treatment.

      This helps doctors make informed decisions and improves the overall quality of healthcare. Information science and health analytics work together to improve health care. Data science helps us collect and process data, while health analytics helps us apply this information to real-world medical situations. For example, they can analyze patient data to find patterns that can indicate the early onset of disease or help identify the most effective treatments for different diseases.Simply put, data science helps us make sense of large reams of health data, and health analytics uses that understanding to improve patient care and outcomes.The development of the digital age has caused healthcare and technological confusion, which has led to the emergence of newer data-related applications [1].Given the large amount of clinical data generated by the healthcare industry, such as patient electronic health records (EHRs),prescriptions, clinical reports, drug purchase data, health insurance information, research and laboratory reports, there is a huge opportunity. analyze and study them with the latest technology[2]. Large amounts of data can be combined and

      efficiently analyzed using machine learning algorithms.Analyzing data details and understanding patterns can help improve decision making, leading to better quality of care for patients. This can help understand trends, improve treatment outcomes, life expectancy,early detection and recognition of diseases at an early stage, and necessary treatment at an affordable cost [3]. A health information exchange (HIE) can be implemented to help extract clinical data from multiple repositories and combine it into a single individual health record for safe use by all caregivers. Therefore, healthcare organizations should strive to acquire all available tools and infrastructure to take advantage of big data, which can increase revenues and profits and create better healthcare networks and differentiation.you get significant benefits [4, 5]. Data mining techniques may create a transition from traditional medical databases to data-rich evidence-based health environment in the next decade of.

    2. Overview of Healthcare Analytics:

    Health analytics involves the use of data analysis tools and techniques to obtain health-related information. It helps healthcare professionals make better decisions, improve patient care and improve the overall efficiency of the healthcare system.

    The Importance of Healthcare:

    Improved patient care: By analyzing data about patient health, treatment and outcomes, healthcare professionals can identify trends and patterns that can adjust treatment plans and improve patient outcomes.

    Cost reduction: Analyzing health data can help identify areas where costs can be reduced without compromising

    patient care, such as optimizing resource allocation and reducing unnecessary procedures.

    Preventive care: Health analytics can predict potential health risks and diseases by analyzing factors such as lifestyle, genetics and medical history, enabling proactive prevention.

    Healthcare management: Data analytics can help healthcare facilities manage resources more efficiently, streamline operations and identify areas for improvement in processes and workflows.

    Research and Development: Analyzing health data can lead to new discoveries, advances in medical research and development of innovative treatments and technologies.

    Mechanism of Healthcare analytics:

    Data Collection: Health services are collected from a variety of sources, such as electronic health records (EHRs), medical devices, patient surveys, and administrative records.

    Data Storage and Management: Collected data is stored in databases and managed securely to ensure patient privacy and compliance with regulations such as HIPAA (Health Insurance Portability and Accountability Act).

    Data analytics: Analytical techniques such as statistical analysis, machine learning, and predictive modeling are applied to health data to discover insights and patterns.

    Visualization and Reporting: Analyzed data is often visualized using graphs, charts and dashboards to help healthcare professionals understand and interpret results.

    Decision making: insights from health analytics are used in decision-making processes such as care plans, resource allocation and policy development.

  2. FOUNDATION OF DATA SCIENCE IN HEALTHCARE

    1. Data storage and organization:

      After collection, health data must be securely stored in databases. It's like organizing files on your computer into folders so you can easily find them when you need them.

    2. Data Analysis:

      This is where the magic happens! Data analytics uses special techniques and algorithms to find patterns and insights in data.

      Imagine you are a detective looking for clues in a mystery novel; data analysis helps us uncover the hidden stories of data.

    3. Machine Learning and Predictive Modeling:

      Machine learning is a fancy term for teaching computers to learn from data and make predictions or decisions without special programming.

      Predictive modeling uses past data to predict future outcomes, such as whether a patient is at risk for a particular disease based on their medical history.

    4. Visualization:

      Data visualization means converting data into graphs, charts and other visual forms that facilitate understanding and interpretation.

      It's like turning numbers into a colorful picture that tells a story.

    5. Application in Health Care:

      Health informatics helps doctors and researchers in many ways:

      Individualized patient care based on their unique characteristics.

      Anticipates diseases and plans preventive measures. Improve hospital performance by optimizing resources and reducing waiting times.

      Discovering new treatments by analyzing large data sets.

      A. Data collection:

      p>Healthcare collects data from a variety of sources, such as patient records, lab results, medical images and even wearable devices such as fitness trackers.

      Think of it like putting puzzle pieces together, where each piece represents a different aspect of the patient's health.

    6. Ethical Aspects:

    It is important to use health information responsibly and ethically, respecting patient privacy and confidentiality.

    As in real life, we must handle sensitive information with care and always put patients' well-being first.

    Healthcare data science is fundamentally about using technology and creativity to unlock the secrets of health data, with the ultimate goal of improving patient care and advancing medical knowledge.

  3. IMPORTANCE OF DATA DRIVEN DECISION MAKING IN HEALTHCARE

    1. Better patient care:

      Informed health decisions help doctors and nurses provide better care to patients. By analyzing patient data, healthcare professionals can tailor treatment to individual needs, leading to better outcomes and faster recovery times.

    2. Early detection of diseases:

      Analysis of treatment data allows doctors to detect diseases at earlier stages. By identifying patterns in patient data, healthcare professionals can identify risk factors and warning signs, enabling earlier intervention and potentially saving lives.

    3. Effective allocation of resources:

      Hospitals and health facilities have limited resources such as staff, equipment and beds. Data-driven decision making helps optimize resource allocation by identifying high-demand or inefficient areas and ensuring that resources are used where they are most needed.

    4. Reduce costs:

      Health care can be expensive, but making informed decisions can help reduce costs. By analyzing data on treatments, interventions and outcomes, healthcare providers can identify opportunities to streamline processes, reduce waste and lower overall healthcare costs.

    5. Better public health:

      Informed decision making is critical to responding to public health problems such as epidemics and epidemics. By analyzing population health data, health authorities can monitor the spread of disease, identify risk groups and implement targeted measures to prevent infections.

    6. Evidence-Based Medicine:

      Evidence-based decision-making promotes evidence-based medicine, where treatments and interventions are based on scientific evidence and clinical knowledge rather than anecdotal experience or intuition. This ensures that patients receive the most effective and appropriate treatment based on the latest research and best practice.

    7. Continuous Improvement:

    Healthcare is constantly evolving and informed decision making enables continuous improvement. By regularly analyzing data and tracking results, healthcare providers can identify areas for improvement, implement changes, and monitor the impact of change over time, resulting in continuous improvement in

    patient care. Overall, informed decision making is critical in health care because it leads to better patient outcomes, more efficient use of resources, and continuous improvement in the quality of care provided to patients. By harnessing the power of information, healthcare professionals can make informed decisions that positively affect both individual patients and the health of the public at large.

    III. APPLICATIONS OF DATA SCIENCE IN HEALTHCARE

    1. Predictive analytics: Data science can be used to analyze patient data to predict the likelihood of certain diseases or conditions, allowing healthcare providers to intervene early and prevent potential health problems.

    2. Electronic Health Records (EHR) Management: Information science helps organize and manage electronic health records and ensure that patient records are easily accessible, accurate and secure.

    3. Medical Image Analysis: Data science is used to interpret and analyze medical images such as X-rays, MRI and CT scans, helping healthcare professionals diagnose and monitor diseases such as tumors, fractures and internal injuries.

    4. Drug discovery and development: Data science plays an important role in the analysis of biological and chemical data that helps in the discovery and development of new drugs and treatments for various diseases.

    5. Personalized medicine: Using data analytics, healthcare professionals can tailor their treatment plans and drug dosages based on a person's genetic, environmental and lifestyle factors, resulting in more personalized and effective healthcare.

    6. Predicting diseases: Data science can be used to analyze patterns in public health data to predict and track diseases, allowing authorities to take proactive measures and allocate resources efficiently.

    7. Health Monitoring Devices: Data science is used in the development and analysis of wearable health monitoring devices that provide real-time information about vital signs and health parameters to individuals and health professionals.

    It is estimated that at least ten percent of all hospitalized patients in Europe experience adverse events, including adverse events (ADEs), healthcare-associated infections (HAIs), falls and exudation wounds – a total of three million patients per year [7]

    . Such side effects prolong the patient's treatment, cause suffering to the patient and are costly to society. In Sweden, with ten million inhabitants, it is estimated that AE is responsible for 750,000 additional hospital days at a cost of 700 million euros per year, without taking into account patient suffering [8]. Therefore, AE detection is a critical issue in healthcare.

    The Stockholm EPR corpus of Stockholm University has been used for several research projects of practical importance in health care. These projects included HAI detection, postmarketing ADE detection, EHR text simplification for lay users, automated ICD10 diagnosis code assignment, cancer data and pathology report mining to further improve cancer screening, and comorbidity studies.Successful development of such applications requires basic word processors. EHR clinical notes are difficult to process for several reasons: they contain many typos, non-standard words and abbreviations, incomplete sentences and medical jargon. That is why we have developed a set of basic tools for processing clinical text written in Swedish. These include fact-level classification [9, 10], negation detection [11], typer detection [12], abbreviation normalization, [13, 14, 15], called entity detection [16, 17 ], and medical vocabularies as tools for extension [18, 19, 20, 21].We have also pioneered research on characterizing domain-specific language in this type of text [22] and conducted studies on how well linguistic tools and techniques work in clinical notes, such as syntactic analyzers [23]. and distributed semantic models – important research for the future developing tools tailored to this field. The development of these tools also included the creation of seven reference standards manually labeled for de-identification (protected health data), expert levels of diagnostic expressions, clinical designation units,indications and ADE ratios, cervical cancer symptoms.HAI classifications (healthcare-associated infections)clinical abbreviations. Many of the tools mentioned above are trained on annotated corpora. We want to share these valuable resources with other researchers.

    Fig 1. Various applications of data science in healthcare

  4. TECHNIQUES AND TOOLS IN PREDICTIVE HEALTHCARE ANALYTICS

  1. Introduction to Machine Learning Algorithms: Machine Learning algorithms are like virtual detectives in healthcare, trained to uncover hidden patterns in patient data. These algorithms learn from past cases to predict future health outcomes or help doctors make decisions. By analyzing massive amounts of data, they can help identify potential health risks at an early stage and guide healthcare professionals to more individualized treatment plans. Examples of machine learning algorithms include decision trees, which mimic a flowchart for making decisions, and neural networks inspired by the human brain. These virtual detectives are becoming valuable tools in healthcare, providing insights that were once impossible to obtain from traditional analytical methods.

  2. Data Collection and Preprocessing Methods: Imagine collecting puzzle pieces across a room – similar to collecting health data. From electronic health records to genetic information, a variety of sources provide valuable information about a patient's health history. But before this data can be used effectively, it must be cleaned and organized, like pieces of a puzzle. This preprocessing step involves removing errors, handling missing data, and ensuring data consistency. By carefully preparing the data, healthcare professionals ensure that the insights they gain are accurate and reliable, similar to ready-made puzzles that reveal a clear picture of a patient's health.

  3. Health Information Privacy and Ethical Considerations: Just as physicians respect patient confidentiality, health information privacy ensures that sensitive medical information is protected in the digital world. Respect for patient privacy is paramount, and strict regulations such as the Health Insurance Portability and Accountability Act (HIPAA) are in place to

protect this confidentiality. Ethical aspects of health analytics emphasize the responsible use of patient data, ensuring data collection with patient consent and ethical use for research and analysis purposes. By prioritizing ethical guidelines and data protection measures, healthcare professionals maintain trust with patients and preserve the integrity of healthcare analytics practices.

TABLE I

Sr.no

Example of Predictive Analytics Techniques

Technique

Description

Application in Healthcare

1.

Decision Tree

Hierarchical decision- making models based on data

Treatment outcome prediction, disease diagnosis

2.

Logistic Regression

Statistical modeling technique for predicting outcomes

Identifying disease risk factors, mortality prediction

3.

Neural Networks

Algorithms inspired by the human brain for pattern recognition

Medical image analysis, disease classification

Table 1. Examples of Predictive Analytics Techniques

VI. CHALLENGES AND FUTURE TRENDS

Data science and data mining are becoming more common in the private and public domain. Companies such as banking, insurance, pharmaceuticals and retail often use data mining to lower fees, improve research and increase auctions. Therefore, data science and mining will gradually become valuable in the coming period. Information science continues to resemble the growth of software, and its additional diverse project increases its viability in computing.For the convenience of our regions,access to this digital gold may require external commitment to opportunities and disputes. As the amount of data grows,SC algorithms become more elegant and our computing capabilities, and customization requirements evolve. Creating a

strong case for using data science at our institution and preparing for what the next spell

will bring. Three intertwined trends, growing volumes of data, higher quality SC procedures and advanced computing ability are having an electrifying effect on the field of data science.

Enhancing valuable insights into object/business data and the insights they convey. Almost all companies today make data selections using one method or another. And if they don't, they'll have to sort it out soon. Data science works ad hoc and is about how modern information technologies are used to solve business problems for targeted benefits. In the near future, data scientists will practice their profession in the opposite way. As big data, algorithmic geoeconomics, the Internet of Things and the cloud continue amid universal locations developing into mainstream trends, stores largely accelerate familiarization with new low-cost practices and remain at the forefront of development. The two most important facts of this development are the mechanization of information methods and the sharing of immediate logical results.

The future of SC in healthcare is very favorable with many forward-looking SC practices such as deep reinforcement, one-time learning and capsule network in collaboration with physicians to enable innovative SC practices in biomedicine and healthcare knowledge that SC can be ubiquitous and invisible in the healthcare fields of the future, using new information from various sources.

Additionally, crossover

between clinicians and data and computer scientists and analysts is needed to ensure data-to-data consistency and data-to-intelligence communication. Future of SC: Augmented and Virtual Reality Blockchain and Cyber- Secure Cloud Computing Learning and New Learning Types (Capsule Web) (Third Wave) (Deep Sensing) Internet of Everything.

  1. Ethical considerations for health data analysis:

    Ethical considerations are central to the analysis of health data, ensuring that patient privacy, consent and confidentiality are respected. When analyzing health data, it is important to consider the ethical impact of using sensitive data to make health decisions. Respect for patient autonomy and confidentiality is essential, and health professionals must follow ethical guidelines and regulations to protect patient rights. Data usage transparency, informed consent, and secure data practices are the cornerstones of ethical healthcare data analysis. By adhering to ethical standards, healthcare professionals can build trust with patients and ensure that data analysis is conducted responsibly and ethically.

    TABLE II

    Sr.no

    Key Ethical Considerations in Healthcare Analytics

    Consideration

    Description

    Importance in Healthcare

    1.

    Patient Privacy

    Protecting sensitive medical information and maintaining confidentiali ty

    HIPAA

    compliance, patient trust

    2.

    Informed Data Consent

    Obtaining permission from patients for the use of their healthcare data

    Ethical data usage, patient autonomy

    3.

    Data Security and Confidentiality

    Ensuring secure storage and transmission of patient information

    Preventing unauthorized access to sensitive data

    Table 2. Key Ethical Considerations in Healthcare Analytics

  2. Challenges in Applying Predictive Analytics in Healthcare Environments:

    Applying predictive analytics in healthcare presents several challenges such as data quality issues, system interoperability and resilience to change. Ensuring the accuracy and reliability of health information is a significant challenge, as information from

  3. Future Opportunities and Emerging Trends in Health Analytics:

The future of health analytics has great potential to transform patient care through advanced technologies and data insight. Emerging trends in health analytics include the widespread adoption of artificial intelligence and machine learning algorithms to improve diagnosis, personalized medicine and treatment optimization. Predictive modeling tools are being developed to predict disease outcomes, optimize resource allocation, and improve patient outcomes. There is also increasing use of mobile devices and remote monitoring technologies that enable continuous data collection and real-time health monitoring. In addition, the integration of genomic data in health analytics promises to open new opportunities for personalized medicine and targeted therapy. As health analytics continues to evolve, the future holds exciting opportunities for improving health delivery, patient outcomes, and overall health system efficiency.[24]

VII. CONCLUSION

  1. The role of data science in predictive health analytics: Data science plays a key role in predictive health analytics, revolutionizing the way healthcare professionals interpret patient data and make informed decisions. Through advanced analytics, machine learning and predictive modeling, data science empowers healthcare providers to predict and prevent disease, adjust treatment plans and optimize patient outcomes. Harnessing the power of data, predictive health analytics enables early intervention, individualized treatment and better healthcare.

  2. Final thoughts on the impact and future of data-driven healthcare:

    The impact of data-driven healthcare is transformative, paving the way for more accurate diagnoses, personalized treatment and predictive disease management. The future of healthcare holds tremendous promise as data-driven technologies advance, potentially revolutionizing healthcare and improving patient outcomes. The adoption of data-driven approaches will lead to more efficient health systems, better allocation of resources and, ultimately, improved quality of patient care.

    multiple sources can vary in form and quality. Integrating predictive analytics into existing healthcare systems can also be challenging and requires compatibility with different software platforms and data sources. In addition, healthcare professionals and organizations may face resistance to the adoption of predictive analytics due to concerns about job transitions, training requirements, and algorithmic predictions. Meeting

    these challenges requires collaboration among healthcare stakeholders, investment in technology infrastructure and training to increase confidence in predictive analytics

    solutions.

  3. A call for continued research and innovation in this area: As we see the profound impact of knowledge-based approaches in health care, it is imperative to support continued research and innovation in this area. By fostering interdisciplinary collaboration, investing in health information infrastructure, and promoting ethical data practices, we can advance the development of predictive

IJERTV13IS060073

(This work is licensed under a Creative Commons Attribution 4.0 International License.)

health analytics. Embracing a culture of innovation and continuous learning will lead the healthcare industry to a future where data insights empower healthcare providers and positively impact patient well-being.

In conclusion, this research paper discussed the crucial role of data science in predictive health analytics and highlighted its transformative impact on healthcare. With advanced analytics and machine learning, healthcare professionals can predict and prevent disease, modify treatment plans and optimize patient outcomes. The future of data-driven healthcare promises more accurate diagnoses, tailored treatment and better allocation of resources. It is important to support continued research and innovation in this area, ensuring responsible data practices and ethical considerations. Embracing a culture of innovation and continuous learning will lead the healthcare industry to a future where data insights empower healthcare providers and positively impact patient well-being.

REFERENCE

  1. S. V. G. Subrahmanya et al., The role of data science in healthcare advancements: applications, benefits, and future prospects, Irish Journal of Medical Science (1971 -), vol. 191, no. 4, pp. 14731483, Aug. 2021, doi: 10.1007/s11845-021-02730-z.

  2. Sengupta PP (2013) Intelligent platforms for disease assessment: novel approaches in functional echocardiography. JACC: Cardiovascular Imaging 6(11):12061211. https://doi.org/10.1016/j.jcmg.2013.09.003

  3. Muni Kumar N, Manjula R (2014) Role of big data analytics in rural health care-a step towards svasth bharat. Int J Comp Sci Inform Technol 5(6):7172 7178

  4. Ren Y, Werner R, Pazzi N, Boukerche A (2010) Monitoring patients via a secure and mobile healthcare system. IEEE Wirel Commun 17(1):5965

  5. IBM Corporation (2013) Datadriven healthcare organizations use big data analytics for big gains. https://silo.tips/download/ibm-software-white-paper- data-driven-healthcareorganizations-use-big-data-analy

  6. Burghard C (2012) Big data and analytics key to accountable care success.

    IDC health insights :19

  7. Humphreys, H., Smyth, E.T.M.: Prevalence surveys of healthcare-associated infections: what do they tell us, if anything? Clinical Microbiology and Infection 12(1), 24 (2006)

  8. SALAR: Swedish Association of Local Authorities and Regions: Vårdrelaterade infektioner framgångsfaktorer som förebygger. Stockholm, Sweden.ISBN:978-91-7585-109-9,

    http://webbutik.skl.se/bilder/artiklar/pdf/978-91-7585-109-9.pdf, Accessed April 10 (2014)

  9. Velupillai, S.: Shades of Certainty: Annotation and Classification of Swedish Medical Records. Ph.D. thesis, Stockholm University (2012)

  10. Velupillai, S., Skeppstedt, M., Kvist, M., Mowery, D., Chapman, B.E., Dalianis, H., Chapman, W.W.: Cue-based assertion classification for swedish clinical textdeveloping a lexicon for pycontextswe. Artificial intelligence in medicine 61(3), 137144 (2014)

  11. Skeppstedt, M.: Negation detection in Swedish clinical text: An adaption of NegEx to Swedish. Journal of Biomedical Semantics 2(Suppl 3), S3 (2011)

  12. Isenius, N., Velupillai, S., Kvist, M.: Initial Results in the Development of SCAN:a Swedish Clinical Abbreviation Normalizer. In: Proceedings of the CLEF 2012 Workshop on Cross-Language Evaluation of Methods, Applications, and Resources for eHealth Document Analysis – CLEFeHealtp012. CLEF, Rome,Italy (September 2012)

  13. Kvist, M., Velupillai, S.: SCAN: A Swedish Clinical Abbreviation Normalizer. In: Information Access Evaluation. Multilinguality, Multimodality, and Interaction, pp. 6273. Springer (2014)

  14. Tengstrand, L., Megyesi, B., Henriksson, A., Duneld, M., Kvist, M.: EACL Expansion of Abbreviations in Clinical text. In: Proceedings of the 3rd Workshop on Predicting and Improving Text Readability for Target Reader Populations (PITR). pp. 94103. Association for Computational Linguistics (2014)

  15. Skeppstedt, M., Kvist, M., Nilsson, G., Dalianis, H.: Automatic recognition of disorders, findings, pharmaceuticals and body structures from clinical text: An annotation and machine learning study. In: Journal of Biomedical Informatics, 49. pp. 148158

  16. Henriksson, A., Dalianis, H., Kowalski, S.: Generating features for named entity recognition by learning prototypes in semantic space: The case of de-identifyin health records. In: International Conference on Bioinformatics and Biomedicine (BIBM). pp. 450

    457. IEEE (2014)

  17. Henriksson, A., Conway, M., Duneld, M., Chapman, W.W.: Identifying synonymy between SNOMED clinical terms of varying length using distributional analysis of electronic health records. In: AMIA Annual Symposium Proceedings. pp. 600609. American Medical Informatics Association (2013)

  18. Henriksson, A., Skeppstedt, M., Kvist, M., Duneld, M., Conway, M.: Corpus-driven terminology development: populating Swedish SNOMED CT with synonyms extracted from electronic health records. In: Proceedings of BioNLP. pp. 3644. Association for Computational Linguistics (2013)

  19. Skeppstedt, M., Ahltorp, M., Henriksson, A.: Vocabulary expansion by semantic extraction of medical terms. In: The 5th International Symposium on Languages in Biology and Medicine (LBM). pp. 63 68 (2013)

  20. Henriksson, A., Moen, H., Skeppstedt, M., Daudaravicius, V., Duneld, M.: Synonym extraction and abbreviation expansion with ensembles of semantic spaces. J. Biomedical Semantics 5(6) (2014)

  21. Smith, K., Megyesi, B., Velupillai, S., Kvist, M.: Professional language in Swedish clinical text: Linguistic characterization and comparative studies. Nordic Journal of Linguistics 2, 297327 (2014)

  22. Hassel, M., Henriksson, A., Velupillai, S.: Something Old, Something New Applying a Pre-trained Parsing Model to Clinical Swedish. In: Proc. 18th Nordic Conf. on Comp. Ling. – NODALIDA 11 (May 11-13 2011),

    http://dspace.utlib.ee/dspace/handle/10062/17355

  23. Henriksson, A.: Semantic Spaces of Clinical Text: Leveraging Distributional Semantics for Natural Language Processing of Electronic Health Records. Licentiate Thesis, Stockholm University (2013)

  24. S. Dhamodaran and A. Balmoor, Future Trends of the Healthcare Data Predictive Analytics using Soft Computing Techniques in Data Science, CVR Journal of Science and Technology, vol. 16, no. 1, pp. 8996, Jul. 2019.

Cite relevant scholarly articles, reports,and ethical guidelines pertaining to AI ethics in Data Science.

IJERTV13IS060073

(This work is licensed under a Creative Commons Attribution 4.0 International License.)