Sille / Choudhury / Talreja Elevating Next Generation Genomic Science and Technology using Machine Learning in the Healthcare Industry

1. Auflage 2026
ISBN: 979-8-89881-549-3
Verlag: De Gruyter
Format: EPUB
Kopierschutz: 0 - No protection

E-Book, Englisch, Band 4, 232 Seiten

Reihe: Applied Machine Learning for IoT and Data Analytics

Applied Machine Learning for IoT and Data Analytics (Volume-4)- Elevating Next Generation Genomic Science and Technology Using Machine Learning for the Healthcare Sector explores how machine learning and artificial intelligence are transforming modern genomics and healthcare. The book highlights how advanced computational methods can analyse complex genomic data to improve disease detection, enable personalised treatments, and support precision medicine.
It covers key applications such as AI-driven cancer detection, microbiome analysis, genome annotation, mutation detection, and pharmacogenomics. The chapters also discuss real-world healthcare applications, ethical concerns, and data privacy challenges, offering a balanced view of both opportunities and limitations in AI-driven genomic research.
Key Features:
-Comprehensive coverage of machine learning applications in genomics
-Focus on precision medicine, disease prediction, and personalised therapies
-Integration of bioinformatics, AI, and healthcare applications
-Real-world case studies and analytical frameworks
-Discussion of ethical, privacy, and regulatory considerations

Autoren/Hrsg.

Sille, Roohi

Choudhury, Tanupriya

Talreja, Sonal

Balamurugan, S

Fachgebiete

• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz

Leseproben

Overview of Next Generation Genomic Science and Technology Utilising Machine Learning in Healthcare

Garima Sharma1, *

1 Department of Botany, SMS Govt. Model Science College, Gwalior, India

Abstract

Genomics is an interdisciplinary field of molecular biology that focuses on studying the structure and function of the gene as well as its relation to gene mapping and tailoring of the genome. The techniques of genomics have led to a revolution in the area of clinical medicine and public health. Genomics plays a critical role in health science by identifying targeted genes, precision in treatment, and drug therapies for patients. The tremendous progress in genomics in the healthcare field is due to the high speed, low cost, increased accuracy, and improved sensitivity of its techniques. The next generation of genomics is marked by recent advances in the field, which utilise computational tools, like artificial intelligence and machine learning. Machine Learning (ML) allows computers to learn, filter, and classify data without human intervention. The Next Generation genomic science technology has major applications in the fields of early detection of tumour gene analysis, non-invasive prenatal screening, and genomic tests for childhood and rare disorders. In this article, we have discussed some recent advances in Next-Generation Machine Learning techniques (NGML) in healthcare and summarised their applications in some recent genomic science techniques like Nanopore sequencing, CRISPR-Cas system, and Spatial transcriptomes technique.

Keywords: Artificial neural network, CRISPR-Cas system, Deep learning, Machine learning, Medical image analysis, Spatial transcriptosome.

* Corresponding author Garima Sharma: Department of Botany, SMS Govt. Model Science College, Gwalior, India;
E-mail: [e-mail]

INTRODUCTION

The study of genes of an individual and its analytical applications in healthcare are the most advanced fields of medicine, collectively known as ‘Genomic Medicine.’ Genomic medicine helps with the diagnosis, treatment, and prevention of disease, and it is gradually revolutionizing the scenario in healthcare from pre-

dicting diseases to finding cures. Especially after the COVID-19 outbreak, genomic medicine has proved its marvellous role in delivering next-generation breakthroughs in designing diagnostic kits, drug delivery systems, and gene therapies.

Currently, healthcare is experiencing a paradigm shift as there is a continuous rise in the availability of health records of patients in electronic forms known as Electronic Health Records (EHRs) and the growing advances in techniques of medical imaging. ‘Machine learning’ in healthcare has become one of the most popular buzzwords these days as it helps healthcare professionals to utilise artificial intelligence for providing better care for patients and managing their clinical data. Machine learning is showing a positive impact in this field, although its full potential is still not realised. In the coming years, the use of Machine learning in healthcare will become even more essential and revolutionary due to continuously growing clinical data sets.

Machine Learning (ML) has emerged as a key enabler of this transformation, with applications ranging from disease diagnosis to population health management. ML is the process of programming and training computers to learn and analyse the given clinical details, to understand the patterns of disease, and to recommend treatments. The healthcare professionals are gradually adapting and recognising the potential of machine learning to reduce workload, cost of treatment, risks, and improve decision-making in this field. The demand for a skilled workforce in the area of machine learning for healthcare industries is continuously on the rise.

The two terms, “artificial intelligence” and “machine learning,” might seem to be the same. Artificial Intelligence (AI) is a specialised part of computational technology that creates computer machines that can partially or fully replicate the intelligence of the human brain in various fields. The cleaning robots, self-driven cars, etc., are examples of AI. Machine learning is a type of AI application in which a computer is trained to learn and improve from observations of patterns and correlations without direct instruction. In this way, ML can allow a computer to make predictions and take decisions like human experts. Machine learning applications improve with use and become more and more accurate as they get access to more data. With the advent of technology, expansion in medical data and its analysis tools, the machine learning technique is, day by day, providing exciting opportunities in healthcare.

The following are some of the benefits of machine learning applications in the healthcare industry:

Improving Diagnosis: Machine learning can be used to design and develop better diagnostic tools to make quicker and more accurate analysis of medical images like X-rays or MRI. With the help of machine learning, various patterns in the scan are identified that indicate a particular disease. This is very important in case of fast-progressing diseases to improve patient care.

Developing New Treatment Methods: With the help of machine learning, healthcare organisations and pharmaceutical companies can identify relevant information by analysing patterns in medical data of unknown/ rare side effects of drugs, thus improving patient care, drug discovery, safety, and effectiveness of drugs or medical procedures.

Reducing Healthcare Costs: Machine learning technologies have significantly improved the efficiency of healthcare services by reducing the time and resources required for diagnosis. Additionally, better algorithms are being developed for managing patient consultations and health records.

Increasing Patient Data Security: The privacy of patients’ Electronic Health Records (EHR) is of paramount importance. For this, Machine learning is very useful as it can detect cyber threats in real-time and manage them. New algorithms can identify abnormal/ non-specific patterns to identify any breach to cybersecurity, thus ensuring the protection of patient data.

The key areas of healthcare in which machine learning has played an important role are shown in Fig. (1) [1]:

Fig. (1))
Key areas of healthcare affected by machine learning.

NEXT GENERATION MACHINE LEARNING (NGML) TECHNIQUES

The next generation of ML is poised to further transform the field of healthcare by leveraging advances in data analytics, computing power, and algorithmic complexity. Many techniques that may be included in next-generation machine learning, and their applications in healthcare, are discussed in the following section:

A. Deep Learning (DL): It is an advanced type of machine learning that can be used to analyse a bulk of complex data and patterns with minimal human intervention. A traditional machine learning has the following steps: a. data collection and pre-processing, b. choosing a model, c. training a model, and d. evaluation of the model. In the pre-processing, raw data is converted into a suitable internal representation from which the classifier can detect patterns. This is where the main difference between machine learning and deep learning lies, as deep learning has multiple hidden layers and their connections. Thus, deep learning has more efficiency and the capability to learn meaningful abstractions of the inputs. In traditional learning, only three layers are used to supervise specific tasks, and it is not generalizable [2]. In contrast, in deep learning, there are multiple layers and connectors that represent the pattern observed in the input data received from the layer below by optimising a local unsupervised criterion [3]. Fig. (2) demonstrates the comparison of the architecture of a traditional Machine Learning (ML) and a Deep Learning (DL) [4].

Fig. (2))
Basic architecture of an ANN and a Deep learning model.

There are four types of architectures in deep learning: Convolutional network, Recurrent neural network, the Deep belief network, and the Autoencoder.

The Convolutional Neural Network: A CNN typically consists of multiple layers, including:

A. Convolutional Layers: These layers scan the image in both horizontal and vertical directions and apply a set of filters to the input image.

B. Pooling Layers: The purpose of these layers is to downsample the feature maps, thus reducing the spatial dimensions without loss of any important information.

C. Fully Connected Layers: These layers take the output of convolutional and pooling layers as input and use it for classification. Figs. (3 and 4) show functions and basic architecture of CNN.

Fig. (3))
The basic architecture and flow in a convolutional network. Fig. (4))
Basic convolutional neural...