Multiomics and digital biomic solutions in cancer care

• Digital biomics has the potential to transform healthcare on virtual platforms
• A multifaceted approach will be necessary to effectively leverage biomics technologies in healthcare
• AI analytics will play a key role in unlocking digital biomics’ potential and further enhancing healthcare decisions

The convergence of ‘omics, digital health, and data science has ushered in a new era in medical research and healthcare delivery, bringing transformative advancements in diagnostics, personalized medicine, and genomics research.  Advanced technologies and their synergistic applications can revolutionize healthcare worldwide, providing more precise treatment pathways to a larger population. This breakthrough can transform healthcare delivery and improve patient care globally.

‘Omics science has the potential to improve understanding of underlying mechanisms of disease and provide better biomarkers of disease risk and responses to interventions. Digital biomics combines omics science with the insights we gain from digital sources of data.^1,2 Digital health, including telemedicine, electronic health records (EHR), wearable, implantable, injectable & ingestible digital medical devices, and tools like sensors and apps, allow for the collection of real-time behavioral and physiological data within an individual’s environment.^1,2 Data science allows integration and analysis of these real-time data and other large datasets to provide comprehensive models of disease risk and responses to interventions.³ This also includes the application of artificial intelligence (AI) and machine learning (ML) algorithms to medical and public health prognosis and decision-making.

The area of oncology is just one example of where data science is playing a vital role in advancing personalized healthcare. Through the use of predictive analytics, data science is helping us to gain a much deeper understanding of the molecular dysfunctions caused by cancer-associated mutations.⁴ These insights also enable us to design more effective clinical decision support systems. In addition, they are helping us to better manage the huge volumes of data generated from the different omics branches and ensure they can be used for diagnostics and therapeutic purposes.⁴

Using computing technology, such as ML, can take on the task of modeling these vast datasets, providing clinicians and scientists with another vital tool that can help them learn more about the incredibly complex cancer landscape.

ML methods can organize and filter multiomic data from a patient that can allow the quick identification of the gene sets or pathways most relevant to a particular type of cancer.⁵  It can also validate the multiomic biomarker panels needed to ensure patients receive the best treatment options for their particular cancer.³  More specifically, applying ML algorithms to large-scale datasets can assist in the analysis of cancer multiomic data for the prognosis, diagnosis, classification, and identification of biomarkers that can enhance early disease detection and treatment optimization. ^3-6

The generation of one-time digital multiomic data of healthy individuals will help facilitate the comparison of omics data with cancer patients. This will enable the identification of distinct biomic signatures that are associated with complex phenotypes such as cancer hallmarks, inter-individual genomic diversity, and the cell-type composition of the tissue. This would pave the way for conducting genomics studies on liquid biopsies to identify the dynamic molecular alterations associated with the evolution of tumors through the course of cancer progression and would further help to discover the biomarkers and therapeutic strategies that are essential for precision medicine.

The goal should be to create a multiomic driven digital hub for cancer combined with digital biobanking and a digital twin of the cancer patient and personalized cancer database (from genomic and/or transcriptomic knowledge specific to the pathology). The hope is that this will result in more durable responses as well as next-generation biotherapeutics that could lead to improved quality of life and care.Various cutting-edge ‘omics techniques are available commercially. From deciphering genetic information to exploring epigenetic modifications, these techniques play pivotal roles in advancing our understanding of genomic diversity, gene expression dynamics, and disease mechanisms.⁷ Advancements in the field of digital pathology and image analysis for cancer care have been achieved by large companies such as IBM, Google, and others.^4,5,8 Successful integration of omics data with other data types such as EHR’s and imaging data, is expected to increase the understanding of human health, allowing precise and individualized preventive, diagnostic, and therapeutic strategies.^9,10

In healthcare, databases hinge on interdisciplinary collaboration for efficient patient information management. We must build teams comprising clinicians, bioinformaticians, data scientists, and IT experts so that we can take a holistic approach to delivering care and ensuring that key challenges including integration, privacy, security, and compliance are addressed.

The intricate interplay of medicine and IT is evident in the crucial roles of computer/ IT experts in study protocol preparation, AI application, and data analysis, while molecular biologists and bioinformaticians contribute to gene profiling, screening of inborn errors, cancer studies, and sensor development.

A multi-disciplinary approach will result in innovative, user-friendly databases that enhance clinical decision-making and patient outcomes.

The landscape of healthcare is undergoing a transformative shift with the integration of digital health and data science methods.^11-13 This includes the Brain Somatic Mosaicism Network, IoT in Healthcare, Augmented Reality (AR) and Virtual Reality (VR), Natural Language Processing (NLP), and Data Analytics for Population Health. These areas are all contributing to improved patient care, personalized treatment plans, and enhanced medical education.

Global benefits of integration:

The global impact of integrating digital health, multiomics in precision medicine, and data science is evident in several areas:^14-16

1. Personalized management: AI-driven personalized healthcare optimizes treatment strategies, tailoring interventions for better therapeutic outcomes.
2. Clinical and epidemiological data: Data science and AI transform the handling of clinical and epidemiological data, providing insights for disease diagnosis, prognosis, and treatment, especially for cancers.
3. Precision medicine: Advancements in precision medicine through the integration of data science, ‘omics technologies, and AI enable a nuanced understanding of diseases, especially in cancer biology, and personalized ‘omics’ for precision health.¹¹
4. Hypothesis generation using ML: ML accelerates scientific discovery by uncovering hidden patterns within genomic, proteomic, and clinical data, guiding researchers in formulating targeted research questions and generating electronic phenotypes.
5. Cancer data conundrum: Addressing the challenge of managing vast datasets in multiomics research requires advanced bioinformatics tools, collaborative efforts, and interoperable platforms for precision oncology.
6. Virtual ideas lab: For example: Toward Building a Cancer Patient “Digital Twin”.^13,16 A cancer patient’s digital medical twin could be used as a holistic computer-based model to enable personalized medicine, support cancer research, pre-clinical development, clinical trials, aid diagnosis, and support running treatment simulations.

Digital clinical trials: to investigate causation and provide evidence to support the use of novel diagnostic, prognostic, and therapeutic interventions in clinical medicine and produce molecular tumor boards to review and interpret molecular-profiling results for individual patients with cancer and match each patient to available therapies.

Digital biomics datasets would provide a unique resource for future biological investigations and would support a wide range of applications, including individualized medicine, integrated, real-time pandemic surveillance, digital clinical trials, and virtual health coaches.

A multiscale and multimodal dataset from individual-level patient data can be created via clinical trials and population studies. Such datasets can be used to train mechanistic and AI models, forming the basis for predictive modeling that will provide key insights into disease progression and the optimal treatment options available.

The integration of digital biomics datasets into healthcare systems requires collaborative efforts from executives to overcome technical, regulatory, and organizational challenges.^12,17 To achieve this, executives must prioritize investments in IT infrastructure and foster partnerships with academic and research organizations as well as technology vendors to accelerate innovation in digital biomics. They should also prioritize recruitment and talent acquisition, ensure compliance with regulations, prioritize engagement and education of patients, and support research initiatives to develop biomics-based tools and technologies into routine healthcare.

By implementing these actions, executives can drive interdisciplinary and multiomics research and capitalize on multiomic and biomics data to improve patient outcomes, advance precision medicine, and transform healthcare delivery globally.