Precision Oncology and Individualized Treatment: A Comprehensive Look at the Medicine of the Future

Marking the beginning of a new era in medicine, Precision Medicine is an excellent example of how genetic knowledge is transforming our approaches to treatment. The completion of the Human Genome Project in 2003 launched this era, laying the foundations for precision medicine, which personalizes treatment and allows scientists to view diseases from a different perspective. Understanding how medicine has evolved, and what precision medicine means—its principles, tools, and applications—is essential.

Precision Medicine: A Perspective on the Medicine of the Future

Precision medicine offers tailored treatment by considering individual differences in genetic makeup and environmental factors. Unlike evidence-based medicine and traditional medical practice, it aims to develop individual treatments based on genetic, environmental, and lifestyle factors. In particular, susceptibility to certain diseases or response to particular treatments can vary because of genetic differences, which have become a focus of scientific research in this field.

Launched in the United States in 2015, the Precision Medicine Initiative increased awareness and popularity in this field, and the term "precision medicine" attracted growing global interest. Even in search engines, it surpassed "personalized medicine" and became a trend in medicine and healthcare.

To understand precision medicine, however, we need to examine the evolution of medical concepts: the journey from traditional medicine through evidence-based medicine to precision medicine. By examining each concept's effects on medical science and practice, we can better understand what precision medicine offers and its future potential.

Understanding this discipline's goals, achievements, and potential challenges is critical to fully appreciating its effects on health and shaping our future in the field. Built around two main goals, precision medicine's approach to classifying different disease subtypes and offering targeted treatments for each subtype is among the main topics covered in this review.

The Emergence of Precision Medicine

Although the term precision medicine is new, the concept dates back to Hippocrates. In 1979, Canadian researcher Dr. L.Y. Wei proposed "3P": preventive medicine, precision medicine, and folk medicine.

Genome-based precision medicine emerged after completion of the Human Genome Project, as knowledge of the genetic basis of disease began to guide tailored treatments.

• Stratified Medicine: It aims to group patients according to risk or treatment response to maximize treatment benefits. Using our knowledge of disease and diagnosis can make clinical decision-making more precise.
• Personalized Medicine: First used in 1971, this term describes using genetic profile information to guide decisions on disease prevention, diagnosis, and treatment . The term "personalized medicine" caused public confusion: a 2013 survey found that only 4% understood it.
• Individualized Medicine: Topol proposed replacing "personalized medicine" with "individualized medicine" . This term had previously meant matching an individual's disease to a specially designed therapy. Patient-specific vaccines such as Onkofaj  and stem cell–based therapies are examples.
• P4 Medicine: Introduced by Hood in 2004, P4 medicine stands for predictive, preventive, personalized, and participatory medicine. It aims to enable comprehensive approaches to public health and monitor population health using a broad information network.

Precision medicine generally aims to approach disease treatment and prevention in a more personalized, effective way. These different terms and concepts seek to help us understand and treat diseases more effectively and individually using genetic and biological data. They advocate effectively classifying patients into subgroups based on a shared biological basis of disease.

Implementing precision medicine has two main goals: 

1. Accurately classifying diseases into different subtypes 
2. Finding targeted treatments for these specific subtypes

Advances in omics sciences, electronic health records and big data analysis have made these two goals increasingly attainable.

"Omics" refers to large-scale, comprehensive analyses of biological systems. In biological and biomedical sciences, it commonly denotes specific fields such as genetics, transcriptomics, proteomics, and metabolomics. These terms refer, respectively, to comprehensive, systematic analyses of genes, RNA molecules, proteins, and metabolites. Omics analyses generally use high-throughput technologies and big data analytics to better understand biological systems and diseases.

Accuracy and Precision in Precision Medicine

Precision medicine includes the concepts of "accuracy" and "precision" : 

• Accuracy describes how closely a measurement agrees with a standard or true value, while  
• precision describes how closely repeated measurements agree with one another. 

Accurately representing genomes (accuracy) and ensuring the reproducibility of genetic tests (precision) are critical in precision medicine, as incomplete or incorrect genetic tests can have serious consequences for individuals and families.

Dividing Diseases Into Subgroups

Precision medicine aims to classify a particular disease into distinct subgroups based on a patient's specific characteristics, guiding treatment decisions for each subgroup. This concept has prompted extensive research into subtyping conditions such as cancer, autism, asthma, autoimmune diseases, and cardiovascular diseases. Scientifically and medically, disease subtyping can help manage treatment decisions and anticipated costs more intelligently. It can also guide genetic test design and research into the causes of diseases. When linked directly to a disease mechanism, these subtypes are called "endotypes"; when they represent similar patients for treatment purposes, they are called “verotypes”.

Historically, doctors subtyped diseases by observing different patients' symptoms and treatment responses, then conducting research to validate those observations. Over the past 20 years, modern high-throughput biotechnologies and declining costs of "omics" data (genomics, proteomics, and others) have led scientists toward computational subtyping approaches. These include molecular subtyping using various biomarkers and omics data, as well as clinical subtyping based on electronic health records and deep phenotyping, while also considering environmental, social, and behavioral factors. This integrative approach allows more comprehensive patient assessment and more personalized treatment strategies. 

Molecular Subtyping: Omics

Multifactorial, life-threatening diseases, particularly cancer, cardiovascular disease, and diabetes, are complex and heterogeneous targets for precision medicine. Traditional biomarker identification methods are insufficient for their molecular subtyping, and omics technologies fill this gap. Originating with the Human Genome Project, these technologies provide detailed, high-throughput biological analyses and encompass genomics, epigenomics, transcriptomics, proteomics, metabolomics, microbiomics, and metagenomics. Next-generation sequencing (NGS) technology stands out for its ability to generate extensive, detailed molecular data across omics disciplines. Comprehensive molecular profiling of individuals enables a more detailed understanding of disease subtypes and the development of more tailored treatment strategies. 

Genomics

Genomics, an omics discipline, focuses on studying whole genomes, unlike genetics, which examines individual genes. Genomic approaches used to investigate variants in Mendelian (single-gene) and complex diseases include genome-wide association studies (GWASs), whole-genome sequencing (WGS), and whole-exome sequencing (WES) . 

• GWASs help identify relationships between genetic variants (changes or mutations) and complex diseases.
• WGS and WES are used to sequence different parts of a gene. 

These technologies, particularly through next-generation sequencing (NGS), offer extensive data-generation capacity. WGS and WES each have different advantages and limitations: WES is faster and provides deeper coverage, whereas WGS provides broader information, including regulatory regions. Single-cell genomic sequencing (SGS) also analyzes individual cell genomes, allowing detailed investigation of genomic variation between tumor and nontumor cells.

Epigenomics

Epigenomics focuses on changes in gene expression that occur without changes in genetic structure. Research in this field fundamentally examines how and why epigenetic modifications—such as DNA methylation, histone acetylation, and microRNAs (miRNAs)—occur, and their effects on the organism. Chemical modifications of DNA and histones regulate gene transcription, while miRNAs control and regulate gene expression. 

Epigenetic modifications are driven by genetic and environmental factors; these modifications are sometimes inherited and play important roles in disease, particularly cancer, cardiovascular disease, and metabolic syndrome. 

Epigenomic studies focus on techniques for understanding these changes, identifying epigenetic biomarkers, and developing epigenetically targeted therapeutic strategies.

Treating DNA with bisulfate is the first step in assessing DNA methylation, while chromatin immunoprecipitation (ChIP) followed by sequencing (ChIP-seq) is used to examine histone modifications. Techniques used to assess miRNA expression include microarrays, qRT-PCR, and small RNA-seq. 

Epigenomics not only helps us understand disease but may also enable strategies for diagnosis, prognosis, and treatment.

Transcriptomics

Transcriptomics studies all RNA transcripts in a cell or a particular condition. Developed in the early 1990s, the field initially relied heavily on microarrays for gene expression analysis. Today, however, advances in NGS (next-generation sequencing) and falling costs have made RNA-seq the preferred method for transcriptome analysis.

Transcriptomics helps us understand an organism's biology, differences in gene expression, and uncharacterized gene functions, playing an important role in understanding human disease. It provides a "snapshot" of the transcriptome at a single time point, so measurements vary across times and conditions. Spatial transcriptomics can localize gene expression spatially, helping reveal expression differences between cells and disease causation.

Proteomics

Proteomics studies the composition, functions, interactions, and structures of proteins. Proteomes, reflecting gene expression and post-translational modifications, are the main molecules carrying out cellular functions. Proteomics generally uses high-throughput methods based on MS (mass spectrometry). 

There are three main types of proteomics: 

• Expression proteomics: Identifies differences in protein expression.
• Structural proteomics: Reveals proteins' three-dimensional structures.
• Functional proteomics: Reveals protein functions and interactions.

In proteomics, gene expression levels reflect protein levels only partly, and post-translational modifications, such as phosphorylation and ubiquitination, can substantially change protein function. This is critical to understanding genes and, particularly, discovering disease-associated proteins and signaling pathways.

Metabolomics

Metabolomics studies metabolites—the small molecules within cells, tissues, and organisms—on a large scale. It encompasses the complete collection of metabolites, known as the metabolome, and their interactions within a biological system. 

Metabolomic studies use analytical platforms such as ultra-performance liquid chromatography (UPLC), nuclear magnetic resonance (NMR) and mass spectrometry (MS) to quantify various metabolites in biological systems, including amino acids, lipids, and carbohydrates. 

Metabolomics can investigate metabolic abnormalities associated with many human diseases, particularly cardiovascular disease, diabetes, and cancer. With advances in analytical technologies, it has also become a powerful tool for elucidating pathological mechanisms, finding new drug targets, interpreting drug interactions, predicting drug responses, identifying diagnostic biomarkers for early detection, and optimizing personalized treatments.

Metabolite levels and ratios are generally reliable indicators of metabolic function, and abnormalities often indicate disease. Through quantitative metabolite measurements, metabolomics can identify genetic regions regulating small-molecule metabolism in different tissues and body fluids.

Microbiomics and Metagenomics

The microbiome encompasses all microorganisms colonizing the human body, including bacteria, viruses, and fungi. Microbiomics studies the structure, function, and dynamics of these microorganisms and their associated molecules. Various body sites, including the gut, skin, and mucosal surfaces, are colonized by microorganisms; this community is called the microbiota . Metagenomics involves extensive genetic analysis of microbial genes, enabling us to understand these organisms' vast genetic potential. 

Analysis of the human microbiome encompasses metagenomics and other omics analyses. The microbiome substantially affects many components of the human body, disease development, and overall health. In particular, it influences health through interactions with the gut–brain axis and immune system, and may also play an important role in drug metabolism. Understanding how it functions may improve our understanding of disease mechanisms and treatment options.

Clinically Enriched Subtypes and Deep Phenotyping

Phenotype refers to an individual's observable biological characteristics, while phenotyping involves analyzing and describing them. Deep phenotyping provides a detailed, comprehensive analysis of these features. 

Precision medicine aims to divide patients into subgroups based on characteristics such as phenotype and genotype. Integrating these data is critical to identifying subgroups and developing treatment strategies. 

Data sources such as electronic health records, along with algorithms, are used to subtype people according to phenotypic features. Different subtypes may differ in disease course, treatment response, and complications. 

Inadequate and fragmented phenotype descriptions can complicate analyses, especially in rare diseases and incomplete datasets. Precision medicine enables the development of subtype-specific treatments, pharmaco-omics approaches, and functional precision medicine approaches.

Developing treatments for identified molecular subtypes, along with pharmaco-omics and functional precision medicine, plays an important role in precision medicine practice.

Development and Application of Targeted Therapies

Targeted therapies involve therapeutic drugs focused on specific pathogenic molecules or cells, targeting only disease-causing cellular processes and reducing the risk of damage to normal cells. Paul Ehrlich introduced this concept through the idea of "magic bullets" (magic bullets), aiming for drugs to target disease specifically and thus provide more precise, personalized treatment. Advances in the Human Genome Project and omics technologies have improved understanding of disease progression mechanisms, enabling the design of new targeted drugs. Targeted therapy is particularly strong in oncology, where drugs are developed for specific cancers. It has also been applied to cardiovascular diseases, autoimmune diseases, cystic fibrosis, and other conditions.

Molecularly Targeted Treatment Strategies and Advances in Cancer

Targeted approaches in cancer treatment aim to act specifically on particular molecular and biological mechanisms in cancer cells and tumors. Until the late 1990s, cancer drugs generally targeted cell division broadly, also damaging normal cells. In the 1980s, scientists focused on specific cancer-cell growth factors and oncogene products and used this knowledge to develop drugs blocking cancer-specific signals, such as trastuzumab (Herceptin), gefitinib (Iressa), imatinib (Gleevec), and cetuximab (Erbitux). 

Angiogenesis inhibitors also prevent tumors from forming new blood vessels and growing. The first such drug, bevacizumab (Avastin, Altuzan) , was approved in 2004, and new drugs continue to be developed in this area. 

More recently, the molecular mechanisms and triggers driving cancer have become central to drug development, which involves two main strategies: antibodies and small molecules .

Antibodies

Antibody-based therapeutics play an important role in cancer treatment, and monoclonal antibodies (mAbs) were among the earliest developments. They generally have high specificity, but administration is usually limited to intravenous or subcutaneous injection because their targets are mostly on the cell surface and they have large molecular structures. The first generation of mAbs was mouse-derived, creating limitations and problems in humans, but later developments, such as chimeric and humanized mAbs, overcame these difficulties. 

Humanized mAbs retain all or part of the mouse variable regions while replacing the mouse Fc domain with a human Fc domain, reducing immune responses in humans. The human IgG1 isotype is important and widely used for mediating Fc-domain functions, particularly antibody-dependent cellular cytotoxicity (ADCC). 

The first two FDA-approved mAbs were rituximab and trastuzumab, launched in 1997 and 1998, respectively. Within 25 years, more than 100 mAbs received approval. 

Antibody therapies fall into three categories:

1. Naked Antibodies: These largely retain natural IgG (immunoglobulin G) properties. Trastuzumab is an example.
2. Genetically Engineered Antibodies: These target cytotoxic (cell-killing) T cells and enhance their ability to fight disease. Examples include immune checkpoint inhibitors and CAR T-cell therapy applications in cellular treatment. 
3. Antibody–Drug Conjugates: These carry cytotoxic payloads—chemotherapy molecules—to target cells, destroying diseased cells. An example is trastuzumab deruxtecan.

Figure Description: Antibody-based cancer treatments can be classified into three categories by their mechanisms of action: 

1. Naked antibodies based on natural IgG properties involve ADCC, ADCP, CDC, and inhibition of cellular signaling.
2. Engineered antibodies engaging cytotoxic T cells include immune checkpoint inhibitors (ICIs), T-cell-engaging bispecific antibodies (T-biAb), and chimeric antigen receptor T cells (CAR-Ts) using single-chain variable fragments (scFv).
3. Antibody conjugates delivering cytotoxic payloads include antibody–drug conjugates (ADCs), antibody–radionuclide conjugates (ARCs), and immunocytokines.

Small-Molecule Inhibitors

Small-molecule inhibitors are important in cancer treatment, particularly advanced cancers resistant to conventional chemotherapy. 

In this context, the FDA has approved 43 different small-molecule inhibitors for use in oncology. 

These inhibitors broadly fall into two categories: 

• Selective small-molecule inhibitors 
• Multikinase inhibitors

Selective inhibitors interact with fewer targets and generally inhibit a specific cellular signaling component. Multikinase inhibitors target a broader range of kinases and have lower specificity. Patients are selected for selective inhibitors based on particular biomarkers, whereas multikinase inhibitors are generally used based on histological diagnosis without additional individual patient selection. 

Small-molecule inhibitors offer effective strategies to fight cancer and improve long-term survival, may reduce adverse effects, and can replace cytotoxic chemotherapy as first-line treatment. This shows the potential of targeted strategies to improve outcomes with minimal adverse effects by supporting personalized, precision treatment approaches.

Pharmaco-Omics Approaches and Understanding Individual Variation in Drug Response

Pharmaco-omics uses omics disciplines to investigate individual differences in drug responses and their underlying molecular mechanisms. It provides an overarching framework for understanding and guiding drug responses, with its various branches investigating responses and mechanisms at different molecular levels. 

Pharmacogenomics is the earliest and most developed branch, allowing us to understand drug responses genetically. Other branches—including pharmacotranscriptomics, pharmacoepigenetics, pharmacoproteomics, pharmacometabolomics, and pharmacomicrobiomics—expand its scope by examining gene expression, epigenetic modifications, protein levels, metabolite profiles, and microbiome effects on drug response. This broad approach deepens our understanding of individual differences and supports personalized treatment strategies.

Pharmacogenomics

Pharmacogenomics examines relationships between genetic variation and drug response within a broad genomic context, while pharmacogenetics takes a narrower view. Both aim to develop personalized drug treatment strategies based on individual genetic makeup. 

Initially focused on single-gene variation, pharmacogenetics evolved through scientific and technological advances into pharmacogenomics, which encompasses the entire genome. This broader perspective enables investigation of genetic effects on pharmacokinetic and pharmacodynamic mechanisms, differences across populations, and integration of this knowledge into clinical practice and drug development. 

Two important examples—genetically influenced responses to isoniazid and succinylcholine, and genetic approaches to warfarin treatment—highlight the importance of pharmacogenomic applications and the polygenic model. 

Pharmacogenomics paves the way for personalized medicine by enabling future drug treatments to be more individualized and effective.

Pharmacotranscriptomics

Pharmacotranscriptomics studies transcriptome variation to personalize drug treatment and dosing. Still an emerging field, it is useful for evaluating drug efficacy and discovering targets. 

One study profiled the pharmacotranscriptomics of treatment-resistant triple-negative breast cancer cells treated with lapatinib, an approved anticancer drug, and berberine, a traditional medicine product, as well as gene networks regulating ferroptosis. By examining gene activity during drug treatment in detail, this profiling aims to clarify the effects of these substances on cells and the ferroptosis process.

Pharmacoepigenetics

Pharmacoepigenetics investigates individual differences in drug responses, focusing particularly on epigenetic modifications and how they affect drug response. 

Research shows that epigenetic changes are associated with drug treatment and may modulate drug effects. Some epigenetic treatments involve gene modulation, and specific gene variations may influence responses to particular drugs.

Pharmacoproteomics

As a branch of proteomics, pharmacoproteomics examines variation at the protein level and its relationship with drug responses. Complementing genetic and transcriptomic data, it explores individual differences and their interactions with drugs in greater detail. 

Recent research seeks to identify potential molecular targets in this area and determine how drugs may affect organs such as the kidneys.

Pharmacometabolomics

Pharmacometabolomics studies relationships between pharmacology and metabolic phenotypes. Using metabolomic approaches, it aims to understand drug movement in the body (pharmacokinetics) and drug effects (pharmacodynamics), find biomarkers of drug responses, and identify new research targets. 

By focusing on particular drug interactions and metabolism, pharmacometabolomics helps develop new strategies and targets for specific diseases. Examples include research identifying new molecular targets for prostate cancer and acute myeloid leukemia treatment, and studies of inhaled corticosteroid response in people with asthma. 

Raman spectroscopy-guided cellular pharmacometabolomics is also an emerging technique enabling metabolite analysis at the single-cell level.

Functional Precision Medicine

Functional precision medicine (FPM) is a precise, personalized medical approach that directly examines drug responses in tissues obtained from affected individuals. It aims to address some challenges and shortcomings of omics-based precision medicine.

Because genomic information alone cannot fully predict how patients will respond to treatment, FPM aims to fill this gap.

Generating dynamic, functional data reveals various factors that may influence treatment response in an individual, including the tumor microenvironment, gene expression, and protein modifications. These data allow us to examine and understand such factors within a broader framework.

With rapidly advancing technologies and a growing number of cancer drugs, FPM also uses patient-derived models to investigate cancer heterogeneity and treatment response more comprehensively. Model development and validation focus on short- and long-term applications and include preclinical models such as patient-derived xenografts, organoids, and microfluidic chips.

By making medical approaches more functional and effective, FPM may play an important role in developing personalized treatment strategies.

Patient-Derived Xenograft (PDX) Models

PDX models play a critical role in cancer research by using human tumors directly in mice, more accurately mimicking the natural environment of tumor cells and bridging clinical and laboratory research. They also show a high correlation between clinical and drug responses, making them valuable for predicting drug responses and providing patients with more effective treatments.

Patient-Derived Organoid (PDO) Models

PDO (patient-derived organoid) models grow patients' tumor cells in laboratory 3D cultures to evaluate drug responses and new treatments. Although first used in pancreatic cancer, PDOs now support research and treatment testing across many cancers. Preserving phenotype and genotype makes them particularly useful for drug discovery and treatment strategies.

Figure Description: Individualized tumor response testing using patient-derived organoids (PDOs). 

Tissue is obtained from the patient's tumor through diagnostic biopsy and enzymatically and mechanically dissociated into a single-cell suspension. It is embedded in a droplet of basement membrane extract and grown in a specialized culture medium to form organoids. Once tumor histology is confirmed, the organoids are placed in living biobanks and used for drug screening. Various outcomes can characterize PDO drug-screening responses, including organoid size, viability, and coculture cytokine measurements. Drugs identified as effective through screening are then used to treat the patient.

Microfluidic Chips

Microfluidic chip technology combines microfluidics and tissue engineering to create miniature models of human organs and tissues, providing critical data on drug interactions and toxicity. These biochips can model the tumor microenvironment and its interactions with immune cells, enabling detailed study of drug responses, toxicity, and cell behavior. Offering advantages of both in vitro and in vivo research, these models provide comprehensive analysis.

Other Aspects of Precision Medicine

Environmental, Social, and Behavioral Factors

Environmental, social, and behavioral factors substantially influence health, and precision medicine must consider them alongside genetics. It is known that genetic factors account for only 30% of influences on individual health, with the remainder attributable to behavioral, social, and environmental factors and healthcare. Precision medicine should integrate these factors with genetic information to develop individualized health management strategies.

Some critics suggest that insufficient attention to environmental and social factors helps explain why precision medicine has not yet clearly affected morbidity and mortality at the population level. Effective, holistic practice requires considering genetic predispositions alongside environmental and social factors and understanding their interactions. 

This may be more challenging for complex, multifactorial diseases than for single-gene conditions such as cystic fibrosis. Advances in omics disciplines, digital health technologies, and big data analytics may help overcome these challenges and enable personalized risk assessments. This approach may play an important role in developing individualized prevention and treatment strategies, supporting effective applications across medicine.

Electronic Health Records

Electronic health records (EHRs) are digital information systems containing patients' medical histories, treatment plans, and medicines. They have evolved with advances in computing since the 1970s (e-nabız being the best-known example in Turkey). Early EHR applications focused on billing and scheduling; over time, they developed to support medical care and research. EHR systems are now widely used among healthcare professionals, hospitals, insurers, and patients, digitally transforming patient–doctor relationships and communication.

In precision medicine, EHRs are increasingly important, particularly for integrating genomic data. Personalized medicine depends substantially on EHR systems to use genomic information effectively. This enables more specific, tailored care and creates new possibilities for biomedical research.

However, data accuracy, missing data, and bias pose major research challenges because these systems were not originally designed for research. Ethical and scientific issues also require careful attention when genomic data are integrated with EHRs. Widespread implementation poses another challenge, especially in developing countries without robust healthcare and information technology infrastructure.

Digital Health

Digital health improves healthcare efficiency and makes medicine more personalized. It encompasses a wide range of information and communication technologies, with hardware and software solutions including EHRs, telemedicine, mobile health applications, and wearable devices . These technologies may improve healthcare delivery and increase individuals' awareness of their health. Digital health also enables patients to collect their own health data, for example through FDA-approved mobile devices and applications, and share them with doctors. This may create valuable data sources for clinical decisions and potentially large-scale health research.

Active patient participation increases control over and understanding of health, potentially encouraging healthy behaviors and helping patients follow care plans more effectively. Digital health also supports precision medicine by integrating environmental and omics data, enabling holistic, personalized care. It thus forms an important dimension of tailored medicine by creating an effective partnership among patients, doctors, and researchers.

Related topic: Why Has DIGITAL HEALTH Been a DISAPPOINTMENT, and How Can It Be Fixed?

Big Data Analytics and Artificial Intelligence

Big data analytics and artificial intelligence (AI) are critical technologies supporting precision medicine. "Big data" encompasses large, diverse datasets from biomolecular tests, clinical assessments, and social and environmental factors. Analyzing these data is central to precision medicine's progress. However, their volume and diversity challenge traditional software and hardware approaches to analysis and management.

Big data analytics involves combining heterogeneous data, quality control, analysis, modeling, and interpretation. Major biotechnological advances have generated large, complex biomedical datasets, and detailed analytical processes are needed to transform them into meaningful information. In medicine and healthcare, big data analytics enables analysis of large disease and patient datasets, identification of relationships and correlations between datasets, and development of predictive models. Artificial intelligence and its subfields, deep learning and machine learning, meanwhile enable machines to imitate human-like thinking processes. 

In healthcare, AI can analyze and process large, heterogeneous health datasets promptly, from multiomics to environmental and biomedical literature data. This gives it the potential to make sense of large datasets and translate them into useful diagnostic and treatment strategies. Big data and AI are therefore important tools for advancing precision medicine and other healthcare innovations.

In Conclusion: The Role and Importance of Precision Medicine

Over the past decade, major advances in our understanding of the genetic basis of disease have accelerated precision medicine's development and application. This has enabled more detailed disease characterization and more specific treatments.

The table below shows important shifts in understanding over the past 10 years in oncology that have also affected clinical practice.

What Has Changed in Oncology in 10 Years?

Effective precision medicine requires classifying diseases into different subtypes and finding specific treatments for each. Subtyping and tailored treatment strategies are evolving from clinical phenotyping through molecular subtyping toward a comprehensive approach integrating omics and clinical data. 

For precision medicine to fulfill its promise, different levels of knowledge—molecular, clinical, laboratory, and environmental data—must be integrated. Big data analytics and artificial intelligence will play key roles in achieving this integration and shaping precision medicine's future.