From patterns to patients: Advances in clinical machine learning for cancer diagnosis, prognosis, and treatment.

Machine learning (ML) is increasingly used in clinical oncology to diagnose cancers, predict patient outcomes, and inform treatment planning. Here, we review recent applications of ML across the clinical oncology workflow. We review how these techniques are applied to medical imaging and to molecular data obtained from liquid and solid tumor biopsies for cancer diagnosis, prognosis, and treatment design. We discuss key considerations in developing ML for the distinct challenges posed by imaging and molecular data. Finally, we examine ML models approved for cancer-related patient usage by regulatory agencies and discuss approaches to improve the clinical usefulness of ML.

The next horizon in precision oncology: Proteogenomics to inform cancer diagnosis and treatment.

When it comes to precision oncology, proteogenomics may provide better prospects to the clinical characterization of tumors, help make a more accurate diagnosis of cancer, and improve treatment for patients with cancer. This perspective describes the significant contributions of The Cancer Genome Atlas and the Clinical Proteomic Tumor Analysis Consortium to precision oncology and makes the case that proteogenomics needs to be fully integrated into clinical trials and patient care in order for precision oncology to deliver the right cancer treatment to the right patient at the right dose and at the right time.

Extracellular Vesicle and Particle Biomarkers Define Multiple Human Cancers.

There is an unmet clinical need for improved tissue and liquid biopsy tools for cancer detection. We investigated the proteomic profile of extracellular vesicles and particles (EVPs) in 426 human samples from tissue explants (TEs), plasma, and other bodily fluids. Among traditional exosome markers, CD9, HSPA8, ALIX, and HSP90AB1 represent pan-EVP markers, while ACTB, MSN, and RAP1B are novel pan-EVP markers. To confirm that EVPs are ideal diagnostic tools, we analyzed proteomes of TE- (n = 151) and plasma-derived (n = 120) EVPs. Comparison of TE EVPs identified proteins (e.g., VCAN, TNC, and THBS2) that distinguish tumors from normal tissues with 90% sensitivity/94% specificity. Machine-learning classification of plasma-derived EVP cargo, including immunoglobulins, revealed 95% sensitivity/90% specificity in detecting cancer. Finally, we defined a panel of tumor-type-specific EVP proteins in TEs and plasma, which can classify tumors of unknown primary origin. Thus, EVP proteins can serve as reliable biomarkers for cancer detection and determining cancer type.

Biomedical Research Goes Viral: Dangers and Opportunities.

Researchers around the globe have been mounting, accelerating, and redeploying efforts across disciplines and organizations to tackle the SARS-CoV-2 outbreak. However, humankind continues to be afflicted by numerous other devastating diseases in increasing numbers. Here, we outline considerations and opportunities toward striking a good balance between maintaining and redefining research priorities.

Next-Generation Sequencing of Circulating Tumor DNA for Early Cancer Detection.

Curative therapies are most successful when cancer is diagnosed and treated at an early stage. We advocate that technological advances in next-generation sequencing of circulating, tumor-derived nucleic acids hold promise for addressing the challenge of developing safe and effective cancer screening tests.

Germline HLA landscape does not predict efficacy of pembrolizumab monotherapy across solid tumor types.

We evaluated the impact of class I and class II human leukocyte antigen (HLA) genotypes, heterozygosity, and diversity on the efficacy of pembrolizumab. Seventeen pembrolizumab clinical trials across eight tumor types and one basket trial in patients with advanced solid tumors were included (n > 3,500 analyzed). Germline DNA was genotyped using a custom genotyping array. HLA diversity (measured by heterozygosity and evolutionary divergence) across class I loci was not associated with improved response to pembrolizumab, either within each tumor type evaluated or across all patients. Similarly, HLA heterozygosity at each class I and class II gene was not associated with response to pembrolizumab after accounting for the number of tests conducted. No conclusive association between HLA genotype and response to pembrolizumab was identified in this dataset. Germline HLA genotype or diversity alone is not an important independent determinant of response to pembrolizumab and should not be used for clinical decision-making in patients treated with pembrolizumab.

Cancer screening with multicancer detection tests: A translational science review.

Multicancer detection (MCD) tests use a single, easily obtainable biospecimen, such as blood, to screen for more than one cancer concurrently. MCD tests can potentially be used to improve early cancer detection, including cancers that currently lack effective screening methods. However, these tests have unknown and unquantified benefits and harms. MCD tests differ from conventional cancer screening tests in that the organ responsible for a positive test is unknown, and a broad diagnostic workup may be necessary to confirm the location and type of underlying cancer. Among two prospective studies involving greater than 16,000 individuals, MCD tests identified those who had some cancers without currently recommended screening tests, including pancreas, ovary, liver, uterus, small intestine, oropharyngeal, bone, thyroid, and hematologic malignancies, at early stages. Reported MCD test sensitivities range from 27% to 95% but differ by organ and are lower for early stage cancers, for which treatment toxicity would be lowest and the potential for cure might be highest. False reassurance from a negative MCD result may reduce screening adherence, risking a loss in proven public health benefits from standard-of-care screening. Prospective clinical trials are needed to address uncertainties about MCD accuracy to detect different cancers in asymptomatic individuals, whether these tests can detect cancer sufficiently early for effective treatment and mortality reduction, the degree to which these tests may contribute to cancer overdiagnosis and overtreatment, whether MCD tests work equally well across all populations, and the appropriate diagnostic evaluation and follow-up for patients with a positive test.

Interpreting and integrating genomic tests results in clinical cancer care: Overview and practical guidance.

The last decade has seen rapid progress in the use of genomic tests, including gene panels, whole-exome sequencing, and whole-genome sequencing, in research and clinical cancer care. These advances have created expansive opportunities to characterize the molecular attributes of cancer, revealing a subset of cancer-associated aberrations called driver mutations. The identification of these driver mutations can unearth vulnerabilities of cancer cells to targeted therapeutics, which has led to the development and approval of novel diagnostics and personalized interventions in various malignancies. The applications of this modern approach, often referred to as precision oncology or precision cancer medicine, are already becoming a staple in cancer care and will expand exponentially over the coming years. Although genomic tests can lead to better outcomes by informing cancer risk, prognosis, and therapeutic selection, they remain underutilized in routine cancer care. A contributing factor is a lack of understanding of their clinical utility and the difficulty of results interpretation by the broad oncology community. Practical guidelines on how to interpret and integrate genomic information in the clinical setting, addressed to clinicians without expertise in cancer genomics, are currently limited. Building upon the genomic foundations of cancer and the concept of precision oncology, the authors have developed practical guidance to aid the interpretation of genomic test results that help inform clinical decision making for patients with cancer. They also discuss the challenges that prevent the wider implementation of precision oncology.

Cancer diagnosis and treatment in working-age adults: Implications for employment, health insurance coverage, and financial hardship in the United States.

The rising costs of cancer care and subsequent medical financial hardship for cancer survivors and families are well documented in the United States. Less attention has been paid to employment disruptions and loss of household income after a cancer diagnosis and during treatment, potentially resulting in lasting financial hardship, particularly for working-age adults not yet age-eligible for Medicare coverage and their families. In this article, the authors use a composite patient case to illustrate the adverse consequences of cancer diagnosis and treatment for employment, health insurance coverage, household income, and other aspects of financial hardship. They summarize existing research and provide nationally representative estimates of multiple aspects of financial hardship and health insurance coverage, benefit design, and employee benefits, such as paid sick leave, among working-age adults with a history of cancer and compare them with estimates among working-age adults without a history of cancer from the most recently available years of the National Health Interview Survey (2019-2021). Then, the authors identify opportunities for addressing employment and health insurance coverage challenges at multiple levels, including federal, state, and local policies; employers; cancer care delivery organizations; and nonprofit organizations. These efforts, when informed by research to identify best practices, can potentially help mitigate the financial hardship associated with cancer.

A Biomarker Harvest from One Thousand Cancer Cell Lines.

Identifying molecular biomarkers that predict cancer drug efficacy is crucial for the advancement of precision medicine. In this issue of Cell, Iorio et al. nominate hundreds of potential genetic and epigenetic biomarkers through high-throughput drug screening in ∼1,000 molecularly annotated cancer cell lines.

Patient navigation across the cancer care continuum: An overview of systematic reviews and emerging literature.

Patient navigation is a strategy for overcoming barriers to reduce disparities and to improve access and outcomes. The aim of this umbrella review was to identify, critically appraise, synthesize, and present the best available evidence to inform policy and planning regarding patient navigation across the cancer continuum. Systematic reviews examining navigation in cancer care were identified in the Cochrane Central Register of Controlled Trials (CENTRAL), PubMed, Embase, Cumulative Index of Nursing and Allied Health (CINAHL), Epistemonikos, and Prospective Register of Systematic Reviews (PROSPERO) databases and in the gray literature from January 1, 2012, to April 19, 2022. Data were screened, extracted, and appraised independently by two authors. The JBI Critical Appraisal Checklist for Systematic Review and Research Syntheses was used for quality appraisal. Emerging literature up to May 25, 2022, was also explored to capture primary research published beyond the coverage of included systematic reviews. Of the 2062 unique records identified, 61 systematic reviews were included. Fifty-four reviews were quantitative or mixed-methods reviews, reporting on the effectiveness of cancer patient navigation, including 12 reviews reporting costs or cost-effectiveness outcomes. Seven qualitative reviews explored navigation needs, barriers, and experiences. In addition, 53 primary studies published since 2021 were included. Patient navigation is effective in improving participation in cancer screening and reducing the time from screening to diagnosis and from diagnosis to treatment initiation. Emerging evidence suggests that patient navigation improves quality of life and patient satisfaction with care in the survivorship phase and reduces hospital readmission in the active treatment and survivorship care phases. Palliative care data were extremely limited. Economic evaluations from the United States suggest the potential cost-effectiveness of navigation in screening programs.

A pathology foundation model for cancer diagnosis and prognosis prediction.

Histopathology image evaluation is indispensable for cancer diagnoses and subtype classification. Standard artificial intelligence methods for histopathology image analyses have focused on optimizing specialized models for each diagnostic task1,2. Although such methods have achieved some success, they often have limited generalizability to images generated by different digitization protocols or samples collected from different populations3. Here, to address this challenge, we devised the Clinical Histopathology Imaging Evaluation Foundation (CHIEF) model, a general-purpose weakly supervised machine learning framework to extract pathology imaging features for systematic cancer evaluation. CHIEF leverages two complementary pretraining methods to extract diverse pathology representations: unsupervised pretraining for tile-level feature identification and weakly supervised pretraining for whole-slide pattern recognition. We developed CHIEF using 60,530 whole-slide images spanning 19 anatomical sites. Through pretraining on 44 terabytes of high-resolution pathology imaging datasets, CHIEF extracted microscopic representations useful for cancer cell detection, tumour origin identification, molecular profile characterization and prognostic prediction. We successfully validated CHIEF using 19,491 whole-slide images from 32 independent slide sets collected from 24 hospitals and cohorts internationally. Overall, CHIEF outperformed the state-of-the-art deep learning methods by up to 36.1%, showing its ability to address domain shifts observed in samples from diverse populations and processed by different slide preparation methods. CHIEF provides a generalizable foundation for efficient digital pathology evaluation for patients with cancer.

A whole-slide foundation model for digital pathology from real-world data.

Digital pathology poses unique computational challenges, as a standard gigapixel slide may comprise tens of thousands of image tiles1-3. Prior models have often resorted to subsampling a small portion of tiles for each slide, thus missing the important slide-level context4. Here we present Prov-GigaPath, a whole-slide pathology foundation model pretrained on 1.3 billion 256 × 256 pathology image tiles in 171,189 whole slides from Providence, a large US health network comprising 28 cancer centres. The slides originated from more than 30,000 patients covering 31 major tissue types. To pretrain Prov-GigaPath, we propose GigaPath, a novel vision transformer architecture for pretraining gigapixel pathology slides. To scale GigaPath for slide-level learning with tens of thousands of image tiles, GigaPath adapts the newly developed LongNet5 method to digital pathology. To evaluate Prov-GigaPath, we construct a digital pathology benchmark comprising 9 cancer subtyping tasks and 17 pathomics tasks, using both Providence and TCGA data6. With large-scale pretraining and ultra-large-context modelling, Prov-GigaPath attains state-of-the-art performance on 25 out of 26 tasks, with significant improvement over the second-best method on 18 tasks. We further demonstrate the potential of Prov-GigaPath on vision-language pretraining for pathology7,8 by incorporating the pathology reports. In sum, Prov-GigaPath is an open-weight foundation model that achieves state-of-the-art performance on various digital pathology tasks, demonstrating the importance of real-world data and whole-slide modelling.

Practical recommendations for using ctDNA in clinical decision making.

The continuous improvement in cancer care over the past decade has led to a gradual decrease in cancer-related deaths. This is largely attributed to improved treatment and disease management strategies. Early detection of recurrence using blood-based biomarkers such as circulating tumour DNA (ctDNA) is being increasingly used in clinical practice. Emerging real-world data shows the utility of ctDNA in detecting molecular residual disease and in treatment-response monitoring, helping clinicians to optimize treatment and surveillance strategies. Many studies have indicated ctDNA to be a sensitive and specific biomarker for recurrence. However, most of these studies are largely observational or anecdotal in nature, and peer-reviewed data regarding the use of ctDNA are mainly indication-specific. Here we provide general recommendations on the clinical utility of ctDNA and how to interpret ctDNA analysis in different treatment settings, especially in patients with solid tumours. Specifically, we provide an understanding around the implications, strengths and limitations of this novel biomarker and how to best apply the results in clinical practice.

Black in Cancer: An interview with founders Sigourney Bell and Henry J. Henderson.

We talk to Sigourney Bell and Henry J. Henderson about what motivated them to found Black in Cancer, the importance of community and representation, as well as the resources the organization provides, future directions, and how we and our readers can provide support.

Older adult participation in cancer clinical trials: A systematic review of barriers and interventions.

Cancer is a disease of aging and, as the world's population ages, the number of older persons with cancer is increasing and will make up a growing share of the oncology population in virtually every country. Despite this, older patients remain vastly underrepresented in research that sets the standards for cancer treatments. Consequently, most of what we know about cancer therapeutics is based on clinical trials conducted in younger, healthier patients, and effective strategies to improve clinical trial participation of older adults with cancer remain sparse. For this systematic review, the authors evaluated published studies regarding barriers to participation and interventions to improve participation of older adults in cancer trials. The quality of the available evidence was low and, despite a literature describing multifaceted barriers, only one intervention study aimed to increase enrollment of older adults in trials. The findings starkly amplify the paucity of evidence-based, effective strategies to improve participation of this underrepresented population in cancer trials. Within these limitations, the authors provide their opinion on how the current cancer research infrastructure must be modified to accommodate the needs of older patients. Several underused solutions are offered to expand clinical trials to include older adults with cancer. However, as currently constructed, these recommendations alone will not solve the evidence gap in geriatric oncology, and efforts are needed to meet older and frail adults where they are by expanding clinical trials designed specifically for this population and leveraging real-world data.

Onconephrology: The intersections between the kidney and cancer.

Onconephrology is a new subspecialty of nephrology that recognizes the important intersections of kidney disease with cancer. This intersection takes many forms and includes drug-induced nephrotoxicity, electrolyte disorders, paraneoplastic glomerulonephritis, and the interactions of chronic kidney disease with cancer. Data clearly demonstrate that, when patients with cancer develop acute or chronic kidney disease, outcomes are inferior, and the promise of curative therapeutic regimens is lessened. This highlights the imperative for collaborative care between oncologists and nephrologists in recognizing and treating kidney disease in patients with cancer. In response to this need, specific training programs in onconephrology as well as dedicated onconephrology clinics have appeared. This comprehensive review covers many of the critical topics in onconephrology, with a focus on acute kidney injury, chronic kidney disease, drug-induced nephrotoxicity, kidney disease in stem cell transplantation, and electrolyte disorders in patients with cancer.

Circulating tumor DNA in advanced solid tumors: Clinical relevance and future directions.

The application of genomic profiling assays using plasma circulating tumor DNA (ctDNA) is rapidly evolving in the management of patients with advanced solid tumors. Diverse plasma ctDNA technologies in both commercial and academic laboratories are in routine or emerging use. The increasing integration of such testing to inform treatment decision making by oncology clinicians has complexities and challenges but holds significant potential to substantially improve patient outcomes. In this review, the authors discuss the current role of plasma ctDNA assays in oncology care and provide an overview of ongoing research that may inform real-world clinical applications in the near future.

Blueprint for cancer research: Critical gaps and opportunities.

We are experiencing a revolution in cancer. Advances in screening, targeted and immune therapies, big data, computational methodologies, and significant new knowledge of cancer biology are transforming the ways in which we prevent, detect, diagnose, treat, and survive cancer. These advances are enabling durable progress in the goal to achieve personalized cancer care. Despite these gains, more work is needed to develop better tools and strategies to limit cancer as a major health concern. One persistent gap is the inconsistent coordination among researchers and caregivers to implement evidence-based programs that rely on a fuller understanding of the molecular, cellular, and systems biology mechanisms underpinning different types of cancer. Here, the authors integrate conversations with over 90 leading cancer experts to highlight current challenges, encourage a robust and diverse national research portfolio, and capture timely opportunities to advance evidence-based approaches for all patients with cancer and for all communities.

Planning for post-pandemic cancer care delivery: Recovery or opportunity for redesign?

The delivery of cancer care has never changed as rapidly and dramatically as we have seen with the coronavirus disease 2019 (COVID-19) pandemic. During the early phase of the pandemic, recommendations for the management of oncology patients issued by various professional societies and government agencies did not recognize the significant regional differences in the impact of the pandemic. California initially experienced lower than expected numbers of cases, and the health care system did not experience the same degree of the burden that had been the case in other parts of the country. In light of promising trends in COVID-19 infections and mortality in California, by late April 2020, discussions were initiated for a phased recovery of full-scale cancer services. However, by July 2020, a surge of cases was reported across the nation, including in California. In this review, the authors share the response and recovery planning experience of the University of California (UC) Cancer Consortium in an effort to provide guidance to oncology practices. The UC Cancer Consortium was established in 2017 to bring together 5 UC Comprehensive Cancer Centers: UC Davis Comprehensive Cancer Center, UC Los Angeles Jonsson Comprehensive Cancer Center, UC Irvine Chao Family Comprehensive Cancer Center, UC San Diego Moores Cancer Center, and the UC San Francisco Helen Diller Family Comprehensive Cancer Center. The interventions implemented in each of these cancer centers are highlighted, with a focus on opportunities for a redesign in care delivery models. The authors propose that their experiences gained during this pandemic will enhance pre-pandemic cancer care delivery.