Featured
-
-
News & Views |
The promise of AI in personalized breast cancer screening: are we there yet?
The benefits and potential harms of mammography-based screening for breast cancer are often a matter of debate. Here, I discuss the promises and limitations of a recent study that tested an artificial intelligence-based tool for the detection of breast cancer in digital mammograms in a large, prospective screening setting.
- Despina Kontos
-
Review Article |
Advancing CAR T cell therapy through the use of multidimensional omics data
Data obtained using omics technologies can offer important insights into various aspects of chimeric antigen receptor (CAR) T cell therapy. In this Review, the authors provide an overview of the multidimensional profiling technologies that have been applied in investigations of CAR T cell therapy. They then discuss the ways in which multi-omics data obtained through such analyses can be used to elucidate CAR targets, factors associated with response or resistance to therapy, and mechanisms underlying the associated toxicities, which could potentially be exploited to improve the efficacy and safety of CAR T cell therapies.
- Jingwen Yang
- , Yamei Chen
- & Leng Han
-
Review Article |
Criteria for the translation of radiomics into clinically useful tests
Despite a considerable increase in research output over the past decades, the translation of radiomic research into clinically useful tests has been limited. In this Review, the authors provide 16 key criteria to guide the clinical translation of radiomics with the hope of accelerating the use of this technology to improve patient outcomes.
- Erich P. Huang
- , James P. B. O’Connor
- & Lalitha K. Shankar
-
Perspective |
Harnessing big data to characterize immune-related adverse events
Immune-checkpoint inhibitors are associated with a unique spectrum of organ-specific inflammatory toxicities known as immune-related adverse events (irAEs). In the past few years, aggregate clinical data, real-world data and multi-omics data have been used to investigate the underlying mechanisms and clinical presentations of irAEs. The authors of this Perspective summarize the knowledge on irAEs that has been obtained from different sources of ‘big data’.
- Ying Jing
- , Jingwen Yang
- & Leng Han
-
Perspective |
Predicting cancer outcomes with radiomics and artificial intelligence in radiology
Prognostication of outcome across multiple cancers and prediction of response to various treatment modalities are among the next generation of challenges that artificial intelligence (AI) tools can solve using radiology images. The authors of this Perspective describe the evolution of AI-based approaches in oncology imaging and address the path to their adoption as decision-support tools in the clinic.
- Kaustav Bera
- , Nathaniel Braman
- & Anant Madabhushi
-
News & Views |
Prospective clinical deployment of machine learning in radiation oncology
Artificial intelligence and machine learning have the potential to make cancer care more accessible, efficient, cost-effective and personalized. However, meticulously planned prospective deployment strategies are required to validate the performance of these technologies in real-world clinical settings and overcome the human trust barrier.
- Issam El Naqa
-
-
Editorial |
What to expect from AI in oncology
An increasing number of studies suggest that artificial intelligence could revolutionize medicine. In oncology, we are only beginning to fully understand the practical implications.
-
Perspective |
Artificial intelligence in digital pathology — new tools for diagnosis and precision oncology
The authors of this Perspective critically evaluate various artificial intelligence (AI)-based computational approaches used for digital pathology and provide a broad framework to incorporate these tools into clinical oncology, discussing challenges such as the need for well-curated validation datasets, regulatory approval and fair reimbursement strategies.
- Kaustav Bera
- , Kurt A. Schalper
- & Anant Madabhushi
-
News & Views |
Google’s lung cancer AI: a promising tool that needs further validation
Researchers from Google AI have presented results obtained using a deep learning model for the detection of lung cancer in screening CT images. The authors report a level of performance similar to, or better than, that of radiologists. However, these claims are currently too strong. The model is promising but needs further validation and could only be implemented if screening guidelines were adjusted to accept recommendations from black-box proprietary AI systems.
- Colin Jacobs
- & Bram van Ginneken
-
-
News & Views |
Multi-omic profiling refines the molecular view
Muscle-invasive bladder cancer (MIBC) is a heterogeneous disease for which treatment has, historically, lagged behind that of other solid tumour types. A more detailed understanding of the biology of individual tumours, and the identification of molecular features providing prognostic and predictive information is key to the application of personalized care for patients with MIBC. The publication of a study of 412 samples now provides such data.
- Carolyn D. Hurst
- & Margaret A. Knowles
-
-
Review Article |
Patient-reported outcomes in cancer care — hearing the patient voice at greater volume
In the past decade, the importance of patient-reported outcomes (PROs) as a key measure of the quality of care delivered to patients with cancer has been acknowledged. PROs were used in the context of research studies, but growing evidence indicates that the incorporation of electronic PRO (ePRO) assessments into standard health-care settings can improve the quality of care delivered to patients with cancer. The authors of this Review discuss aspects related to PROs such as measurements, implementation challenges, and outcome improvements associated with their use.
- Thomas W. LeBlanc
- & Amy P. Abernethy
-
Editorial |
Context: the grey matter of cancer
-
News & Views |
Clinical hallmarks in whole cancer genomes
Fraser and colleagues describe the whole-genome sequencing (WGS) profiles of over 200 localized intermediate-risk prostate cancers. WGS has been widely used in research but not, thus far, in clinical settings. Herein, we consider the possible use of WGS in the field of precision oncology.
- Marcin Imielinski
- & Mark A. Rubin
-
Opinion |
Precision medicine needs randomized clinical trials
Clinical trial design has dramatically evolved with the advent of precision medicine. As a result, expedited drug-approval decisions have been made on the basis of evidence obtained in uncontrolled clinical trials. Herein, Saad et al. discuss the need to conduct randomized controlled trials at all phases of drug development in oncology, and present strategies to facilitate a seamless transition between phases of drug and/or biomarker development.
- Everardo D. Saad
- , Xavier Paoletti
- & Marc Buyse
-
-
Review Article |
Predicting outcomes in radiation oncology—multifactorial decision support systems
The emergence of individualized medicine has spurred the need for the development of clinical decision-support systems (CDSSs) based on prediction models of treatment outcome. In radiation oncology, CDSSs combine clinical, imaging and molecular factors to achieve the highest accuracy to predict tumour response. Here, the authors provide an overview of these factors—including survival, recurrence patterns and toxicity—and discuss the methodology behind the multistage development of CDSSs.
- Philippe Lambin
- , Ruud G. P. M. van Stiphout
- & Andre Dekker
-
Opinion |
Hazard ratios in cancer clinical trials—a primer
The increasing reliance on hazard ratios for the assessment of clinical trial data prompted this Perspectives article, designed to outline the uses and misuses of this popular statistical value. The authors use real trial data and synthetic examples to explain how the hazard ratio is derived and why the numerical value of a survival measure should also be published alongside it.
- Krastan B. Blagoev
- , Julia Wilkerson
- & Tito Fojo
-
-
Correspondence |
P5 medicine: a plus for a personalized approach to oncology
- Alessandra Gorini
- & Gabriella Pravettoni
-
Opinion |
Predictive, personalized, preventive, participatory (P4) cancer medicine
The authors takes a systems-biology approach to the problems of personalized cancer medicine. They describe the challenges of moving to a discipline that is predictive, personalized, preventive and participatory and explore methods for overcoming these obstacles.
- Leroy Hood
- & Stephen H. Friend
Browse broader subjects
Browse narrower subjects
- Biochemical reaction networks
- Cellular signalling networks
- Classification and taxonomy
- Communication and replication
- Computational models
- Computational neuroscience
- Computational platforms and environments
- Data acquisition
- Data integration
- Data mining
- Data processing
- Data publication and archiving
- Databases
- Functional clustering
- Gene ontology
- Gene regulatory networks
- Genome informatics
- Hardware and infrastructure
- High-throughput screening
- Image processing
- Literature mining
- Machine learning
- Microarrays
- Network topology
- Phylogeny
- Power law
- Predictive medicine
- Probabilistic data networks
- Programming language
- Protein analysis
- Protein design
- Protein folding
- Protein function predictions
- Protein structure predictions
- Proteome informatics
- Quality control
- Scale invariance
- Sequence annotation
- Software
- Standards
- Statistical methods
- Virtual drug screening