Artificial Intelligence Systems Assisting Oncologists? Resist and Desist or Enlist and Coexist

Adashek, Jacob J.; Subbiah, Ishwaria Mohan; Subbiah, Vivek

doi:10.1634/theoncologist.2019-0267

Cited by 6 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The integration of AI into clinical trial research has been slower than expected, mainly owing to the (perceived) friction between AI versus human intelligence. Nevertheless, trials of data generation and interpretation should be conducted, and AI should be used to augment human intelligence-not seen as something to replace it 77 . Next-generation clinical trials using AI should consider AI + human rather than AI versus human scenarios 75,78 .…”

Section: Aimentioning

confidence: 99%

The next generation of evidence-based medicine

Subbiah

2023

Nat Med

Self Cite

274

View full text Add to dashboard Cite

Recently, advances in wearable technologies, data science and machine learning have begun to transform evidence-based medicine, offering a tantalizing glimpse into a future of next-generation 'deep' medicine. Despite stunning advances in basic science and technology, clinical translations in major areas of medicine are lagging. While the COVID-19 pandemic exposed inherent systemic limitations of the clinical trial landscape, it also spurred some positive changes, including new trial designs and a shift toward a more patient-centric and intuitive evidence-generation system. In this Perspective, I share my heuristic vision of the future of clinical trials and evidence-based medicine.

show abstract

Section: Aimentioning

confidence: 99%

The next generation of evidence-based medicine

Subbiah

2023

Nat Med

Self Cite

274

View full text Add to dashboard Cite

show abstract

“…However, predicting clinical outcome for cancer treatments still remains a challenging endeavor due to the diversity of genetic and environmental factors influencing tumor biology. Thus, investigating complex datasets requires sophisticated nonlinear algorithms found in the machine learning (ML) software 7 . The use of ML in oncology is a recently emerging innovative technology, and previous applications have shown promising results 8,9 .…”

Section: Introductionmentioning

confidence: 99%

“…Thus, investigating complex datasets requires sophisticated nonlinear algorithms found in the machine learning (ML) software. 7 The use of ML in oncology is a recently emerging innovative technology, and previous applications have shown promising results. 8,9 For example, ML has been used to identify cancer pathways and phenocopying variants affecting patient response rates, 10 to distinguish high-risk and low-risk patient groups using an integrative network analysis of modules containing signature gene variants 11 and to aid in cancer diagnosis through pattern recognition.…”

mentioning

confidence: 99%

Machine learning model to predict oncologic outcomes for drugs in randomized clinical trials

Schperberg

Boichard

Tsigelny

et al. 2020

Intl Journal of Cancer

View full text Add to dashboard Cite

Predicting oncologic outcome is challenging due to the diversity of cancer histologies and the complex network of underlying biological factors. In this study, we determine whether machine learning (ML) can extract meaningful associations between oncologic outcome and clinical trial, drug‐related biomarker and molecular profile information. We analyzed therapeutic clinical trials corresponding to 1102 oncologic outcomes from 104 758 cancer patients with advanced colorectal adenocarcinoma, pancreatic adenocarcinoma, melanoma and nonsmall‐cell lung cancer. For each intervention arm, a dataset with the following attributes was curated: line of treatment, the number of cytotoxic chemotherapies, small‐molecule inhibitors, or monoclonal antibody agents, drug class, molecular alteration status of the clinical arm's population, cancer type, probability of drug sensitivity (PDS) (integrating the status of genomic, transcriptomic and proteomic biomarkers in the population of interest) and outcome. A total of 467 progression‐free survival (PFS) and 369 overall survival (OS) data points were used as training sets to build our ML (random forest) model. Cross‐validation sets were used for PFS and OS, obtaining correlation coefficients (r) of 0.82 and 0.70, respectively (outcome vs model's parameters). A total of 156 PFS and 110 OS data points were used as test sets. The Spearman correlation (rs) between predicted and actual outcomes was statistically significant (PFS: rs = 0.879, OS: rs = 0.878, P < .0001). The better outcome arm was predicted in 81% (PFS: N = 59/73, z = 5.24, P < .0001) and 71% (OS: N = 37/52, z = 2.91, P = .004) of randomized trials. The success of our algorithm to predict clinical outcome may be exploitable as a model to optimize clinical trial design with pharmaceutical agents.

show abstract

“…Compared to other cancers, gastric cancer is relatively rare in the U.S. According to the National Institute of Health Surveillance, Epidemiology, and End Results program, stomach cancer comprises 1.6% of all newly diagnosed cancer cases in the U.S ( 1 ). However, it is the fifth most common malignancy and the third primary cause of cancer death in the world ( 2 ).…”

Section: Introductionmentioning

confidence: 99%

“…The number of new cases of stomach cancer was 7.4 per 100,000 men and women per year. In 2019, the estimated incidence of gastric cancer will be more than 27,000 with over 11,000 fatalities ( 1 ). Although there has been a decrease in the incidence of gastric cancer, the prognosis of patients with advanced gastric cancer continues to be poor, with a median overall survival (OS) of <12 months ( 3 ).…”

Section: Introductionmentioning

confidence: 99%

Therapeutic Implications of Epidermal Growth Factor Receptor (EGFR) in the Treatment of Metastatic Gastric/GEJ Cancer

et al. 2020

Self Cite

View full text Add to dashboard Cite

Gastric cancer remains third leading cause of global cancer mortality and is the fifth most common type of cancer in the United States. A select number of gastric cancers harbor alterations in EGFR and/or have amplification/overexpression in the HER2; 2–35 and 9–38%, respectively. The advent of next-generation sequencing of tissue and circulating tumor DNA has allowed for the massive expansion of targeted therapeutics to be employed in many settings. There have been a handful of trials using EGFR inhibitors with modest outcomes. Using novel strategies to target multiple co-mutations as well as identifying immunoregulatory molecule expression patterns will potentially drive future trials and improve gastric cancer patient outcomes.

show abstract

Artificial Intelligence Systems Assisting Oncologists? Resist and Desist or Enlist and Coexist

Abstract: The use of artificial intelligence (AI) has become an integral part of patient care, but there are concerns about the impact of non‐human decision assistance on patient outcomes. This commentary focuses on how AI can assist oncologists and benefit patients.

Cited by 6 publications

References 9 publications

The next generation of evidence-based medicine

The next generation of evidence-based medicine

Machine learning model to predict oncologic outcomes for drugs in randomized clinical trials

Therapeutic Implications of Epidermal Growth Factor Receptor (EGFR) in the Treatment of Metastatic Gastric/GEJ Cancer

Contact Info

Product

Resources

About