An introduction to machine learning for clinicians: How can machine learning augment knowledge in geriatric oncology?

Ramsdale, Erika; Snyder, Eric M.; Culakova, Eva; Xu, Huiwen; Dziorny, Adam; Yang, Shuhan; Zand, Martin S.; Anand, Ajay

doi:10.1016/j.jgo.2021.03.012

Cited by 8 publications

(9 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This summarized information can be used with GA to assess the vulnerability of older adults . For patients in the high-severity cluster, clinicians may consider modifying treatment options and monitor adverse events during and after treatments . Clinical studies are warranted to examine whether clinicians use the clustering information to inform treatment decisions and improve patient outcomes, similar to recent GA trials …”

Section: Discussionmentioning

confidence: 99%

“…One potential approach is to use machine learning algorithms in addition to traditional methods, such as total score (eg, the scoring of MD Anderson Symptom Inventory) . Specifically, unsupervised machine learning, a data mining method that aims to detect unknown patterns in data without the need for prior human knowledge and intervention, may achieve this purpose. Researchers have become increasingly interested in applying unsupervised machine learning to identify cancer symptom subgroups .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Unsupervised Machine Learning Approach to Evaluating the Association of Symptom Clusters With Adverse Outcomes Among Older Adults With Advanced Cancer

Mohamed

Flannery

et al. 2023

JAMA Netw Open

Self Cite

View full text Add to dashboard Cite

ImportanceOlder adults with advanced cancer who have high pretreatment symptom severity often experience adverse events during cancer treatments. Unsupervised machine learning may help stratify patients into different risk groups.ObjectiveTo evaluate whether clusters identified from baseline patient-reported symptom severity were associated with adverse outcomes.Design, Setting, and ParticipantsThis secondary analysis of the Geriatric Assessment Intervention for Reducing Toxicity in Older Patients With Advanced Cancer (GAP70+) Trial (2014-2019) included patients who completed the National Cancer Institute Patient-Reported Outcomes version of the Common Terminology Criteria for Adverse Events (PRO-CTCAE) before starting a new cancer treatment regimen and received care at community oncology sites across the United States. An unsupervised machine learning algorithm (k-means with Euclidean distance) clustered patients based on similarities of baseline symptom severities. Clustering variables included severity items of 24 PRO-CTCAE symptoms (range, 0-4; corresponding to none, mild, moderate, severe, and very severe). Total severity score was calculated as the sum of 24 items (range, 0-96). Whether the clusters were associated with unplanned hospitalization, death, and toxic effects was then examined. Analyses were conducted in January and February 2022.ExposuresSymptom severity.Main Outcomes and MeasuresUnplanned hospitalization over 3 months (primary), all-cause mortality over 1 year, and any clinician-rated grade 3 to 5 toxic effect over 3 months.ResultsOf 718 enrolled patients, 706 completed baseline PRO-CTCAE and were included (mean [SD] age, 77.2 [5.5] years, 401 [56.8%] male patients; 51 [7.2%] Black and 619 [87.8%] non-Hispanic White patients; 245 [34.7%] with gastrointestinal cancer; 175 [24.8%] with lung cancer; mean [SD] impaired Geriatric Assessment domains, 4.5 [1.6]). The algorithm classified 310 (43.9%), 295 (41.8%), and 101 (14.3%) into low-, medium-, and high-severity clusters (within-cluster mean [SD] severity scores: low, 6.3 [3.4]; moderate, 16.6 [4.3]; high, 29.8 [7.8]; P &lt; .001). Controlling for sociodemographic variables, clinical factors, study group, and practice site, compared with patients in the low-severity cluster, those in the moderate-severity cluster were more likely to experience hospitalization (risk ratio, 1.36; 95% CI, 1.01-1.84; P = .046). Moderate- and high-severity clusters were associated with a higher risk of death (moderate: hazard ratio, 1.31; 95% CI, 1.01-1.69; P = .04; high: hazard ratio, 2.00; 95% CI, 1.43-2.78; P &lt; .001), but not toxic effects.Conclusions and RelevanceIn this study, unsupervised machine learning partitioned patients into distinct symptom severity clusters; patients with higher pretreatment severity were more likely to experience hospitalization and death.Trial RegistrationClinicalTrials.gov Identifier: NCT02054741

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

An Unsupervised Machine Learning Approach to Evaluating the Association of Symptom Clusters With Adverse Outcomes Among Older Adults With Advanced Cancer

Mohamed

Flannery

et al. 2023

JAMA Netw Open

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Machine Learningmentioning

confidence: 99%

“…52 These programs can be further categorized by whether the learning is supervised where the outcome is known, and unsupervised where the outcome is unknown. 53,54 The goal of supervised learning is to train the model to predict the output when new data are provided, while the goal of unsupervised learning is to use the provided data to identify natural relationships within the data. 53 Within supervised learning, one common method is the random forest method which is used to solve regression and classification problems through the collection of a large number of decision trees.…”

Section: Machine Learningmentioning

confidence: 99%

Health Services Research in Anesthesia: A Brief Overview of Common Methodologies

Illescas

Zhong

Cozowicz

et al. 2022

Anesthesia &Amp; Analgesia

View full text Add to dashboard Cite

The use of large data sources such as registries and claims-based data sets to perform health services research in anesthesia has increased considerably, ultimately informing clinical decisions, supporting evaluation of policy or intervention changes, and guiding further research. These observational data sources come with limitations that must be addressed to effectively examine all aspects of health care services and generate new individual- and population-level knowledge. Several statistical methods are growing in popularity to address these limitations, with the goal of mitigating confounding and other biases. In this article, we provide a brief overview of common statistical methods used in health services research when using observational data sources, guidance on their interpretation, and examples of how they have been applied to anesthesia-related health services research. Methods described involve regression, propensity scoring, instrumental variables, difference-in-differences, interrupted time series, and machine learning.

show abstract

“…Real-world evidence from big data sets and their analysis with machine learning is widely seen as an opportunity to develop medical knowledge, especially in a complex field such as GO. 29 Such tools are also typically seen in the realm of large academic cancer centers and large companies. Yet most patients with cancer are treated in nonacademic settings.…”

Section: Leveraging Artificial Intelligence and Big Data To Improve C...mentioning

confidence: 99%

Global Aging and Cancer: Advancing Care Through Innovation

Extermann

Hernández-Favela

Celis

et al. 2022

American Society of Clinical Oncology Educational Book

View full text Add to dashboard Cite

The oncology field, like many others, is digitalizing rapidly, a phenomenon that may have been accelerated by the COVID-19 pandemic. This movement is creating opportunities and challenges. Another rapidly developing change is the aging of the global population; because cancer is a disease of aging, there is a need for health systems to adapt to taking care of such patients. In this article, we address how these innovative technologies can be leveraged to improve the care of older patients with cancer beyond academic centers, such as in underserved areas and low- and middle-income countries. We review how digital technologies can be used to enhance the follow-up of patients in low- and middle-income countries. We also tackle the issue of training a global workforce to treat cancer in an aging population and how to leverage innovations in this matter. Finally, we review opportunities to expand the usefulness of big data and machine learning beyond academic centers to support private practices and underserved areas.

show abstract

An introduction to machine learning for clinicians: How can machine learning augment knowledge in geriatric oncology?

Cited by 8 publications

References 36 publications

An Unsupervised Machine Learning Approach to Evaluating the Association of Symptom Clusters With Adverse Outcomes Among Older Adults With Advanced Cancer

An Unsupervised Machine Learning Approach to Evaluating the Association of Symptom Clusters With Adverse Outcomes Among Older Adults With Advanced Cancer

Health Services Research in Anesthesia: A Brief Overview of Common Methodologies

Global Aging and Cancer: Advancing Care Through Innovation

Contact Info

Product

Resources

About