System for High-Intensity Evaluation During Radiotherapy

Conditions

Chemotherapeutic Toxicity, Radiation Therapy Complication

Brief summary

This quality improvement project will evaluate the implementation of a previously described intervention (twice per week on-treatment clinical evaluations) in a feasible fashion using a previously described machine learning algorithm identifying patients identified at high risk for an emergency visit or hospitalization during radiation therapy.

Jennifer Yin, Maurizio Elia, Ryzen Benson, Alon Witztum, Neville Eclov et al. (10 authors)

JCO Oncology Practice2025-10-01

10.1200/op.2025.21.10_suppl.596

Health Care Cost Reductions with Machine Learning-Directed Evaluations during Radiation Therapy - An Economic Analysis of a Randomized Controlled Study.

Divya Natesan, Eric L. Eisenstein, Samantha M. Thomas, Neville Eclov, Nicole Dalal et al. (14 authors)

UNC Libraries2024-10-05

10.17615/39z7-5n48

Health Care Cost Reductions with Machine Learning–Directed Evaluations during Radiation Therapy — An Economic Analysis of a Randomized Controlled Study

Divya Natesan, Eric L. Eisenstein, Samantha M. Thomas, Neville Eclov, Nicole Dalal et al. (14 authors)

NEJM AI2024-03-158 citations

10.1056/aioa2300118

Implementation of machine learning in the clinic: challenges and lessons in prospective deployment from the System for High Intensity EvaLuation During Radiation Therapy (SHIELD-RT) randomized controlled study.

Hong JC, Eclov NCW, Stephens SJ, Mowery YM, Palta M.

2022-09-307 citations

10.1186/s12859-022-04940-3

System for High-Intensity Evaluation During Radiation Therapy (SHIELD-RT): A Prospective Randomized Study of Machine Learning–Directed Clinical Evaluations During Radiation and Chemoradiation

Julian C. Hong, Neville Eclov, Nicole Dalal, Samantha Thomas, Sarah Jo Stephens et al. (12 authors)

Journal of Clinical Oncology2020-09-0492 citations

10.1200/jco.20.01688

Interventions

OTHERMachine learning algorithm

machine learning directed identification of radiotherapy or chemoradiotherapy patients at high-risk for emergency department acute care and/or hospitalization

Study design

Allocation

RANDOMIZED

Intervention model

PARALLEL

Primary purpose

SUPPORTIVE_CARE

Masking

NONE

Masking description

The ML directed twice-weekly evaluation arm was unblinded. Participants and providers were blinded to ML identification of high risk participants in the once weekly evaluation (standard of care) arm.

Intervention model description

Participants identified by the machine learning (ML) algorithm as high risk were randomized to either once weekly or twice weekly clinical evaluations

Eligibility

Sex/Gender

ALL

Age

18 Years to No maximum

Healthy volunteers

No

Inclusion criteria

• started outpatient radiation therapy with or without concurrent systemic therapy at Duke Cancer Center

Exclusion criteria

* undergoing total body radiation therapy for hematopoetic stem cell transplantation * undergoing therapy as inpatient * treating physician who opted out of randomization * completed radiation therapy prior to algorithm execution

Design outcomes

Primary

Measure	Time frame
Number of unplanned emergency department visits or hospital admissions	6 months

Secondary

Measure	Time frame
Number of unplanned emergency department visits or hospital admissions up to 15 days post radiation treatment	up to 15 days post radiation treatment
Number of missed clinical evaluation visits	6 months
Number of acute care visits with listed reason as anemia, nutrition (including dehydration), diarrhea, emesis, infectious (including fever, pneumonia, and sepsis), nausea, neutropenia, pain category	6 months

Countries

United States

Outcome results

None listed