Machine learning in oncology—Perspectives in patient-reported outcome research

Lehmann, Jens; Cofala, Tim; Tschuggnall, Michael; Giesinger, Johannes; Rumpold, Gerhard; Holzner, Bernhard

doi:10.1007/s00761-021-00916-9

Cited by 4 publications

(2 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of ePROs will continue to expand in the future including machine learning techniques which will offer higher predictive power with regard to survival and QoL of cancer patients (40). Therefore, compliance with ethical principles in the design and implementation of digital novel technologies is not only a concern of the present but will increasingly be a crosscutting issue in the treatment and empowerment of cancer patients.…”

Section: Building a Trustworthy Ethical Approachmentioning

confidence: 99%

Ethical Principles in Digital Palliative Care for Children: The MyPal Project and Experiences Made in Designing a Trustworthy Approach

Garani-Papadatos¹,

Natsiavas²,

Meyerheim³

et al. 2022

Front. Digit. Health

View full text Add to dashboard Cite

This paper explores the ethical dimension of the opportunity to offer improved electronic patient-reported outcome (ePRO) systems addressing personal needs of pediatric cancer patients, their parents and caregivers, with regard to technological advance of digital health. This opportunity has been explored in the MyPal research project, which aims to assess a patient-centered service for palliative care relying on the adaptation and extension of digital health tools and concepts available from previous projects. Development and implementation of ePROs need to take place in a safe, secure and responsible manner, preventing any possible harm and safeguarding the integrity of humans. To that end, although the final results will be published at the end of the project, this paper aims to increase awareness of the ethical ramifications we had to address in the design and testing of new technologies and to show the essentiality of protection and promotion of privacy, safety and ethical standards. We have thus reached a final design complying with the following principles: (a) respect for the autonomy of participants, especially children, (b) data protection and transparency, (c) fairness and non-discrimination, (d) individual wellbeing of participants in relation to their physical and psychological health status and e) accessibility and acceptability of digital health technologies for better user-engagement. These principles are adapted from the Ethics Guidelines for a trustworthy Artificial Intelligence (AI) which provide the framework for similar interventions to be lawful, complying with all applicable laws and regulations, ethical, ensuring compliance to ethical principles and values and robust, both from a technical and social perspective.

show abstract

Section: Building a Trustworthy Ethical Approachmentioning

confidence: 99%

Ethical Principles in Digital Palliative Care for Children: The MyPal Project and Experiences Made in Designing a Trustworthy Approach

Garani-Papadatos¹,

Natsiavas²,

Meyerheim³

et al. 2022

Front. Digit. Health

View full text Add to dashboard Cite

show abstract

“…Applications of AI in oncological management include medical/pathological image or video analysis, natural language processing of free-full text electronic health record (EHR) reports, robots, and chatbots as intervention assistants and information resources, affective computing for digital health assistants, automated treatment planning and scheduling, and machine learning (ML) models for the prediction of cancer-related outcomes (7)(8)(9)(10)(11)(12)(13)(14)(15). ML-based models have been proposed or evaluated regarding their ability to perform individualized diagnosis, risk stratification, tumor profiling, assisted screening, treatment selection, and disease prognosis prediction (7,(14)(15)(16)(17)(18). However, many of the predictive intelligent models have been constructed for and using populations in upper-middle and high-income countries in line with the current distributions of cancer burden (19).…”

Section: Introductionmentioning

confidence: 99%

Construction of machine learning-based models for cancer outcomes in low and lower-middle income countries: A scoping review

Adeoye

Akinshipo²,

Koohi‐Moghadam³

et al. 2022

Front. Oncol.

View full text Add to dashboard Cite

BackgroundThe impact and utility of machine learning (ML)-based prediction tools for cancer outcomes including assistive diagnosis, risk stratification, and adjunctive decision-making have been largely described and realized in the high income and upper-middle-income countries. However, statistical projections have estimated higher cancer incidence and mortality risks in low and lower-middle-income countries (LLMICs). Therefore, this review aimed to evaluate the utilization, model construction methods, and degree of implementation of ML-based models for cancer outcomes in LLMICs.MethodsPubMed/Medline, Scopus, and Web of Science databases were searched and articles describing the use of ML-based models for cancer among local populations in LLMICs between 2002 and 2022 were included. A total of 140 articles from 22,516 citations that met the eligibility criteria were included in this study.ResultsML-based models from LLMICs were often based on traditional ML algorithms than deep or deep hybrid learning. We found that the construction of ML-based models was skewed to particular LLMICs such as India, Iran, Pakistan, and Egypt with a paucity of applications in sub-Saharan Africa. Moreover, models for breast, head and neck, and brain cancer outcomes were frequently explored. Many models were deemed suboptimal according to the Prediction model Risk of Bias Assessment tool (PROBAST) due to sample size constraints and technical flaws in ML modeling even though their performance accuracy ranged from 0.65 to 1.00. While the development and internal validation were described for all models included (n=137), only 4.4% (6/137) have been validated in independent cohorts and 0.7% (1/137) have been assessed for clinical impact and efficacy.ConclusionOverall, the application of ML for modeling cancer outcomes in LLMICs is increasing. However, model development is largely unsatisfactory. We recommend model retraining using larger sample sizes, intensified external validation practices, and increased impact assessment studies using randomized controlled trial designsSystematic review registrationhttps://www.crd.york.ac.uk/prospero/display_record.php?RecordID=308345, identifier CRD42022308345.

show abstract

Development of machine learning models to predict cancer-related fatigue in Dutch breast cancer survivors up to 15 years after diagnosis

Beenhakker,

Wijlens,

Witteveen

et al. 2023

J Cancer Surviv

View full text Add to dashboard Cite

Purpose To prevent (chronic) cancer-related fatigue (CRF) after breast cancer, it is important to identify survivors at risk on time. In literature, factors related to CRF are identified, but not often linked to individual risks. Therefore, our aim was to predict individual risks for developing CRF. Methods Two pre-existing datasets were used. The Nivel-Primary Care Database and the Netherlands Cancer Registry (NCR) formed the Primary Secondary Cancer Care Registry (PSCCR). NCR data with Patient Reported Outcomes Following Initial treatment and Long-term Evaluation of Survivorship (PROFILES) data resulted in the PSCCR-PROFILES dataset. Predictors were patient, tumor and treatment characteristics, and pre-diagnosis health. Fatigue was GP-reported (PSCCR) or patient-reported (PSCCR-PROFILES). Machine learning models were developed, and performances compared using the C-statistic. Results In PSCCR, 2224/12813 (17%) experienced fatigue up to 7.6 ± 4.4 years after diagnosis. In PSCCR-PROFILES, 254 (65%) of 390 patients reported fatigue 3.4 ± 1.4 years after diagnosis. For both, models predicted fatigue poorly with best C-statistics of 0.561 ± 0.006 (PSCCR) and 0.669 ± 0.040 (PSCCR-PROFILES). Conclusion Fatigue (GP-reported or patient-reported) could not be predicted accurately using available data of the PSCCR and PSCCR-PROFILES datasets. Implications for Cancer Survivors CRF is a common but underreported problem after breast cancer. We aimed to develop a model that could identify individuals with a high risk of developing CRF, ideally to help them prevent (chronic) CRF. As our models had poor predictive abilities, they cannot be used for this purpose yet. Adding patient-reported data as predictor could lead to improved results. Until then, awareness for CRF stays crucial.

show abstract

Machine learning in oncology—Perspectives in patient-reported outcome research

Cited by 4 publications

References 26 publications

Ethical Principles in Digital Palliative Care for Children: The MyPal Project and Experiences Made in Designing a Trustworthy Approach

Ethical Principles in Digital Palliative Care for Children: The MyPal Project and Experiences Made in Designing a Trustworthy Approach

Construction of machine learning-based models for cancer outcomes in low and lower-middle income countries: A scoping review

Development of machine learning models to predict cancer-related fatigue in Dutch breast cancer survivors up to 15 years after diagnosis

Contact Info

Product

Resources

About