Aid of a Machine Learning Algorithm Can Improve Clinician Predictions of Patient Quality of Life During Breast Cancer Treatments

19 Pages Posted: 23 Mar 2022

See all articles by Mikko Nuutinen

Mikko Nuutinen

Nordic Healthcare Group

Anna-Maria Hiltunen

affiliation not provided to SSRN

Sonja Korhonen

affiliation not provided to SSRN

Ira Haavisto

Nordic Healthcare Group

Paula Poikonen-Saksela

affiliation not provided to SSRN

Johanna Mattson

affiliation not provided to SSRN

Georgios Manikis

affiliation not provided to SSRN

Haridimos Kondylakis

Foundation for Research and Technology - Hellas (FORTH) - Institute of Computer Science (ICS)

Panagiotis Simos

affiliation not provided to SSRN

Ketti Mazzocco

University of Milan

Ruth Pat-Horenczyk

Hebrew University of Jerusalem

Berta Sousa

affiliation not provided to SSRN

Fatima Cardoso

affiliation not provided to SSRN

Isabel Manica

affiliation not provided to SSRN

Ian Kudel

affiliation not provided to SSRN

Riikka-Leena Leskelä

Nordic Healthcare Group

Abstract

Proper and well-timed interventions may improve breast cancer patient adaptation and quality of life (QoL) through treatment and recovery. The challenge is to identify those patients who would benefit most from a particular intervention. The aim of this study was to measure whether the machine learning prediction incorporated in the clinical decision support system (CDSS) improves clinicians’ performance to predict patients’ QoL during treatment process. We conducted two user experiments in which clinicians used a CDSS to predict QoL of breast cancer patients. In both experiments each patient was evaluated both with and without the aid of a machine learning (ML) prediction. In Experiment I, 60 breast cancer patients were evaluated by 6 clinicians. In Experiment II, 90 patients were evaluated by 9 clinicians. The task of clinicians was to predict the patient’s quality of life at either 6 (Experiment I) or 12 months post-diagnosis (Experiment II). Taking into account input from the CDSS considerably improved clinicians’ prediction accuracy. Accuracy of clinicians for predicting QoL of patients at 6 months post-diagnosis was .745 (95% CI .668-.821) with the aid of the prediction provided by the ML model and .696 (95% CI .608-.781) without the aid. Clinicians’ prediction accuracy at 12 months was .739 (95% CI .667-.812) with the aid and .709 (95% CI .633- .783) without the aid. When the machine learning model’s prediction was correct, the average accuracy of the clinicians for predicting QoL at 6 months was .793 (95% CI .739-.838) with the aid and .720 (95% CI .636-.798) without the aid. Corresponding prediction accuracy of QoL at 12 months was .909 (95% CI .881-.936) and .827 (95% CI .782-.871).

Note:
Funding Information: This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 777167.

Declaration of Interests: The authors declare no conflicts of interest relevant to the manuscript content.

Ethics Approval Statement: This study is part of EU-funded multicenter clinical study (H2020 EU project BOUNCE GA no 777167), approved by the European Institute of Oncology, Applied Research Division for Cognitive and Psychological Science (Approval No R868/18 – IEO 916) and the clinical ethical committees of each hospital.

Keywords: Clinical decision support system, breast cancer, quality of life, Machine learning, user experiment

Suggested Citation

Nuutinen, Mikko and Hiltunen, Anna-Maria and Korhonen, Sonja and Haavisto, Ira and Poikonen-Saksela, Paula and Mattson, Johanna and Manikis, Georgios and Kondylakis, Haridimos and Simos, Panagiotis and Mazzocco, Ketti and Pat-Horenczyk, Ruth and Sousa, Berta and Cardoso, Fatima and Manica, Isabel and Kudel, Ian and Leskelä, Riikka-Leena, Aid of a Machine Learning Algorithm Can Improve Clinician Predictions of Patient Quality of Life During Breast Cancer Treatments. Available at SSRN: https://ssrn.com/abstract=4064780 or http://dx.doi.org/10.2139/ssrn.4064780

Mikko Nuutinen (Contact Author)

Nordic Healthcare Group ( email )

Helsinki
Finland

Anna-Maria Hiltunen

affiliation not provided to SSRN ( email )

No Address Available

Sonja Korhonen

affiliation not provided to SSRN ( email )

No Address Available

Ira Haavisto

Nordic Healthcare Group ( email )

Paula Poikonen-Saksela

affiliation not provided to SSRN ( email )

No Address Available

Johanna Mattson

affiliation not provided to SSRN ( email )

No Address Available

Georgios Manikis

affiliation not provided to SSRN ( email )

No Address Available

Haridimos Kondylakis

Foundation for Research and Technology - Hellas (FORTH) - Institute of Computer Science (ICS) ( email )

Crete
Greece

Panagiotis Simos

affiliation not provided to SSRN ( email )

No Address Available

Ketti Mazzocco

University of Milan ( email )

Via Festa del Perdono, 7
Milan, 20122
Italy

Ruth Pat-Horenczyk

Hebrew University of Jerusalem ( email )

Mount Scopus
Jerusalem, 91905
Israel

Berta Sousa

affiliation not provided to SSRN ( email )

No Address Available

Fatima Cardoso

affiliation not provided to SSRN ( email )

No Address Available

Isabel Manica

affiliation not provided to SSRN ( email )

No Address Available

Ian Kudel

affiliation not provided to SSRN ( email )

No Address Available

Riikka-Leena Leskelä

Nordic Healthcare Group ( email )

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
70
Abstract Views
245
Rank
557,138
PlumX Metrics