Dataset Information

Towards identifying cancer patients at risk to miss out on psycho-oncological treatment via machine learning.

ABSTRACT:

Objective

In routine oncological treatment settings, psychological distress, including mental disorders, is overlooked in 30% to 50% of patients. High workload and a constant need to optimise time and costs require a quick and easy method to identify patients likely to miss out on psychological support.

Methods

Using machine learning, factors associated with no consultation with a clinical psychologist or psychiatrist were identified between 2011 and 2019 in 7,318 oncological patients in a large cancer treatment centre. Parameters were hierarchically ordered based on statistical relevance. Nested resampling and cross validation were performed to avoid overfitting.

Results

Patients were least likely to receive psycho-oncological (i.e., psychiatric/psychotherapeutic) treatment when they were not formally screened for distress, had inpatient treatment for less than 28 days, had no psychiatric diagnosis, were aged 65 or older, had skin cancer or were not being discussed in a tumour board. The final validated model was optimised to maximise sensitivity at 85.9% and achieved an area under the curve (AUC) of 0.75, a balanced accuracy of 68.5% and specificity of 51.2%.

Conclusion

Beyond conventional screening tools, results might contribute to identify patients at risk to be neglected in terms of referral to psycho-oncology within routine oncological care.

SUBMITTER: Gunther MP

PROVIDER: S-EPMC9286797 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundCancer patients often suffer from psychological distress. Psycho-oncological services (POS) have been established in some health care systems in order to address such issues. This study aims to identify patient and center characteristics that elucidate the use of POS by patients in prostate cancer centers (PCCs).MethodsCenter-reported certification and patient survey data from 3094 patients in 44 certified PCCs in Germany were gathered in the observational study (Prostate Cancer Outcomes). A multilevel analysis was conducted.ResultsModel 1 showed that utilization of POS in PCCs is associated with patients' age (OR = 0.98; 95%-CI = 0.96-0.99; P < .001), number of comorbidities (1-2 vs 0, OR = 1.27; 95%-CI = 1.00-1.60; P=.048), disease staging (localized high-risk vs localized intermediate risk, OR = 1.41; 95%-CI = 1.14-1.74; P < .001), receiving androgen deprivation therapy before study inclusion (OR = 0.19; 95%-CI = 0.10-0.34; P < .001), and hospital teaching status (university vs academic, OR = 0.09; 95%-CI = 0.02-0.55; P = .009). Model 2 additionally includes information on treatment after study inclusion and shows that after inclusion, patients who receive primary radiotherapy (OR = 0.05; 95%-CI = 0.03-0.10; P < .001) or undergo active surveillance/watchful waiting (OR = 0.06; 95%-CI = 0.02-0.15; P < .001) are less likely to utilize POS than patients who undergo radical prostatectomy. Disease staging (localized high-risk vs localized intermediate risk, OR = 1.31; 95%-CI = 1.05-1.62; P = .02) and teaching status (university vs academic, OR = 0.08; 95%-CI = 0.01-0.65; P = .02) are also significant predictors for POS use. The second model did not identify any other significant patient characteristics.ConclusionsFuture research should explore the role of institutional teaching status and whether associations with therapy after study inclusion are due to treatment effects - for example, less need following radiotherapy - or because access to POS is more difficult for those receiving radiotherapy.