Premium
Use of electronic patient data storage for evaluating and setting the risk category of late effects in childhood cancer survivors
Author(s) -
Rajala Samuli,
Järvelä Liisa S.,
Huurre Anu,
Grönroos Marika,
Rautava Päivi,
Lähteenmäki Päivi M.
Publication year - 2020
Publication title -
pediatric blood and cancer
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.116
H-Index - 105
eISSN - 1545-5017
pISSN - 1545-5009
DOI - 10.1002/pbc.28678
Subject(s) - medicine , concordance , categorization , electronic health record , confidence interval , cancer , health records , intervention (counseling) , medline , health care , pediatrics , family medicine , psychiatry , artificial intelligence , economics , economic growth , political science , law , computer science
Background Many of the late effects of cancer treatment in childhood may occur even decades after the treatment, and only a minority of the survivors remain as healthy as their peers. Providing appropriate long‐term care for childhood cancer survivors after transition to primary health care is a challenge. Both survivors and primary care providers need information on potential late effects. The lack of a systematic late effect follow‐up plan may lead to excessive use of health care services or delayed intervention. While manual compilation of individual follow‐up plans is time consuming for experienced clinicians, electronic algorithms may be feasible. Procedure In Finland, international guidelines for determining the risk of late effects have been implemented. Nationally, Turku University Hospital was asked with developing an automatized system for calculating the risk of late effects, based on electronic patient records saved in the hospital data lake. An electronic algorithm that uses details from exposure‐based health screening guidelines published by the Children's Oncology Group was created. The results were compared with those manually extracted by an experienced clinician. Results Significant concordance between the manual and algorithm‐based risk classification was found. A total of 355 patients received a classification using the algorithm, and 325 of those matched with the manual categorization, producing a Cohen's coefficient of 0.91 (95% confidence interval 0.88‐0.95). Conclusion Automated algorithms can be used to categorize childhood cancer survivors efficiently and reliably into late effect risk groups. This further enables automatized compilation of appropriate individual late effect follow‐up plan for all survivors.