Clinical research tools in pediatric oncology: challenges and opportunities

The Role of Machine Learning Approaches in Pediatric Oncology: A Systematic Review

To enhance patient outcomes in pediatric cancer, a better understanding of the medical and biological risk variables is required. With the growing amount of data accessible to research in pediatric cancer, machine learning (ML) is a form of algorithmic inference from sophisticated statistical techniques. In addition to highlighting developments and prospects in the field, the objective of this systematic study was to methodically describe the state of ML in pediatric oncology. We followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines to search for relevant studies on four distinct databases (Scopus, Web of Science, PubMed, and Cochrane Library). A total of 1536 relevant studies were retrieved to the EndNote library (Clarivate, Philadelphia, USA) where duplicates were removed and the rest of the studies were assessed for eligibility based on titles, abstracts, and the availability of full-text articles. After assessing the studies for eligibility, we found 42 studies eligible for inclusion in this systematic review. We found nine studies on liquid tumors, 13 on solid tumors, and 20 on central nervous system (CNS) tumors. ML goals included classification, treatment response prediction, and dose optimization. Neural networks, k-nearest neighbors, random forests, support vector machines, and naive Bayes were among the techniques employed. The identified studies' strengths included treatment response prediction and automated analysis that matched or outperformed physician comparators. Significant variation in clinical applicability, criteria for reporting, limited sample numbers, and the absence of external validation cohorts were among the common issues. We found places where ML can improve clinical care in manners that would not be possible otherwise. Even though ML has great promise for enhancing pediatric cancer diagnosis, decision-making, and monitoring, the discipline is still in its infancy, and standards and recommendations will support future research to guarantee robust methodologic design and maximize therapeutic applicability.

Supportive Care in Pediatric Oncology: Opportunities and Future Directions

The optimization of outcomes for pediatric cancer patients relies on the successful advancement of supportive care to ease the treatment burden and mitigate the long-term impacts of cancer therapy. Advancing pediatric supportive care requires research prioritization as well as the development and implementation of innovations. Like the prevailing theme throughout pediatric oncology, there is a clear need for personalized or precision approaches that are consistent, evidence-based, and guided by clinical practice guidelines. By incorporating technology and datasets, we can address questions which may not be feasible to explore in clinical trials. Now is the time to listen to patients' voices by using patient-reported outcomes (PROs) to ensure that their contributions and experiences inform clinical care plans. Furthermore, while the extrapolation of knowledge and approaches from adult populations may suffice in the absence of pediatric-specific evidence, there is a critical need to specifically understand and implement elements of general and developmental pediatrics like growth, nutrition, development, and physical activity into care. Increased research funding for pediatric supportive care is critical to address resource availability, equity, and disparities across the globe. Our patients deserve to enjoy healthy, productive lives with optimized and enriched supportive care that spans the spectrum from diagnosis to survivorship.

Clinical research with targeted drugs in paediatric oncology

The development of targeted drugs in paediatric oncology has been notoriously slow, in part due to the peculiarities of this rare and highly heterogeneous population. To provide therapeutic breakthroughs for the highest risk subgroups of childhood cancer, innovative research solutions have been implemented in the last several years by different international collaborative groups and regulators. Here, we discuss and summarise some of these approaches, as well as challenges and unmet needs that are still being addressed. A wide range of topics were covered in this review including molecular diagnosis optimisation, innovative research methodologies, big data approaches, trial enrolment strategies, and improvements in regulation and preclinical research platforms.

Updating our understanding of health-related quality of life issues in children with cancer: a systematic review of patient-reported outcome measures and qualitative studies

BACKGROUND

Health-related quality of life (HRQOL) is a key concept in pediatric oncology. This systematic review aims to update the conceptual HRQOL model by Anthony et al. (Qual Life Res 23(3):771-789, 2014), covering physical, emotional, social and general HRQOL aspects, and to present a comprehensive overview of age- and disease-specific HRQOL issues in children with cancer.

METHODS

Medline, PsychINFO, the Cochrane Database for Systematic Reviews (CDSR), and the COSMIN database were searched (up to 31.12.2020) for publications using patient-reported outcome measures (PROMs) and qualitative studies in children with cancer (8-14-year) or their parents. Items and quotations were extracted and mapped onto the conceptual model for HRQOL in children with cancer mentioned above.

RESULTS

Of 2038 identified studies, 221 were included for data extraction. We identified 96 PROMS with 2641 items and extracted 798 quotations from 45 qualitative studies. Most items and quotations (94.8%) could be mapped onto the conceptual model. However, some adaptations were made and the model was complemented by (sub)domains for 'treatment burden', 'treatment involvement', and 'financial issues'. Physical and psychological aspects were more frequently covered than social issues.

DISCUSSION

This review provides a comprehensive overview of HRQOL issues for children with cancer. Our findings mostly support the HRQOL model by Anthony et al. (Qual Life Res 23(3):771-789, 2014), but some adaptations are suggested. This review may be considered a starting point for a refinement of our understanding of HRQOL in children with cancer. Further qualitative research will help to evaluate the comprehensiveness of the HRQOL model and the relevance of the issues it encompasses.

Large Improvements in Health-Related Quality of Life and Physical Fitness during Multidisciplinary Inpatient Rehabilitation for Pediatric Cancer Survivors

Rehabilitation is a key element in improving health-related quality of life (HRQOL) for pediatric cancer survivors. The aim of this study was to present data from a multidisciplinary inpatient rehabilitation treatment. Children took part in a four-week multidisciplinary family-oriented inpatient rehabilitation. A total of 236 children (>5−21 years) and 478 parents routinely completed electronic patient-reported outcomes (ePROs), performance-based assessments, and clinician-rated assessments before (T1) and at the end (T2) of rehabilitation. HRQOL was assessed with the PedsQL generic core and PedsQL cancer module. Data were analyzed using repeated measures analysis of variance (ANOVA). Statistically significant improvements with medium to large effect sizes were observed for most HRQOL scales (η2 = 0.09−0.31), as well as performance-based and clinician-rated assessments for physical activity and functional status (η2 > 0.28). Agreement between children’s PROs and parents’ proxy ratings was lower before (rICC = 0.72) than after (rICC = 0.86) rehabilitation. While the concordance between children and parents’ assessment of changes during rehab was low to moderate (r = 0.19−0.59), the use of the performance score led to substantially increased scores (r = 0.29−0.68). The results of this naturalistic observational study thus highlight the benefits of multidisciplinary pediatric inpatient rehabilitation for childhood cancer survivors. The use of the performance score is recommended in this field.

Patient-reported outcomes are under-utilised in evaluating supportive therapies in paediatric oncology - A systematic review of clinical trial registries

BACKGROUND

Children with cancer suffer from numerous symptoms and side-effects, making supportive interventions indispensable to improve their quality of life. The gold standard for evaluating the latter is patient-reported outcome (PRO) assessment. This systematic review investigates the current practice of clinical outcome assessment (COA) in clinical trials on supportive interventions.

METHODS

ClinicalTrials.gov and EudraCT were searched for trials including children and adolescents (≤21 years) with cancer receiving supportive care registered 2007-2020. The use of different types of COAs was analysed, focusing on PRO assessment and the domains measured with PRO measures (PROMs). Associations with trial characteristics were investigated using univariate and multivariable analyses.

RESULTS

Of 4789 identified trials, 229 were included. Among them, 44.1 % relied on PROMs, the most commonly used COA. The proportion of trials using PROMs did not significantly differ over time. In the multivariable analysis, intervention type (higher PROM use in behavioural vs. medical interventional trials) and cancer type (higher PROM use in mixed and solid tumour samples vs. haematological samples) were significant predictors of PROM use. The majority of trials using PROMs (59.6 %) measured more than one health domain. 'Physical health' was the most frequently assessed domain (92.6 %).

CONCLUSION

Less than half of registered clinical trials investigating supportive interventions for children with cancer used PROMs. This result is striking since supportive care explicitly focuses on patients' quality of life, which is best assessed using PROMs. Our systematic review underlines the need to identify barriers for PROM implementation and to improve PRO research in paediatric oncology.

Chemotherapy induced kidney and urinary tract related complications: A study in the Department of Pediatric Oncology and Hematology

Nephrotoxicity is one of the most severe late-term side effects after chemotherapy. It is important to evaluate the possible risks and provide valuable treatment and follow-up for the patient.

METHODS

the data was observed from 50 patients from 0 till 18 years old that were treated for childhood cancer and was collected according to methodological recommendations.

RESULTS

28 boys and 22 girls were included and the average age of all patients when the diagnosis was made was five years. 56% have faced kidney and urinary tract related complications. 75% of those patients have faced nephrotoxicity, 10,71 - urinary tract related complications and 14,29 have faced both - nephrotoxicity and urinary tract related complications. GFR was decreased in one case, increased in three cases and normal in the remaining cases. There was no statistical significance between kidney and urinary tract related complications and patient's age at the time of treatment, type of cancer (except for sarcomas), type of surgery or radiotherapy. Nephrotoxicity had statistical significance to occur more commonly during the first two years after treatment, while urinary tract related complications occurred more frequently during five years after treatment. Doxorubicin and Ifosfamide had statistical significance with kidney-related long-side effect; Lomustine also had a close relation. Chemotherapy drug's cumulative dose also had statistical significance of the same chemotherapy drugs.

CONCLUSIONS

this study suggests that chemotherapy drug and its cumulative dosage has the most influence on kidney and urinary tract related complications.

Implementation of daily patient-reported outcome measurements to support children with cancer

BACKGROUND

Several stakeholders, including patients and health care providers, suggest symptom self-reporting measurements for a more patient-directed cancer control approach. However, services tailored to measure daily reporting and implementing it in clinical care are lacking. This study aimed to evaluate the feasibility and value of daily patient-reported outcome measures (PROMs) by children receiving chemotherapy for cancer.

METHODS

Health status was recorded daily with a web-based child-friendly patient portal (ePROtect). Following aspects of feasibility and usability were assessed: (a) the completion rate and time, (b) user feedback on usability and satisfaction, and (c) the performed interventions if moderate to severe symptom deterioration was noted.

RESULTS

Twelve children (median age: 7.2 years) were included. A total number of 891 daily reports were collected during the study period; the median percentage of ePROtect completion days was 85.3% (interquartile range [IQR] 64.2-100.0) and 55.9% (IQR 51.9-76.9) for inpatient and outpatient stay, respectively. Mean time to complete the questionnaire was 47.6 seconds. Severe symptoms were reported in 14.7% of measurement time points, which led to prompt health care interventions in 57 cases, including extension of supportive care (n = 37) and pre-emptive inpatient admissions (n = 5). Over 80% of the patients (10/12) and their proxies (16/18) provided feedback with high rating for satisfaction (>90%) and usefulness (>80%) of ePROtect.

CONCLUSION

Our study shows that daily symptom monitoring is feasible for all children with newly diagnosed cancer aged 5-18 years. Monitoring offers the opportunity to identify symptoms early and trigger appropriate clinical action.

Bridging the gap in outpatient care: Can a daily patient-reported outcome measure help?

BACKGROUND

Childhood patients have high risks for developing debilitating somatic and mental health side-effects as a consequence of the many different approaches employed in treating their cancer. Early recognition and close monitoring of clinical and psychological problems are essential in planning appropriate interventions and preventing further deterioration.

CASE

ePROtect was established as an easy-to-use application for daily self-reporting of symptoms during cancer therapy. ePROtect includes six to eight questions pertaining to seven common symptoms: appetite loss, fatigue, nausea, pain, physical functioning, cognitive impairments and sleep quality. The case of a child diagnosed with Burkitt leukemia developing chemotherapy-induced oral mucositis in home care is presented to show the therapeutic impact of early symptom detection with a daily web-based tool.

CONCLUSION

This case highlights how electronic patient-reported outcome measures (PROM) can directly facilitate patient care in real time and might be incorporated in future clinical routine.