The role of artificial intelligence in paediatric neuroradiology

Artificial intelligence in paediatric endocrinology: conflict or cooperation

Artificial intelligence (AI) in medicine is transforming healthcare by automating system tasks, assisting in diagnostics, predicting patient outcomes and personalising patient care, founded on the ability to analyse vast datasets. In paediatric endocrinology, AI has been developed for diabetes, for insulin dose adjustment, detection of hypoglycaemia and retinopathy screening; bone age assessment and thyroid nodule screening; the identification of growth disorders; the diagnosis of precocious puberty; and the use of facial recognition algorithms in conditions such as Cushing syndrome, acromegaly, congenital adrenal hyperplasia and Turner syndrome. AI can also predict those most at risk from childhood obesity by stratifying future interventions to modify lifestyle. AI will facilitate personalised healthcare by integrating data from 'omics' analysis, lifestyle tracking, medical history, laboratory and imaging, therapy response and treatment adherence from multiple sources. As data acquisition and processing becomes fundamental, data privacy and protecting children's health data is crucial. Minimising algorithmic bias generated by AI analysis for rare conditions seen in paediatric endocrinology is an important determinant of AI validity in clinical practice. AI cannot create the patient-doctor relationship or assess the wider holistic determinants of care. Children have individual needs and vulnerabilities and are considered in the context of family relationships and dynamics. Importantly, whilst AI provides value through augmenting efficiency and accuracy, it must not be used to replace clinical skills.

Neuroquantification enhances the radiological evaluation of term neonatal hypoxic-ischaemic cerebral injuries

Background

Injury patterns in hypoxic-ischaemic brain injury (HIBI) are well recognised but there are few studies evaluating cerebral injury using neuroquantification models.

Objectives

Quantification of brain volumes in a group of patients with clinically determined cerebral palsy.

Method

In this retrospective study, 297 children with cerebral palsy were imaged for suspected HIBI with analysis of various cerebral substrates. Of these, 96 children over the age of 3 years with a clinical diagnosis of cerebral palsy and abnormal MRI findings underwent volumetric analyses using the NeuroQuant® software solution. The spectrum of volumetric changes and the differences between the various subtypes (and individual subgroups) of HIBI were compared.

Results

Compared with the available normative NeuroQuant® database, the average intracranial volume was reduced to the 1st percentile in all patient groups (p < 0.001). Statistically significant differences were observed among the types and subgroups of HIBI. Further substrate volume reductions were identified and described involving the thalami, brainstem, hippocampi, putamina and amygdala. The combined volumes of five regions of interest (frontal pole, putamen, hippocampus, brainstem and paracentral lobule) were consistently reduced in the Rolandic basal ganglia-thalamus (RBGT) subtype.

Conclusion

This study determined a quantifiable reduction of intracranial volume in all subtypes of HIBI and predictable selective cerebral substrate volume reduction in subtypes and subgroups. In the RBGT subtype, a key combination of five substrate injuries was consistently noted, and thalamic, occipital lobe and brainstem volume reduction was also significant when compared to the watershed subtype.

Contribution

This study demonstrates the value of integrating an artificial intelligence programme into the radiologists' armamentarium serving to quantify brain injuries more accurately in HIBI. Going forward this will be an inevitable evolution of daily radiology practice in many fields of medicine, and it would be beneficial for radiologists to embrace these technological innovations.

Complications of Cancer Therapy in Children: A Comprehensive Review of Neuroimaging Findings

ABSTRACT

Complications of cancer therapy in children can result in a spectrum of neurologic toxicities that may occur at the initiation of therapy or months to years after treatment. Although childhood cancer remains rare, increasing survival rates mean that more children will be living longer after cancer treatment. Therefore, complications of cancer therapy will most likely occur with increasing frequency.At times, it is very difficult to differentiate between therapeutic complications and other entities such as tumor recurrence, development of secondary malignancy, and infection (among other conditions). Radiologists often play a key role in the diagnosis and evaluation of pediatric patients with malignancies, and thus, awareness of imaging findings of cancer complications and alternative diagnoses is essential in guiding management and avoiding misdiagnosis. The aim of this review article is to illustrate the typical neuroimaging findings of cancer therapy-related toxicities, including both early and late treatment effects, highlighting pearls that may aid in making the appropriate diagnosis.

Artificial intelligence-driven prediction of multiple drug interactions

When a drug is administered to exert its efficacy, it will encounter multiple barriers and go through multiple interactions. Predicting the drug-related multiple interactions is critical for drug development and safety monitoring because it provides foundations for practical, safe compatibility and rational use of multiple drugs. With the progress of artificial intelligence (AI) technology, a variety of novel prediction methods for single interaction have emerged and shown great advantages compared to the traditional, expensive and time-consuming laboratory research. To promote the comprehensive and simultaneous predictions of multiple interactions, we systematically reviewed the application of AI in drug-drug, drug-food (excipients) and drug-microbiome interactions. We began by outlining the model methods, evaluation indicators, algorithms and databases commonly used to build models for three types of drug interactions. The models based on the metabolic enzyme P450, drug similarity and drug targets have empathized among the machine learning models of drug-drug interactions. In particular, we discussed the limitations of current approaches and identified potential areas for future research. It is anticipated the in-depth review will be helpful for the development of the next-generation of systematic prediction models for simultaneous multiple interactions.

Machine Learning in the Classification of Pediatric Posterior Fossa Tumors: A Systematic Review

Background: Posterior fossa tumors (PFTs) are a morbid group of central nervous system tumors that most often present in childhood. While early diagnosis is critical to drive appropriate treatment, definitive diagnosis is currently only achievable through invasive tissue collection and histopathological analyses. Machine learning has been investigated as an alternative means of diagnosis. In this systematic review and meta-analysis, we evaluated the primary literature to identify all machine learning algorithms developed to classify and diagnose pediatric PFTs using imaging or molecular data. Methods: Of the 433 primary papers identified in PubMed, EMBASE, and Web of Science, 25 ultimately met the inclusion criteria. The included papers were extracted for algorithm architecture, study parameters, performance, strengths, and limitations. Results: The algorithms exhibited variable performance based on sample size, classifier(s) used, and individual tumor types being investigated. Ependymoma, medulloblastoma, and pilocytic astrocytoma were the most studied tumors with algorithm accuracies ranging from 37.5% to 94.5%. A minority of studies compared the developed algorithm to a trained neuroradiologist, with three imaging-based algorithms yielding superior performance. Common algorithm and study limitations included small sample sizes, uneven representation of individual tumor types, inconsistent performance reporting, and a lack of application in the clinical environment. Conclusions: Artificial intelligence has the potential to improve the speed and accuracy of diagnosis in this field if the right algorithm is applied to the right scenario. Work is needed to standardize outcome reporting and facilitate additional trials to allow for clinical uptake.