Methodological and ethical challenges in the use of focused ultrasound for blood-brain barrier disruption in neuro-oncology

Abstract

Background: Focused ultrasound (FUS) shows promise for enhancing drug delivery to the brain by temporarily opening the blood-brain barrier (BBB), and it is increasingly used in the clinical setting to treat brain tumours. It remains however unclear whether FUS is being introduced in an ethically and methodologically sound manner. The IDEAL-D framework for the introduction of surgical innovations and the SYRCLE and ROBINS-I tools for assessing the risk of bias in animal studies and non-randomized trials, respectively, provide a comprehensive evaluation for this.

Objectives and methods: A comprehensive literature review on FUS in neuro-oncology was conducted. Subsequently, the included studies were evaluated using the IDEAL-D framework, SYRCLE, and ROBINS-I tools.

Results: In total, 19 published studies and 12 registered trials were identified. FUS demonstrated successful BBB disruption, increased drug delivery, and improved survival rates. However, the SYRCLE analysis revealed a high risk of bias in animal studies, while the ROBINS-I analysis found that most human studies had a high risk of bias due to a lack of blinding and heterogeneous samples. Of the 15 pre-clinical stage 0 studies, only six had formal ethical approval, and only five followed animal care policies. Both stage 1 studies and stage 1/2a studies failed to provide information on patient data confidentiality. Overall, no animal or human study reached the IDEAL-D stage endpoint.

Conclusion: FUS holds promise for enhancing drug delivery to the brain, but its development and implementation must adhere to rigorous safety standards using the established ethical and methodological frameworks. The complementary use of IDEAL-D, SYRCLE, and ROBINS-I tools indicates a high risk of bias and ethical limitations in both animal and human studies, highlighting the need for further improvements in study design for a safe implementation of FUS in neuro-oncology.

Keywords: Brain tumor; Focused ultrasound; Glioblastoma; Glioma; IDEAL; Neuro-oncology; ROBINS-I; SYRCLE.

Fig. 1

A world map showing the country of origin of the published original studies (n = 19) [, , , , , , , , , , , –30, 34, 40, 42, 43] on therapeutic FUS for BBB modulation. The legend at the bottom denotes the number of studies published per respective country as separate colour. The corresponding author’s country of affiliation was chosen to represent the origin of the study itself

Fig. 2

Two bar plots summarise the findings on disease type (A) and sample type (B) examined by the included published original studies on therapeutic FUS for BBB modulation (n = 19) [, , , , , , , , , , , –30, 34, 40, 42, 43]. In the second row, two bar plots summarise the findings on disease type (C) and trial stage and sample size (D) examined by the included registered, but not published, clinical trials on therapeutic FUS for BBB modulation (n = 12) [37].

Fig. 3

A A stacked pie chart summarised the findings of the IDEAL-D analysis of published stage 0 studies (n = 15) [, , , , , , , , –30, 40, 42, 43]. Each ring is denoted with an alphabetical letter and the corresponding categorical variable is denoted in the legend at the bottom of the graph. A) Were all predictable risks to patients investigated before human studies began? B) Were guidelines on best scientific practice and ethics specific to the types of study followed where available? C) Was a minimum dataset describing technical consistency made public before first-in-human testing? D) Did the outcome description address relevant parameters (i.e. Whether intended goal of procedure is accomplished? Level of difficulty of performing procedure or using device as compared to standard of care? Safety risks? Desirability of intervention?) E) Was stage endpoint reached? (Any studies that could avoid predictable risks of failure or harm to the first human should have been conducted.) The colour of the rings correlate to the legend at the right side of the graph and denote whether the categorical variables were fully addressed (“Yes”), incompletely addressed (“Partially”), or not at all addressed (“No”). B Risk of bias summary plot for non-randomized studies with a bar chart of the distribution of risk-of-bias judgments for all included stage 0 studies (n = 15) [, , , , , , , , –30, 40, 42, 43] across the domains of the SYRCLE tool, shown in percentages (%), is shown. At the bottom, an overall risk of bias, which represents the collated risk-of-bias judgements for all domains, is depicted

Fig. 4

A stacked pie chart summarised the findings of the IDEAL-D analysis of published stage 1 (excluding stage 1/2a) studies (n = 2) [14, 23]. Each ring is denoted with an alphabetical letter and the corresponding categorical variable is denoted in the legend at the bottom of the graph. A) Were full details of patient selection, technique, and outcomes and patients not selected during the time frame, and why provided? B) Were standard well-defined measures for reporting outcome and patient characteristics used? C) Was a structured reporting system used? D) Was the above information made available to peers regardless of outcome? E) Was stage endpoint reached? (Outcomes will determine whether to proceed to stage 2a.) The colour of the rings correlate to the legend at the right side of the graph and denote whether the categorical variables were fully addressed (“Yes”), incompletely addressed (“Partially”), or not at all addressed (“No”). B Risk of bias summary plot for non-randomized studies with a bar chart of the distribution of risk-of-bias judgments for all included stage 1 studies (n = 2) [3, 34] across the domains of the ROBINS-I tool, shown in percentages (%) is shown. At the bottom, an overall risk of bias, which represents the collated risk-of-bias judgements for all domains, is depicted

Fig. 5

A A stacked pie chart summarised the findings of the IDEAL-D analysis of published stage 1/2a studies (n = 2) [3, 34]. Each ring is denoted with an alphabetical letter and the corresponding categorical variable is denoted in the legend at the bottom of the graph. A) Was a study protocol made available? B) Were standard well-defined measures for reporting outcome and patient characteristics used? C) Were all exclusions reported and explained? D) Were all cases reported sequentially with annotation and explanation of when and why changes to indication or procedure took place? E) Was stage endpoint reached? (Display main outcomes graphically to illustrate the above.) The colour of the rings correlate to the legend at the right side of the graph and denote whether the categorical variables were fully addressed (“Yes”), incompletely addressed (“Partially”), or not at all addressed (“No”). B Risk of bias summary plot for non-randomized studies with a bar chart of the distribution of risk-of-bias judgments for all included stage 1/2a studies (n = 2) [3, 34] across the domains of the ROBINS-I tool, shown in percentages (%) is shown. At the bottom, an overall risk of bias, which represents the collated risk-of-bias judgements for all domains, is depicted