Semi-Automation of Keratopathy Visual Acuity Grading of Corneal Events in Belantamab Mafodotin Clinical Trials: Clinical Decision Support Software (Preprint)

BACKGROUND Belantamab mafodotin (belamaf) has demonstrated clinically meaningful antimyeloma activity in patients with heavily pretreated multiple myeloma. However, the drug is highly active against dividing cells, which contributes to off-target adverse events, particularly ocular toxicity. Investigators or providers routinely use changes in best corrected visual acuity (BCVA) and corneal examination findings to determine Keratopathy Visual Acuity (KVA) grade to inform belamaf dose modification. We sought to model and translate the complexity of the ophthalmologic examination using the KVA scale into a mobile application that is easily applicable to patients presenting with ocular toxicities. OBJECTIVE We aimed to develop a semiautomated mobile app to facilitate the grading of ocular events in clinical trials involving belamaf. METHODS The paper process was semiautomated by creating a library of finite-state automaton (FSA) models to represent all permutations of KVA grade changes between baseline and current BCVA readings. The transition states in the FSA models operated independently of eye measurement units (eg, Snellen, logMAR, decimal) and provided a uniform approach to determining KVA grade changes. Together with the FSA, the complex decision tree for determining the grade change based on corneal examination findings was converted into logical statements that provide accurate and efficient computation of the overall KVA grade. First, a web-based user interface, conforming to clinical practice settings, was developed to simplify the input of key criteria for overall KVA grading. Subsequently, a mobile app was developed that included additional guided steps to assist in clinical decision-making. RESULTS The app underwent a robust Good Clinical Practice validation process in alignment with GSK standard operating procedures, and the outcomes were reviewed by key stakeholders, our medical lead for belamaf, and the systems integration team. The time to compute a patient’s overall KVA grade using the Belamaf Eye Exam (BEE) app was reduced from a 20- to 30-minute process to less than 1 to 2 minutes using our semiautomated KVA computational framework. The BEE app was well received, with most investigators surveyed selecting “satisfied” or “highly satisfied” for its accuracy and time efficiency. Based on current US Food and Drug Administration and EU standards, the BEE app is considered a nondevice clinical decision support software. CONCLUSIONS We conclude that our semiautomated approach provides for an accurate, simplified method of assessment of patients’ corneal status that reduces the number of potential errors and more quickly delivers information critical for potential belamaf dose modifications related to ocular changes. The app is currently available on the Apple iOS and Android platforms for use by investigators of the DREAMM clinical trials. Moreover, this mobile app could extend to the clinic as a tool to support healthcare providers in making informed belamaf treatment decisions for their patients.