Background: Hepatic arterial infusion (HAI) floxuridine (FUDR) dosing is a complex, multifactorial process with weight-based dosing dependent on the fold change of aspartate aminotransferase, alkaline phosphatase, and total bilirubin relative to reference values from preceding cycles and compounded over time. Given the complexity of dosing calculations and lack of experience with this treatment in community centers, HAI is typically administered only at tertiary oncology centers with limited access for rural disadvantaged patients. We developed an online tool to automate the dosing of FUDR to broaden safe and effective administration of HAI. Methods: The FUDR dosing algorithm developed at Memorial Sloan Kettering Cancer Center was digitalized as eDoseHAI, a novel multi-layer architecture web application tool featuring JavaScript (front-end), C# RESTful API (back-end) and Azure SQL server (data storage with Splunk data lake event registration). To validate this tool, manual dosing from patients who received ≥1 dose of HAI FUDR at our institution 6/2020-8/2023 was retrospectively compared to app-based dosing. Mismatch between app-based dosing and historical manual dosing was designated as dosing errors, excluding intentional adjustments based on physician discretion. Results: Internal validity was tested by entering records into eDoseHAI from 54 patients who received a total of 370 FUDR cycles (median 6; range 1-19). Ten patients (18.5%) were found to have unintentional dosing errors (e.g., delayed dose reductions) during treatment, impacting 52 cycles (14.1%). The median cycle at first error was 3 (range 2-6), impacting a median of 5 cycles (range 3-12). Dosing errors occurred in only 11.1% of the 45 patients supervised by a senior HAI physician, compared to 55.6% of the 9 patients supervised by three less experienced HAI physicians. Dosing accuracy improved over time; among the 14 patients on active HAI therapy, only 1 had an identified dosing error. eDoseHAI was able to reliably and accurately calculate dosing for all patients. Conclusions: HAI FUDR dosing is nuanced and complex, such that dosing errors occurred even with senior HAI oncologists. eDoseHAI is a web-based application tool designed to improve accuracy and thus safety of HAI dosing. We plan to further validate eDoseHAI using external data from an international HAI consortium, and to conduct a phase II clinical trial in which our team supervises FUDR dosing by community oncologists using eDoseHAI's supervisory mode with a goal to disseminate HAI therapy to disadvantaged rural patients who lack access.