Optimisation of the Neonav Software for Accurate Catheter Localisation

Location: Brunswick, VIC

Duration: 5 months

Project Background

Central lines (catheters) are placed in veins of newborn babies in neonatal intensive care to deliver vital drugs and nutrients to patients. The placement procedure is currently done without the ability of the clinician to see where the tip of the catheter is in the vein and leads to catheter misplacement rate of up to 40%. This causes delays in time-sensitive drug delivery to the newborn, potential complications and, in severe cases, death. Navi’s device, the Neonav ECG Tip Location System, provides real-time feedback on catheter tip location, thereby reducing misplacements and ultimately complications and associated clinical inefficiencies

The Neonav system uses ECG signals of the patient to identify the location of the tip of the indwelling catheter. Intravascular ECG signals are transmitted via a saline flushed catheter to a small adaptor connected to the catheter’s proximal (external) end. The adaptor carries these signals to the device via an electrical connection where it is processed by a set of proprietary algorithms to infer the location of the catheter tip and provide visual feedback to the clinician.

Navi is currently developing a prototype that will be used in a clinical feasibility study to test the accuracy of the device. An ECG dataset annotated with x-ray-based catheter tip locations is also currently being recorded to train and test the machine learning component of the device.

Research to be Conducted

The research project involves the development and optimisation of the Neonav software, specifically its machine learning component using the existing and new ECG dataset. While Navi already has analytical solutions in place, it will be the responsibility of the intern to explore and implement new approaches that can potentially lead to improved tip location accuracy. Key elements of the project involve:

  • Reviewing, visualizing and preparing data for the machine learning application;
  • Researching and developing techniques to analyse the trends in the data;
  • Testing and validating various machine learning techniques on the available dataset;
  • Testing and refining already developed algorithms;
  • Identifying and removing redundancies from the current data recording and annotating process; and
  • Collaborating with other software and hardware engineers in the team to achieve optimal outcomes.

This is an interdisciplinary project – you will have the opportunity to work with engineers from various disciplines as well as business executives, newborn specialists and other doctors and nurses.

Skills Required

We are looking for a PhD student with the following:

ESSENTIAL

  • Machine Learning: Proficiency in using AI/ML techniques, including supervised and unsupervised learning.
  • Signal Processing: Experience using time series datasets and demonstrated mathematical/analytical skills.
  • Coding: Proficient in Python and MATLAB.
  • Collaborative Coding: Basic understanding of version control clients

DESIRABLE

  • Advanced Machine Learning: In-depth knowledge of machine learning techniques and data science tools.
  • Biomedical Signal Processing: Experience using ECG or any other physiological signals.
  • Engineering: Experience in interfacing software with hardware (microcontrollers, FPGA etc.).
  • Compliance: Basic familiarity with the Medical Device Standard IEC62304

Expected Outcomes

We anticipate that the successful candidate will develop new tools and methods that will improve the overall accuracy of inferring the catheter tip location using ECG signals. These tools will be deployed as part of the clinical prototype release and will be tested in the upcoming clinical feasibility study. The output of this work will lead to creation of a device that has the potential to create a positive impact on the lives of newborn babies.

Additional Details

The intern will receive $3,000 per month of the internship, usually in the form of stipend payments.

It is expected that the intern will primarily undertake this research project during regular business hours, spending at least 80% of their time on-site with the industry partner.  The intern will be expected to maintain contact with their academic mentor throughout the internship either through face-to-face or phone meetings as appropriate.

The intern and their academic mentor will have the opportunity to negotiate the project’s scope, milestones and timeline during the project planning stage.

Applications Close

25 September 2019

Reference

APR – 1077