Opportunity

Clinical research platforms have gained significant importance due to the critical role they play in helping contract research organizations, regulators, and sponsors gain visibility and understand the outcomes of critical clinical trial data. With COVID-19 continuing to surge in multiple regions around the globe, platforms that digitize data collection for studies not only help to bring efficiencies to the process but are also critical in ensuring clinical trial participation rates remain healthy while much of the population continues to practice physical distancing.

Traditionally, clinical studies involved patients physically visiting clinics and filling out paper surveys and questionnaires. Observers would need to trust that patients remain in compliance with the study. Observation data would be recorded on paper and then transcribed into a database for analysis. The challenges and risks with this are significant – inaccurate or misleading outcomes in clinical studies can have serious public health implications. In times of a pandemic, it can be near impossible to find patients willing to consent to regular office visits, and it may be physically impossible to do so while maintaining adequate social distancing measures.

Aventior was hired by a clinical research automation company to tackle this problem by completely digitizing the clinical trial data collection process. The vision was to help institutions unlock the power of their decentralized studies, allowing sponsors and CROs to remotely capture data from participants and sites during, in between, and in lieu of in-clinic visits – securely through one unified platform.
Aventior’s experience in developing technology for the life sciences industry would make them a leading candidate for this effort.

Approach

There are multiple components that must come together to deliver a centralized clinical study platform. The functionality and architecture need to be such that it can deliver a fit-for-purpose solution built to support the needs of any individual study.

In this case, the client was interested in utilizing serverless technologies as the base platform architecture. This would allow development teams to focus more time on the business logic and less on hosting and server maintenance – the net result being time savings and the ability to launch new features more frequently. To support this need, Aventior developed the application using open-source, technology hosted on Amazon Web Services with scalable infrastructure.

Compliance with regulatory bodies (GCP and 21 CFR Part 11) was another critical component of the platform. Due to the sensitive nature of the information being collected and stored within the platform, robust documentation and testing procedures were needed to ensure adequate privacy and security were built into the application.

With speed to market being an important factor raised by the client, Aventior utilized agile development methodologies, multi-shift operations, and AWS cloud features for fast integrations, to deliver the project within a matter of months.

Impact

With clinical trials being a key mechanism for how modern society advances its practices in healthcare diagnosis, prevention, treatment, and therapy, the impact of technological advances in this field is profound. Clinical trial data helps to inform our scientists and doctors in their decision-making, and the data itself must be accurate and representative of the individuals who will use the new therapies or approaches. Digitizing the clinical trial and information gathering process not only improves the efficiency of trials, but it also helps to improve the accuracy of trial outcomes.

Protocol compliance by participants is an important aspect of clinical trials. Without this, outcomes may be misleading, and results can be skewed. Electronic reminders/alerts, context-sensitive messaging, and compliance feedback help to ensure participants stay in compliance with program protocols.

Patients using ePRO reportedly demonstrate protocol compliance as high as 94%, compared to 11% with paper.[1]

Transcription errors are a risk with any manual paper-based process, and the impact of errors can be severe when dealing with clinical trial data. Paper-based studies would require site personnel to manually transcribe data into the trial management system.

With eCOA, any inconsistencies, missing data, or data quality issues can be caught and corrected in real-time.

Regulatory bodies have strict recommendations around data collection techniques and methods to ensure the data collected is reported according to protocol requirements. eCOA inherently meets regulatory quality guidelines due to it being Attributable, Legible, Contemporaneous, Original, and Accurate (ALCOA).

Adoption of eCOA can help to reduce the number of queries by regulators regarding the capture of clinical trial data. 

 The overall user experience for participants improved drastically both due to increased accessibility and convenience. Whether patient-reported observations or clinician-reported observations, participants can avoid unnecessary travel by leveraging electronic surveys and virtual visits.

Patients leveraging eCOA saw significant savings in personal time that they would otherwise spend on visiting clinics and doctors. 

The improvements in user experience contributed to increases in retention rates. Participants engaging in studies using eCOA were more likely to complete the study due to reduced frictions throughout the entire process.

Patient retention improved by 30% on average as a result.

 These factors ultimately helped to improve the overall efficiency and effectiveness of studies, making eCOA the logical approach for future studies to come.

Researchers have experienced a reduction in clinical trial time and costs, leading to both improved economics and speed.

 By working with Aventior, the client has been able to deliver on their vision of helping institutions unlock the power of their decentralized studies, through a secure platform that digitizes clinical studies data collection and provides outcome visibility in real-time.

[1] Stone, A. A., Shiffman, S., Schwartz, J.E., Broderick, J.E., Hufford, M.R. (2002). Patient non-compliance with paper diaries. British Medical Journal, 324, 1193 – 1194.

Opportunity

Digital pathology driving medical breakthroughs and a new set of challenges

Digital pathology is rapidly becoming the new standard of care, thanks to recent approvals from the Food and Drug Administration (FDA) for applications such as primary disease diagnosis.

Regarded as the bridge between science and medicine, pathology involves teams of scientists and medical staff studying biological samples to understand drivers of illnesses and diseases. It plays an important role in investigating the effects of new drugs as well as understanding the characteristics of viruses and bacteria.

The use of modern technology in pathology has not only improved the efficiency, precision, and granularity at which biological specimens can be captured, it now enables a more automated means for how the metadata associated with specimens is extracted, analyzed, and stored. Computer algorithms can drastically accelerate our ability as a species to identify, prevent, and treat factors in our environment that can harm us.

“This convergence of advanced imaging, automation, and powerful analytics like natural language processing (NLP), machine learning, and artificial intelligence (AI) in healthcare and life sciences organizations are bringing together the tools needed for scientists and clinicians to unlock medical breakthroughs at a pace like never before,” says David Dimond, Chief Innovation Officer Global Healthcare & Life Sciences at Dell Technologies.

Advancements in digital pathology have create a new set of challenges however as researchers begin to adopt new digital workflows. The shift to digital workflows means specimens that were captured using older technologies would require conversion into a digital format in order to remain useful.
Aventior’s experience in developing and implementing technology for companies in the life sciences industry made us a perfect fit to solve the challenges faced by a Massachusetts-based biotechnology company developing gene therapies for severe genetic disorders and cancer.

Over the course of the years, the company had collected tens of thousands of biological specimens as part of their research. Tissue-based studies generate large amounts of histology data containing biological information in the form of imagery and metadata. These digital pathology slides are labeled using text for their identification, and older technologies used printed or handwritten labels for specimen labeling.

As such, it becomes virtually impossible for pathology teams to quickly search and find specimens they are looking for or categorize them based on tissue, disease, markers, and other attributes. Certain specimens can be extremely difficult to come by, and the ability to access archived specimens is critical in this field.

Aventior worked with the client to address this challenge by developing a solution that utilized a combination of techniques that would allow them to efficiently capture, store, and access biological specimens for analysis.

Approach

AI used in label extraction for digital pathology

With tens of thousands of slides stored in various formats and handwritten identification, extracting and organizing the information efficiently would not only require a series of steps, it would also involve the use of image processing techniques, artificial intelligence (AI), and optical character recognition (OCR).

Based on the requirements at hand Aventior developed a solution which would include four key steps:

1. The first step involves extracting label text from files stored in Mirax file format. It scans all the data files (.dat) to find the data file that is associated with the label file. The associated data label file is converted to a raw PNG image.

2. These raw PNG files are then process for better text extraction which includes image rotation, image enhancement and image thresholding modules. The platform would also perform the morphological transformations like erosion and dilation on the text if needed.

3. The text from the processed image would then be extracted using OCR techniques.

4. The extracted text would then be appended in the user defined structure data format, stored in a database with search capabilities, where a manual validation may be conducted to verify the quality of the extracted data.

A proof of concept was first developed to test the approach. The test involved the processing of 1000 slides with an Excel file as the output. Once validation of the platform had been completed, additional functionality was developed to support the output of the data directly to an SQL database.

Using this approach, Aventior was able to design, develop, and launch the platform to the client within the time span of a couple of months.

Impact

More value and efficiency from existing specimens

Aventior’s AI-based automated label extraction platform quickly allowed the client to enhance their research capabilities. Pathology teams saved time by avoiding having to manually review specimen slides, which meant more time could be spent analyzing data and gaining important insights.

Processing times were reduced by 80% compared to the manual process.

In the manual process, the information would be stored in disparate locations, making it difficult to identify outliers and trends. Through the use of the platform, data is now being stored in a much more harmonious manner, enabling teams to find and analyze data faster.

Data harmonization helps users to identify outliers and trends in a much more efficient manner.

Another benefit that had emerged was improved accessibility to the data, as researchers no longer had to be in the same physical location as the slides to access the information. This allowed pathologists to extract additional value out of the archived specimen data as information could be shared more rapidly across a wider range of applications.

Easy search and access of the datasets support further research and analytical activities.

At Aventior, we believe the use of AI in healthcare will continue to accelerate medical breakthroughs. As more healthcare centers continue to adopt the use of digital pathology, one can only imagine what new capabilities will be unlocked in future years to come – and that is why our company is committed to supporting the adoption of AI and machine learning in healthcare and life science industries.

Opportunity

Ability to integrate a configurable Analytics Dashboard within the portal.

A dashboard allows viewing insights and understanding performance at a glance. The insights that we view on the dashboard are based on carefully identified key performance metrics as per an organization’s objectives and processes. Dashboards are a reporting tool that helps businesses in monitoring their performance and make informed decisions regarding their business.

An analytics dashboard is a reporting tool that helps in analyzing huge volumes of data, that allows investigating trends, get deeper insights and forecast outcomes. Therefore, the data that is used by the analytics dashboard has to be up-to-date and accurate.

It is rightly said by the former CEO of HP, Carly Fiorina that, “The goal is to turn data into information, and information into insight”.

The raw data is converted into information and the dashboard presents this information that can be consumed by the user. The user can use the information to study the performance and get in-depth insight to take calculated action. If management can make informed decisions then they can focus on areas where attention is required without any guesswork.
Every organization has its own set of objectives and goals to achieve. An analytics dashboard helps in understanding and planning how to achieve their goals. Also, the company must get to view their data more interactively, have the ability to drill-down further to get more clarity and identify trends.

Aventior has extensive experience in developing technology for the life science industry. A clinical research company hired Aventior to develop a configurable analytics dashboard to gain insight, view key performance indicators (KPI), and report on the site/study/participants.

Approach

The client has an extensive amount of information vital to the customers. Aventior had to develop a dashboard that provides a mechanism to control the display of the new study dashboard for each product as well as customer instance with answers to relevant business questions. The dashboard should also allow the user to configure widgets of visualization across various KPIs. To integrate these functionalities, the technology used by Aventior is Vue.js for the front end, which is an open-source JavaScript framework for developing user interfaces, and for the backend, JAVA integrated with Node.js.

The dashboard developed was in two phases:

Phase 1.0 – Base-Standard Dashboards

Phase 2.0 – Pro-unlock additional dashboards/configurable dashboards

Aventior used the calculation code for each priority grouping KPIs. Aventior team tests and fixes all the KPI visualization bugs and deploys the code to stage/UAT/Prod environments.

Impact

Developing an analytics dashboard involves creating a user-friendly platform, allowing users to configure widgets of visualization, and representing KPIs in a glance. Aventior developed a dashboard that allows users to configure widgets of visualization based upon multiple roll-ups and slices of data across various KPIs. The platform provides a mechanism to control the display of the new study dashboard for each product and customer instance. The users with appropriate access rights to use the portal can view the dashboard. They can view the key performance indicators (KPIs) through interactive visualization, that is displayed on a configurable dashboard. The users can gain insight and reports of their study, site, or participants. The users can configure the types of visualizations, display the visualizations, and download the data generated from the Metrics Dashboard KPIs.

Aventior has developed a configurable dashboard that gives users the ability to access a group of KPIs. The KPIs are organized around a few relevant business questions that the dashboard metrics address. The dashboard groupings that address various concerns are as below:

1. Overall Study Executive Dashboard: Does it predict the health of a study?
   A grouping of high-level metrics related to enrollment, compliance, and data completion is represented by this dashboard. It provides insights such as:
   • Determine the expected completion date for all activities
   • View in a glance enrollment curves by country and site
   • Identify daily activities that cause non-compliance
2. Study Enrollment Dashboard: Does it display target achieved and forecast enrollment goals?
   This dashboard represents a grouping of detailed analytics that represents enrollment trends. at a glance, the below trends can be viewed both country-wise and site-wise:
   • enrollment curves
   • site activation and first visit progress
   • eConsent comprehension quiz metrics
   • review screen failure ranking
3. Activity and Overall Engagement Dashboard: Does it help find out if any user is struggling with any particular activity areas in the technology?
   This dashboard represents a grouping of detailed analytics representing engagement trends. This includes:

• • Identifying any area in particular with different engagement levels by site and country
  • Find if telehealth visit durations are adequate for the study
  • If users are spending a consistent amount of time in the app by site and country
  • Identify statistical impact in activities and training across countries and sites

4. Study Compliance Dashboard: Does it identify current or predicted compliance issues?
   This dashboard represents a grouping of detailed analytics representing potential compliance issues and trends. It helps identify:

• • Daily activities that are causing non-compliance
  • Data collection completion metrics to see if data entry is lagging

5. Data Management Dashboard: Can it identify the status of data collection, cleaning, verification, and approval?
   This dashboard represents a grouping of detailed analytics representing data management statuses and trends, such as:

• • Activity completion percentages
  • Activity completion times
  • Issues and trends involving data queries
  • Timeliness of queries being closed
  • Timeliness of activities and forms being entered, verified, approved, and signed off

6. Study Completion Dashboard: Can I view trends that may impede study completion goals?
   This dashboard represents a grouping of detailed analytics representing completion trends. They are:

• • View the expected completion date for all activities
  • Spot discontinuation trends
  • Review missing data and query trends by site and overtime

Aventior developed an Analytics Dashboard for the client that is integrated into their portal. The configurable dashboard answers all relevant questions which arise after the study configuration.