Dextro

Data-scraping tool for interpreting physicians and healthcare professionals

Product Background

Workload automation for day-to-day routine activities for interpreting physicians is difficult without the assistance of Robotic Process Automation (RPA). Such software decreases the need for manual re-input of the same data across different applications, thus increasing speed and productivity for reading the studies.

To fill in the gaps, our client commissioned us to build and integrate a data-scrapping solution to help radiologists acquire total visibility across different PACS systems. As a result, specialists receive one unified worklist with proper task prioritization retrieved from different exam providers.

Challenge

Our main task was to develop a mechanism that minimizes the time doctors spend on repetitive tasks. For example, searching through different PACS systems/worklists to find a required study or manually organizing studies existing in different applications to comply with overall priority across them. For that purpose, we had to enhance the current doctor’s workflow with RPA which emulates human actions by interacting with the digital systems and scrapping the data. Eventually, we created robots that were ready to merge different data and push that into a unified worklist.

Solution

We created a set of robots to leverage the existing infrastructure without disrupting the related systems. In short, it uses the interface to capture and manipulate data just like humans do; however, instead of taking breaks to eat and sleep, it works around the clock, 24/7.

Robots can:

  • log into accounts with given credentials
  • find required studies
  • extract content from required worklists
  • refresh deliverables after each session
  • control data amendments in a sourcing system
  • operate fully in the background

Results

Our team has built data-scraping robots, suitable for multiple systems, that can automate repetitive and routine tasks. This software was developed from scratch and seamlessly integrated into radiologist-related workflows.

Finally, with the help of Dextro, doctors are free from spending countless hours and resources interpreting worklists thanks to this accurate and efficient automation technology.

TECH STACK:

  • FRONT-END:
    .Net Core

  • BACK-END:
    .Net Core
    WinAppDriver Selenium Web Driver
    DB:
    MS SQL

  • CLOUD:
    AWS

ITR Software

Patient Flow and Bed Management Solution

Product Background

The performance of many hospital departments depends on the way beds are managed across wards. Our client has developed a web app that allows a department to easily handle, manage and reorganize bed requests. The system increases usage efficiency of beds and minimizes any potential issues between patients who share the same hospital room. 

Challenge

In order to deliver better care and empower visually-impaired staff with automated hospital bed allocation, our client decided to overhaul and rewrite the app’s entire front-end. 

As the existing front was outdated and not user-friendly, our mission included:

  • Creating a brand new UX/UI design;
  • Updating user-effectiveness & job satisfaction;
  • Adjusting the operational efficiency;
  • Enhancing the patient journey;
  • Enhancing the accessibility design (contrast mode, font size, light & dark color scheme).

Solution

In order to gain a competitive edge regarding bed management software, our team completed: 

  • An investigation of national regulations about bed assignment;
  • Detailed business analysis;
  • New responsive design with an intuitive interface; 
  • Mock-ups with user-flow & multiple screens; 
  • Customizable user dashboards; 
  • Calendar for scheduling requests;
  • Advanced search engine for filtering & sharing personal lists.

The software covers all necessary information about beds: whether they are dirty or clean; which rooms they are placed in; and patient-related information, such as address, relatives, insurance, etc.

Results

The new intuitive interface guides the user all the way from the patient’s admission to a hospital, until final discharge. These changes boosted staff efficiency by saving time and allowing management to meet hospital performance targets.

With a graphical representation of wards and a list of the beds, it becomes easy for the bed management staff to carry out the allocation process. Information is updated in real-time, allowing a team to omit the manual counting process and improve turnover rates. Disabled users also feel more comfortable with the accessibility design when enhancing patient coordination, contributing to the hospital’s sound operability. 

TECH STACK:

  • FRONT-END:
    Angular
  •  

Project Ipsilon

App for cognitive testing and training

Product Background

MCI (mild cognitive impairment) and signs of early dementia are hard to detect; however, studies show that playing the piano has the ability to highlight even the slightest cognitive abnormalities.

Playing the piano involves multiple sensory processing, comprehension, quasi-simultaneous decision-making, and action execution. In short, it is a sure-fire way to analyze and evaluate brain functions and train minds. In order to test and prevent cognitive disorders, our client (a musician) came up with the idea of building a piano emulator from scratch.

Challenge

In order to build a piano emulator app that could detect and calculate the probability of developing cognitive abnormalities associated with MCI and early-stage dementia, the emulator had to be:

  • Fast and accurate, with gamified cognitive checkups that fit the clinical workflow;
  • Suitable for assessing pre-clinical, early dementia and MCI;
  • Operable by a non-specialist.

Solution

The app was released with the following features:

  • Visuospatial and motor encoding;
  • Time-stamped finger responses;
  • Audio cues;
  • Integrated the tool for different PACS archives/VNAs compatibility;
  • An algorithm that collects user-response and analyzes data;
  • Integrations with EEG and eye-tracking;
  • Recording history;
  • Data export;
  • GDPR and HIPAA compliance.

Results

This app evaluates executive functions, such as inhibition control, attention, multisensory memories, and various brain-region activities. In this way, the software acts as a dementia prevention tool, contributing to remote care for cognitive monitoring. As for now, our client is looking for opportunities to collaborate with Philips as their headsets could enhance app performance and function.

This software is expected to launch as a medical device in the EU at any moment.

TECH STACK:

  • FRONT-END:
    Angular
  •  

  • BACK-END:
    .Net


  • CLOUD:
    AWS

PACS Harmony

Radiology Workflow Management Tool

Product Background

The product allows hospitals to automate the workload and distribution of studies for interpreting radiologists. To meet the SLA time frames, the app’s AI engine defines exam priorities, locates qualified doctors (based on their preferences), and assigns a specific exam to a particular expert. The software balances the workload so that all radiologists receive the correct amount of work they are committed to cover.

Challenge

The main difficulties in the previous version of the app, which became the source of customer disappointment, were poor operational performance combined with a confusing UI. Medium to large hospitals with a significant study turnover rate reported that slow app responsiveness and overall balancing inefficiency were affecting the number of medical exams reviewed. Following some fruitless attempts with other teams to redesign the software, the client finally turned to us to help improve the overall performance right away.

To improve impending faults and to preserve existing customers, we set out to:

  • Find and fix the reasons linked to the app’s slow performance;
  • If needed – change healthcare app architecture to raise performance;
  • Verify the studies distribution algorithm and implement the desired business-logic elements;
  • Significantly decrease the capacity of the infrastructure required to use the application;
  • Improve app UI to make it more responsive and user-friendly.

After putting out the fire, we directed the next flow to complex tasks.

  • To build an integration with the majority of existing dictation systems and image viewers;
  • To gain a competitive edge and remain independent from existing market leaders (Philips, Agfa, etc.);
  • To increase patient satisfaction and shorten the time of studies’ review and finalization.

Solution

After the execution of highly detailed performance tests, our developers reviewed all API calls and database requests and challenged every query’s adequacy.
As a result, we tightened data retrieval and increased the volume of acquired data every step of the way. A large portion of data was cached in order to speed up access to repeatedly queried but rarely changing medical data. Afterward, we implemented the composite pattern approach to enable complicated and nested filters to be compounded, allowing for the instant extraction of data.

We also:

  • Crafted UI / UX for both doctors and hospital admin requirements;
  • Completed integration with multiple image viewers/dictation systems;
  • Added a flexible and robust load balancing mechanism for real-time distribution;
  • Integrated the tool for different PACS archives/VNAs compatibility;
  • Created a mechanism for scheduling systems interoperability;
  • Created an internal audit mechanism to control data access (for HIPAA compliance);
  • Developed a reporting tool for physician performance tracking.

Results

After initial months of working around the clock, the AI engine’s performance and API back-end responsiveness has improved significantly. Presently, the initial infrastructure can efficiently support hospitals with up to 10 million studies per annum. Furthermore, the business-logic of studies distribution was challenged and fixed throughout. Together with UI updates, these achievements lowered the overall page responsiveness to less than one second. Our collaboration has lasted for over 2 years and continues successfully as of the time of writing of this case study, making it possible to polish the product with innovative and competitive features.

TECH STACK:

  • FRONT-END:
    ReactJS

  • BACK-END:
    .Net Core

    Net Framework
    RabbitMQ
  • DB:
    MS SQL

  • CLOUD:
    AWS

Astarte Medical

Data-driven diagnostic and predictive app for improving infant outcomes.

Client Background

Astarte Medical is a precision nutrition company that turned to us to build software based on proprietary predictive analytics. The solution is meant to improve outcomes for preterm infants with a suite of digital tools and diagnostics.

Challenge

We had to build a forecasting & tracking web application for the infants’ treatment plans from scratch.

MAIN COMPONENTS MEANT TO BE:

  • AI-based suggestions for feeding time, amount, and constituents
  • Graphs and tools to monitor feeding
  • A thorough interface to track infant growth.

Solution

To standardize feeding, optimize nutrition, and quantify gut health of preterm infants with our app, we implemented:

  • Integrations with various protocols to suggest feedings for babies based on the clinical indicators, growth speed and other historical data (like previous feedings)
  • Tracking of the protocol suggestion modifications
  • Central identity server
  • Rounding report tab to show consolidated information about the patient
  • Analytics (with charts) for organization performance metrics visualization
  • Epic EHR integration
  • Ability to download data/reports.

Results

Core to Astarte Medical is their comprehensive and proprietary dataset, which integrates feeding protocols, microbiome profiles, and clinical information. We synchronized it with the web application making it generate actionable suggestions in the form of a decision tree.

  • Infant parameters are logged into the app which measures the Protocol compliance for tracking & optimizing their nutrition.
  • Decision tree – AI-based platform that suggests a diet based on the lessons learned from the previous cases

TECH STACK:

  • FRONT-END:
    Angular

  • BACK-END
    .Net Core

  • DB
    .PostgreSQL

Medical doc exchange

Auto-faxing and information exchange for healthcare organizations.

Product Background

The Client is the leading provider of enterprise-wide document delivery solutions for the healthcare industry. Their product automates sending high volume reports such as lab results, a solution for hundreds of top hospitals.

Challenge

The product was powered by Microsoft Silverlight technology / plugin that, as the company revealed, won’t be supported commencing next year. So, the main goal was to update the existing web application with the latest technologies and ensure a seamless transfer.

ADDITIONALLY, WE NEEDED TO:

  • Design a web interface for FAX usage in organizations
  • Create, send, manage recipients and statuses of FAX deliverables
  • Provide security of the application’s data avoiding legacy technologies.

Solution

To allow delivering information more flexibly, we:

  • Recreated a web application using Angular and C#
  • Integrated part of the old Silverlight app into the new one to support real users experience
  • Provided backward compatibility with the early app to allow smooth transfer
  • Applied reverse engineering of the previous app to facilitate the migration of FAX functionalities.

Results

Our solutions helped to update the software and remove technology disruptions that caused lost-in-transit paper reports or separate prints occurrences. Smooth documents management positively affects patient care allowing health providers to focus on diagnostics and treatment.

TECH STACK:

  • FRONT-END
    Angular

  • BACK-END
    .Net Core

  • DB
    MS SQL

Ophardt Hygiene

UI/UX design and interface for the IoT platform that helps tracking provision on hygiene supplies in hospitals.

Client Background

Our client is a dispenser manufacturer that addresses hospitals’ needs with sensors that measure the dosage volume and the timestamp of hand disinfection. They send this data wirelessly through the IoT platform and run analysis programs to ensure compliance with the rules.

Challenge

The former product’s interface was in production for 8 years and required significant improvements. The manufacturer turned to us to develop an interactive smart solution to reform and monitor hand hygiene and eventually reduce hospital-acquired infections.

CHALLENGES:

  • To build a unique and customized web interface for IoT platform
  • To make the web interface user-friendly and adjustable for detailed statistical data checking
  • To create a cross-platform mobile app synchronized with a web app.

Solution

We reworked the entire front-end part of the application using the latest technologies to provide stability, a mature interface, and better user support.

FEATURES IMPLEMENTED:

  • Custom UI/UX and web interface
  • Configurable reports based on custom IoT parameters
  • Organizational and location structure supervision
  • Patient Days management system.

Results

The development of the fundamental part of the product took about 18 months. Now we’re adjusting some UX features. In the meantime, the client engaged us with a related project – building a mobile applications that directly collect data from dispensers through NFC. It expects to facilitate and speed up the work of hygiene specialists in the hospitals.

TECH STACK:

  • FRONT-END:
    Angular

  • MOBILE:
    Android
    iOS

  • BACK-END:
    Java