A few years ago, a relative of mine was diagnosed with Breast Cancer. When I visited her after her surgery, she was lost - chemotherapy, treatment, weakness and fear took a toll, resulting in her secluding herself. - and only relied on the doctor's words for the entire course of treatment.

Unfortunately, she was diagnosed with cancer again within a year and had to face the same cycle once again.

When I reached out to the doctor, the doctor shared about the challenges in prescribing medicines and tracking a particular patient's health progress. He also noted the fear every cancer victim faces throughout the treatment cycle as patients are prone to falling for general misconception - due to a lack of awareness and the lack of a support group that have gone through the same thing. Without a good support mechanism, patients tend to receive a lot of unsolicited advice and get confused in the process.

Considering what we learnt from this experience and others, we felt there was a large gap in treatment -

  • Patients found it stressful to reach out to Doctors
  • Patients lacked a good support mechanism that could help them go through the day to day pains of treatment, keeping track of medication, not being able to talk to someone who has experienced the same.
  • Doctors found it hard to wade through large amounts of past data for each consultation, each visit was a fresh start in most cases.

To bridge this gap, we felt the Patients needed a way to communicate in an easier way that wasn't intrusive to the Doctor's hectic schedules, and didn't require a hospital visit. Patients also needed a way to feel supported through a community of people that have actually fought off cancer, and also have a single source of valid and reliable information - crowdsourcing from experts and events. Doctors would also benefit from having the ability to view suggested medicines through cognitive and machine learning predictions.

This saves time, bridges the gap between patients and doctors. Doctors can access information about suggested medicines (derived from algorithms). Doctors can assign daily fitness and diet goals online and this application will become a one stop health management system for doctors, and provides support for the patient throughout the treatment cycle.

What the application does

-This app lets the doctors manage the patient's medical history, irrespective of the hospital - maintaining scans and comments in one location -This app lets the doctors prescribe medicines in a more informed way with machine learning suggestions. -This app enables seamless, non-intrusive communication between patients and their doctors, -This app enables complete monitoring of patient by the doctor throughout the treatment cycle

How we built it

Using Appian (a low code business process management platform - mobile app friendly), we have built workflows to

  1. Book an appointment online (Zoom app integration to set calendar meetings for online consultation)
  2. Search for Hospitals nearby to book an appointment (Google Maps integration to find hospitals nearby)
  3. Store scans and reports to transfer them to doctors (Appian serves as document repository)
  4. Non live chat feature has been enabled between doctor and patient to resolve patient's queries.
  5. During the treatment cycle, doctors can monitor progress of a patient's health using AI/ML prediction results
  6. Doctors can prescribe medicines and chemo treatment sessions based on ML suggestions
  7. Appian processes automatically send daily tasks to patients to notify about the medicines and diet
  8. Also, Fitbit integration helps doctors monitor a patient's daily status (diet, fitness and sleep)
  9. This application is available in any language (Google Translate Integration)

(Please contact us for credentials to try our web applications)

Challenges we faced

  1. Creating an AI algorithm
  2. Integrations with Fitbit and Zoom were challenging

Accomplishments that we are proud of

We always wanted to solve a real-world problem and to build a simple healthcare solution that would bridge gaps. This app could be very useful to hospitals, doctors and patients as it adds great value to their lives.

What we learnt

We learnt about the power of Machine learning (AI), the healthcare domain and the hidden challenges faced by patients.

What's next for iFlag - I Fight Like a Girl

We would like to experiment with more data so as to train our model and we can progress better with the machine learning aspect of this application. We would also like to understand and address more pain points the doctors and patients face.

Full Video:

For full application demo :

Built With

+ 29 more
Share this project: