GCI-2019 : New Ideas from GCI Students to improve OpenMRS

Community Google Code-in
1

Hi Students,

You can use this thread to post your accepted ideas and thoughts to improve the OpenMRS in several ways!

Mandatory: First, you need to claim one of these tasks from GCI dashboard:

  1. Suggest a new feature to OpenMRS

First Submit your work to the GCI dashboard. Once your mentor reviewed and approved, then only add your ideas here. You should mention the approved Mentor name in the post here.

We would like to keep only the final version of ideas here (Having conversations or discussion for an idea in this thread may reduce the impact on other ideas here) So posts without approved mentor name will be deleted to reduce the number of posts.

Thanks.

3 Likes
2

There are two features that I feel, if included to OpenMRS, would make it a lot more productive. The comparison has been made between OpenMRS and two other Electronic Medical Records Softwares, namely eClinicalWorks and 75health, both of which have these two functions integrated in their softwares. The first feature I feel should be added is ePrescriptions. ePrescriptions is the process of generating a prescription electronically and sending it directly to physicians and other medical staff. Since the main purpose of EMRs is to generate records and charts at the clinics, I feel that ePrescription would make the process a whole lot quicker and versatile. Moreover ePrescribing reduces the chance of error due to handwriting which could sometimes lead to the wrong drug being dispensed. The second feature I feel should be added is Voice Recognition. This will steer the productivity in a very upward direction since it quickly helps identify the physician speaking. This will help in saving time as Voice Recognition can be provisioned to exercise dynamic, command-based responses. So this eliminates the need to write complete sentences. It will also save money as it will completely eliminate the need for any sort of physical transcription, easily saving the average physician $30,000 to $50,000 a year. Addition of these features, in my opinion will bring about a very positive outcome in the software and will make life easier for a lot of people.

So, elaborating on the idea of ePrescriptions, there can be different approaches to making ePrescriptions. One can use online ePrescriptions like Practice Fusion. It can either be used directly by redirecting to their page or if possible somehow, get their system integrated into the OpenMRS software itself, although that is a rather tedious process and it would be better to use their ePrescription facility directly through them. The other way could be to somehow create your own ePrescription system in the software by making use of databases. The ePrescription facility of Practice Fusion is quite popular actually and that is one source that can be considered.

This task was approved by @suthagar23

2 Likes
3

Through the modernization of technology, the appeal these devices have on the user has increased dramatically. The reason for this increase can be substantiated to the overwhelming benefits it provides to the user. One device that has captured the attention and has appealed to the public is the invention of wearable technology, that is the smartwatch. Modern smartwatches have the capability of reporting medical data to the user such as heart beat, distance walked, amount of sleep, etc. Though this alone has had a substantial impact on countless people across the globe, the incorporation of this data with data from medical reports gathered in the OpenMRS database can further help people around the world. For example, using data from medical reports regarding cholesterol level, and other heart related data and combining this information with the continuous pulse reading from a smartwatch, OpenMRS can suggest to the user how they should alter his or her behavior in order to maintain the standard pulse level. Additionally, the advantage of integrating the smartwatch data with OpenMRS is that the information can be conveniently relayed to specific doctors. Through this, doctors will have more information regarding the patient’s vitals and be able to respond with more precise prescriptions or advice. Additionally through the implementation ofMachine Learning (ML) in the OpenMRS system, the system can automatically give advice and predict the probability of contracting a particular disease given data from both reports, and smartwatches. Thus, this type of behavior hasn’t been incorporated in a system such as OpenMRS, rather has been subjected to individual applications focusing on either aspect but not both(e.g, Fitbit for smartwatch data, and GNU Health for reports). The combining of these two factors could relay far more critical and accurate information to the user in less time

2 Likes
4

This was a response to the task: Using Artificial Intelligence to improve OpenMRS.

To facilitate easy retrieval of information from reports, OpenMRS should start by creating an easily readable framework for patents to access their data. By training an AI model to easily search for specific information from multiple reports, and displaying these in an easily readable format on their app, Patients won’t have to open and check multiple reports for information. For example, one could train a model to seek out information for insulin by looking for the keyword “Insulin” and finding the value associated with it. If this was automatically done for each report and displayed in a table format, Patients wouldn’t have to waste time comparing their insulin levels from each report.

Additionally, OpenMRS can use AI to make predictions regarding the data. For example, using data such as cholesterol levels, and insulin level (high level of insulin can cause exacerbated heartbeats), and personal info such as age, weight, height, OpenMRS can use the data from these reports to calculate the likelihood of a person suffering from a cardiac arrest. Through predictive analysis, doctors will be able to know beforehand how likely the patient is to get a particular disease and do a more in-depth analysis to corroborate the predictive analysis. Through implementations such as these, it not only allows for easily accessible data, but the AI model also allows to create predictions on the chance of contracting a particular disease

Another way OpenMRS can use AI is to use Optical Character Recognition (OCR) to convert existing paper reports into readable digital files. OCR is a method in which one uses the camera on their phone to take a picture of documents and it’s then converted from handwritten text to a styled text. The advantage of this is that if there are handwritten notes by doctors for their patients, OCR can convert this text and store it in a database. This way patients will be able to view their notes all on the OpenMRS application without having to scour for their handwritten notes that could be potentially lost.

3 Likes
5

OpenMRS is a reference application that helps in designing a personalized medical record system, without having any knowledge of programming. However, OpenMRS is not the only medical record system around the globe. The other medical record systems are:-

Practice Fusion Epic Kareo Greenway NueMD eClinicalWorks Allscripts

Well, I researched the above-mentioned organizations and this helped me figure out a few features for OpenMRS so that it could much better.

I would like to mention that right now, none of the Medical Record System, provide Bed Management. By Bed Management, I mean that there should be a portal where it could be entered that whether the patient is asleep or has he/she woke up. It should also include that what all, the support staff has to do for the bed (including cleaning, changing bedsheet, etc.) It should also include that whether the patient has received food or not. Such a system would help the staffs to work faster and even control the management information.

OpenMRS right now has a demo system available, but I believe that it should be more than just demo. It could include a proper system running on a 14-day-trial version in the whole building of the hospital, clinic, infirmary etc. This trial should be free, so that more and more organizations can try it out and then hopefully move onto setting up the whole system.

As per my research, eClinicalWorks include a voice recognition system in their medical record system. If OpenMRS includes such a feature in their systems, then it would become easy for the user to run the system as he/she will just have to speak up the command and then the system will do it. I consider that it would take up time to create such a feature but this is crucial these days.

OpenMRS can hire developers from different nations so that the medical record system can be made multi-lingual with languages like Polish, Italian, Hindi, Greek, Spanish, etc. This would help OpenMRS have a stronger control over regional markets.

OpenMRS’s system can include the feature of Handwriting Recognition which is included in eClinicalWorks. This would help more and more people, growing their attention towards OpenMRS’s Medical Record System.

Well! These are a few features, from my side which I believe should be included in OpenMRS to make it spread its wing more…

This task was approved by @mavrk

2 Likes
6

These are the 2 features i feel OpenMRS needs to stand apart in the crowd of MR systems :-

  1. Suggestions and alternatives - this is something no other MR system provides, the Idea is to suggest simple remedies or common medicines (which comes without any side effects) to the user directly by the platform using AI when the user gives details about his/her diagnosed disease foe example - SORE THROAT – gargle with salt water also there are many instances when a prescribed medicine is the one which is not available in most of the medical stores in locality and then patient faces problems finding alternatives to that medicine salts for such a situation the feature of suggesting alternative medicine to that one after entering its name would be a huge help.
  2. Medicine Reminder – this is an original one which is not inspired by any other platform, this is something which I personally have felt the need of a reminder to take medicine, in this world where life is very difficult and short term memory loss and stress is very common it is natural that one may forget to take a particular medicine therefore not completing the course prescribed which can be lethal so in such a situation there is a need of a system which on its own provide a gentle remainder on our phones or desktop to take the medicine prescribed by the doctor (after registering the prescription on the record system of course) for example – Reminder (take medicine for fever) 4:00 pm or just a notification saying this may be sent to the device.

This task was approved by @athira

1 Like
7

Firstly, I am Nayan. Being a part of OpenMRS I felt very happy. OpenMRS is overall good but in comparison to other Electronic Medical Record Systems which I read about like eClinicalWorks, NueMD, iPatientCare etc., it needs some improvement. I want to suggest some improvements, which re written below :

  1. As I read, I want to suggest that OpenMRS should have a system of e-reminders. For example, a patient is prescribed some medicines by the doctor, then every time when patient have to take the medicine then there should be reminder on their mobile like in the form of alarm or something like a ring. It would be better because it doesn’t cause any delay in taking medicine and also it would be good for the health of patient.
  2. Second, I like to suggest is that OpenMRS should use some kind of system like e-doctors. If a person is registered at OpenMRS but he is at his home and if there would be a complication then he needs the sudden prescription of doctor. So, there should be like a virtual assistance which would provide some remedy and answer to the situation. It would be good to have such things because it would help patient in coming out of a big situation or problem.

Thanks, for reading. This task was approved by @athira

2 Likes
8

Devanshk09 December 18, 2019 at 07:34 (India Standard Time)

Hi, I log on to 75health and I have thought of 2 features that OpenMRS can have :-

  1. This will be fully new I didn’t found it in 75health also. The feature is that we need to add a sort by feature (Which sort the patients according to Age, Disease & Country, etc.) in the find patient records so that a doctor can check that how many patients are suffering from a particular disease. In which country which disease is spreading more etc.
  2. In 75health I found a billing in which if a doctor wants to sell medicine then he can do it in the same software. This feature in OpenMRS will also help us to calculate which disease is the most costly one.

It would be great if these features come to OpenMRS. Thank you Task approved by @vansha10

2 Likes
9

Researching a website “Medline Plus”. I observed some features that OpenMRS does not have. One feature I liked was the ability to take tests just by entering some medical information and getting the result instantly.It is able to diagnose symptoms by letting you fill them in. A feature that I would like to add would be able to enter your age or symptoms and you would get a description and names of some diseases that may be common for your age, also it would provide or refer you to some good doctor that can help diagnose a simple solution for your problem.The doctor being close to your address and easy for you too meet. Another feature that I would add is the ability to create a diet plan which would allow you to enter your disease or diagnosis and receive a diet that would take into account your disease ,provide you enough nutrients and not worsen your condition. It would contain all easy to find food and make sure it is available in your locality. And the last feature that I would like to add observing similar condition of some people I know is the ability or option to look for some manpower like someone to help you out in the house. In the current generation everyone is surrounded by work, so for a person with a serious condition such a person would be the biggest help for them. Thanks @jecihjoy for giving me the opportunity to share my views.

3 Likes
10

NOTE:
Hi students , well done for your suggestions , as your posting the ideas here, can you please format your posts a little better, to clearly point out your suggestions ,and make it more readable? That includes all the above who have not properly formatted their posts. thanks.

2 Likes
11

Here are my suggestions for two new features for OpenMRS.

1. Immunisation history

After looking at My Health Record, an electronic medical records platform used by the Australian Medicare system, I noticed that one important feature included was immunisation history. OpenMRS could include a feature for immunisation data with the details of all vaccines taken, in order to screen patients who are at high risk of contracting certain vaccine-preventable diseases. It could also help medical providers keep underage patients up to date with vaccines.

Given that developing countries have lower vaccination rates and more suspicious attitudes towards immunisation, this feature would be particularly important in managing patients at risk, and for tracking the overall public health and the herd immunity of a population.

2. Consent and code status

Due to the large role that ethics plays in medical providers’ daily work, I would like to suggest including a patient’s consent and code status into OpenMRS. For example, this feature could document whether or not a patient agrees to resuscitation during a heart attack, or if they consent to blood transfer.

Looking further into this idea, I found a study conducted at the Vanderbilt University Medical Center shows that documentation of code-status on their Computerised Provider Order Entry system may prevent unnecessary interventions and help doctors make decisions quickly in emergency situations (https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4293350/).

Therefore, a consent and code status feature would be very helpful in guiding medical providers through ethically challenging dilemmas where consent is important.

This task was approved by @mozzy. Thanks for reading!

3 Likes
12

Feature Request: Patient Self-Service

Adding self-service functionalities to OpenMRS may be useful for hospitals that are understaffed but overcrowded. Allowing patients to do some simple self-serving, such as getting their own test results or booking an appointment, will take a lot of work off the staff’s shoulders, allowing them to do more important things and help more people.

Thank you @mozzy for approving this task <3

2 Likes
13

Good point, I would suggest everybody to complete discobot tutorial, to do that message discobot @discobot display help and it shall tell you how to complete both basic tutorial and also the advance user tuturial in an fun and interactive way which should not take much time :grin:

Bonus Reward: You get a badge after completing both tutorials :wink:

1 Like
15

Approved by Athira Nair December 26, 2019 at 15:23 (Bangladesh Standard Time) In the “Register a Patient’ Module along with the given fields the following fields should be added:

  • Blood Type
  • Weight
  • Height

These fields are important & found in A graded hospital while registering for the first time. This helps the doctor to not wait for examination though examining this good but in emergency it saves time.

  • Visit History

This field can help the doctor to keep track of his/her patients. Suppose if the visit of the patient is too early, then doctor can understand the situation of patient is bad without seeing the patient. So, he can check him before the normal ones as “Live First”.

  • Clinical Notes (Family history, Social history, Vitals, General examination, Systematic examination)
  • Medications (Drug history, Drug problem)

The above two fields can help the doctor to review the past situation of the patient without asking them again & again. Also, he can understand & analyze the present & past condition of the patient. Moreover can give patients proper medications.

  • Billings

This feature helps the patients to keep & know the record of expense for medical tests, visits etc.

  • Appointment

With this feature doctors & the administration can keep order & timing of appointment for their patients. In this way they can manage their own time for the patients & hospital.

2 Likes
16

In our hospital, registration takes place when the patient books their appointment. It is done through a cashier window by a non-medical person. Often it is done by a relative or friend of the patient. So this first step would not be possible. It can only happen when the patient arrives at the clinic.

2 Likes
17

EMR Researched: EpicCare EMR

FEATURE 1: Family Healthcare

EpicCare EMR gives user the ability to not only manage their personal information but also their family’s information at their fingertips with their patient’s portal – MyChart. Patients have ability to message their doctors, attend e-visits, schedule appointments and be more involved in managing theirs as well their family’s health.

Why its important?

Having the ability to monitor the patient as well as their family’s health can help the doctors to better diagnosis the patient’s disease and at the same time monitor the safety of their family. It can also help doctors to know the root cause of the disease and even get to know if it’s an ancestry problem

FEATURE 2: AI Driven Trend Prediction

In next decade, we shall see the rise of “Data Driven Healthcare”, which will be powered by AI and ML.

With the power of AI, we can analyse large sets of patient records and predict some diseases in advance, like let’s take example of Flu, each year around 3.7 million people in the US catch flu, most cases are reported between the months of December-February, the cold time of the year. AI can analyse such patient records to predict the surge of some diseases/illnesses in advance.

Why its important?

If doctors know about the trends of future, it becomes easier for them to prepare for future problems and diagnosis. They may also stock up the medicines if they know which problems may be faced by the patients in near future. This would make their job easy and fast.

Task approved by @athira

2 Likes
18

Suggestion #1: Lab Integration - Separate Servers

From Practice Fusion, I think a helpful addition would be a lab and/or imaging integration. Oftentimes, waiting for a lab report can be very stressful as one’s life could be on the line due to a disease. The faster the results get in, the better, and a lab integration would allow workers at the lab to upload their results into the patient’s account. In poorer countries, transportation can be very rough; hence it is best to optimize the least amount of physical travel to and from the clinics. Moreover, the integration should come with a notification system for the doctors such that they can immediately provide expert feedback and help the patient through, if they require any.

For an example of this in practice, consider a common patient in Kenya. Suppose he has recently spent the night with someone whom he wasn’t sure was clean, and is now experiencing symptoms common to HIV. Then, he might go to one of OpenMRS’s clinics or a different clinic to instead get tested. Other clinics might not use OpenMRS, so this integration would be a separate server connected to the patient’s main hospital, which theoretically uses OpenMRS. Hence, it is a bit different from the Lab Module. Moreover, with the e-notifications, the patient should be able to receive the news faster from the doctor, which will be largely impactful.

Though some may believe separate OpenMRS servers are too tedious, the separate servers can help keep information organized and makes information more easily to be accessed. As mentioned before, other hospitals and clinics could also be using separate EHRs, hence this simplifies matters between the patient and other clinic. If the hospital/clinic does not use an EHR, this can help transition them into possibly fully converting into using OpenMRS. Overall, this is a relatively large quality of life change that can help organize informational processes.

Reference URL:

Imaging and Lab Integration, Lab Orders & Results | Practice Fusion

Suggestion #2: User Review Database

During my research on eClinicalWorks, 75health, and the patient portal module on OpenMRS, I thought of something not in place for either EHR. A very helpful addition would be to have a database of different diseases, symptoms, and medicines and allow users to post their own recovery stories and tips on how to feel better. The medicine database might be a bit unfeasible due to the enormous variety, however if it is implemented then it could include guides on how to apply and basic information. Overall, this would be a sort of “review” system. If the medicine isn’t helping or the patient is still waiting on a doctor’s response, then this would be incredibly useful to the patient. Moreover, the database and users’ responses can also help further research in the medical field.

Reference URLS:

https://wiki.openmrs.org/display/docs/Patient+Portal+Module++Personal+Cancer+Toolkit+Project+Revamp

What Is A Patient Portal?

http://curas.net/eclinicalworks/eclinicalworks-patient-portal/

This task was approved by @mozzy

19

How AI(Artificial Intelligence) can be used to analyze the medical records in OpenMRS. By - Devansh Khetan (9).pdf (3.3 MB) this task was approved by @sumangala28

20

Here are my ideas attached In a word document and the task approved by @vansha10.5362462078009344_1578321758_Suggest_a_new_feature_for_OpenMRS.pdf (390.8 KB)

21

Artificial Intelligence in OpenMRS

In recent years, artificial intelligence and machine learning have surged in popularity to become the hottest trends in software. Artificial intelligence, also known as AI, has been used in dozens of fields, from finance and education to transportation and social media.

But what exactly is Artificial Intelligence?

Artificial intelligence is defined as:

“the theory and development of computer systems able to perform tasks normally requiring human intelligence, such as visual perception, speech recognition and decision making.”

AI is commonly applied through machine learning, a statistical technique for fitting models to data in order to “train” computer systems to perform tasks without specific instructions. In medical records systems, these machine learning models could help predict patient outcomes, guide medical decisions and improve user experience.

Predicting patient outcomes

AI can be used to predict which patients have the highest risk of developing more serious conditions, or which medicines could be administered for a certain disease. For example, the company Epic has used machine learning to create a popular sepsis prediction model that scans patients’ information every 15 minutes and monitors over 80 variables. This model decreased mortality caused by sepsis by 18%.

In the case of OpenMRS, artificial intelligence could be used to achieve similar results if applied to detect patterns in entered patient data. Machine learning models could analyse the data inputted into OpenMRS, and find patterns and correlations that human health care workers may not be able to immediately see, making artificial intelligence infinitely useful for producing predictions and correlations. Implementing AI to predict outcomes for hospitalised patients, such as readmission rates and survival chances, would better equip medical providers with information to guide treatment.

Guiding medical decisions

In fact, artificial intelligence could even directly offer suggestions for better clinical decisions. Based on data from previous cases and treatments, an electronic medical records system could recommend treatment strategies for specific patients, enabling more personalised care.

Recently, the University of Iowa Hospitals and Clinics combined machine learning with medical record systems to prevent surgical site infections, by providing clinical decision support to health care providers. This led to a 74% reduction in surgical site infections over three years, saving nearly $1.2 million.

For OpenMRS, implementing a feature to help health care providers make better decisions - for example, warning doctors when two prescribed drugs may interact to create bad side effects - would very likely increase the quality of care immensely.

Improving user experience

Furthermore, according to an article in Harvard Business Review about electronic health records, “the systems’ rigidity is a real obstacle to improvement… AI, and machine learning specifically, could help EHRs continuously adapt to users’ preferences.”

While OpenMRS already offers many add-on modules to help users configure their software to suit their needs, artificial intelligence could make the system even easier to use. Forms of artificial intelligence, such as natural language processing, could be applied to medical records, in order to automatically analyse clinical documentation and reports, instead of forcing doctors to enter data piece by piece into long, tedious forms.

That being said, in the past, medical records systems have found it difficult to implement artificial intelligence, due to the sheer volume of data that can be entered into the system. One small condition, such as high blood pressure, could be entered into the system by different doctors in thousands of different ways. These forms of unstructured data can be difficult for a computer to extract.

However, thanks to the OpenMRS FHIR Module in development, data entered into the software can be transformed into an easily readable, standardised format (called Fast Healthcare Interoperability Resources) for training deep learning systems involving many variables. Therefore, integrating artificial intelligence models into OpenMRS is quite feasible.

In conclusion…

From all the possibilities and outcomes mentioned above, it is clear that artificial intelligence can be applied to medical records systems like OpenMRS to improve the quality of health care, benefiting both patients and providers. Hence, integrating artificial intelligence into OpenMRS is a course of action with enormous potential that should definitely be considered.

References:

A PDF version of the article is also attached here. Artificial Intelligence in OpenMRS(1).pdf (515.5 KB)

This task was approved by @dilantha

2 Likes