Bell Eapen MD, PhD.

Bringing Digital health & Gen AI research to life!

Kedro for multimodal machine learning in healthcare 

Healthcare data is heterogenous with several types of data like reports, tabular data, and images. Combining multiple modalities of data into a single model can be challenging due to several reasons. One challenge is that the diverse types of data may have different structures, formats, and scales which can make it difficult to integrate them into a single model. Additionally, some modalities of data may be missing or incomplete, which can make it difficult to train a model effectively. Another challenge is that different modalities of data may require different types of pre-processing and feature extraction techniques, which can further complicate the integration process. Furthermore, the lack of large-scale, annotated datasets that have multiple modalities of data can also be a challenge. Despite these challenges, advances in deep learning, multi-task learning and transfer learning are making it possible to develop models that can effectively combine multiple modalities of data and achieve reliable performance. 

Kedro for multimodal machine learning in healthcare 
Pipelines Kedro for multimodal machine learning

Kedro for multimodal machine learning

Kedro is an open-source Python framework that helps data scientists and engineers organize their code, increase productivity and collaboration, and make it easier to deploy their models to production. It is built on top of popular libraries such as Pandas, TensorFlow and PySpark, and follows best practices from software engineering, such as modularity and code reusability. Kedro supplies a standardized structure for organizing code, handling data and configuration, and running experiments. It also includes built-in support for version control, logging, and testing, making it easy to implement reproducible and maintainable pipelines. Additionally, Kedro allows to easily deploy the pipeline on cloud platforms like AWS, GCP or Azure. This makes it a powerful tool for creating robust and scalable data science and data engineering pipelines. 

I have built a few kedro packages that can make multi-modal machine learning easy in healthcare. The packages supply prebuilt pipelines for preprocessing images, tabular and text data and build fusion models that can be trained on multi-modal data for easy deployment. The text preprocessing package currently supports BERT and CNN-text models. There is also a template that you can copy to build your own pipelines making use of the preprocessing pipelines that I have built. Any number and combination of data types are supported. Additionally, like any other kedro pipeline, these can be deployed on kubeflow and VertexAI. Do comment below if you find these tools useful in your research. 

Link to the repository below.

Dark Mode

kedro-multimodal (this link opens in a new window) by dermatologist (this link opens in a new window)

Template for multi-modal machine learning in healthcare using Kedro. Combine reports, tabular data and image using various fusion methods.

Six things data scientists in healthcare should know

Healthcare, like most other fields, is eager to get on the data science bandwagon. Data scientists can make a huge difference in the way big data is utilized for clinical decision-making. However, there are paradigmatic differences in the way data scientists from quantitative fields view the world, compared to their clinical counterparts. This is especially true in the emerging fields of machine learning and artificial intelligence. This may lead to considerable inefficiencies. As a person trained in both fields, here is my take on this.

Data scientists
Credit: Dasaptaerwin, CC0, via Wikimedia Commons

Data scientists should focus on the problem and not the solutions

Data scientists are excited about the latest GPT or BERT. Data scientists tend to refine the model a bit more using 10 more GPUs! In the process, they tend to solve problems that do not exist. From my experience practicing medicine in extremely resource-poor areas, simple solutions are valued more than BERT running on Kubernetes! This is true in the developed world as well, and many teams may have fundamental data needs that need to be tackled first.

Explanation comes before prediction

Emerging machine learning methods prioritize prediction accuracy compromising on explainability in the process. Clinicians, in most cases, cannot use nor trust a model that arrives at a conclusion without showing how it reached there. Hence, in the clinical domain, a simple logistic regression model may be more acceptable than a deep learning neural network. Parsimony is the key and a bit of feature selection to ensure parsimony will be appreciated always.

You need to know the clinical terminologies

A basic understanding of the clinical terminologies and terminology systems such as SNOMED and ICD is vital. It helps in understanding the clinical community better. Any healthcare analytics to consider variations in terminologies and adopt a standard system for consistency. Any tool that data scientists build for the clinical community should have support for terminology systems.

Biostatistics is more pervasive than you think

Most healthcare professionals are trained in biostatistics. Hence, the thinking leans towards population, sampling, randomization, blindings and showing a ‘statistically significant’ difference. Moving towards machine learning needs a paradigmatic shift. It may be useful to have a discussion on this at the outset.

Classes are of unequal importance

In healthcare, finding one class (e.g. cancer) is more important than the other class (e.g. no cancer). One class may need active intervention to save lives. Hence, sensitivity and specificity are of vital importance than accuracy!

Life is precious!

In healthcare, there is no room for error. Some decisions may have disastrous consequences while few others may save lives. As a data scientist in the healthcare domain, you should be cognizant of the fact that healthcare data is different from banking/airline data.

Clinical Query Language – Part 1

Clinical Query Language (CQL) is a high-level query language to represent and generate unambiguous quality measures or clinical decision rules. I am not a CQL expert. These are my notes from a system development perspective. I am trying to make sense of this emerging concept and add my notes here in the hope that others may find this useful.

U.S. Navy photo by Chief Warrant Officer 4 Seth Rossman. / Public domain (wikimedia)

Clinical Query Language is designed to be intuitive for clinicians authoring the queries for quality measures and clinical decision support. The decision support rules are mostly alert type rules at the individual and population level that is calculated from a database (not usually diagnostic decision support). You can use any data model with CQL.

Here is an example segment of CQL:

define “InDemographic”:
AgeInYearsAt(start of MeasurementPeriod) >= 16 and AgeInYearsAt(start of MeasurementPeriod) < 24
and “Patient”.”gender” in “Female Administrative Sex”

As Clinical Query Language follows strict semantics, you can autogenerate lexers, parsers and visitors using ANTLR. In simple terms, CQL’s semantics can be represented as a ‘grammar’ that ANTLR can read and generate code to process any CQL in a variety of programming languages, including Java, Javascript, Python, C# and Go. The CQL grammar files are here: https://cql.hl7.org/08-a-cqlsyntax.html. Incidentally, CQL grammar inherits from fhirpath.

If you wish to generate code from these files, there are two things to note:

  • You need to rename CQL.g4 to cql.g4 as the library names are case sensitive and should correspond to the filename.
  • Put fhirpath.g4 in the same folder as cql.g4, and cql refers to fhirpath grammar.

Clinical Query Language aims to provide a high-level domain-independent language for clinicians that can be translated into low-level database logic. As CQL does not prescribe a data model, an intermediary format linking CQL to the data management logic is required. That is called Expression Logical Model (ELM) that we will discuss in part 2.

OHDSI OMOP to FHIR mapper

TL;DR Below is an open-source common-line tool for converting an OHDSI OMOP cohort (defined in ATLAS) to a FHIR bundle and vice versa.

Wikimedia commons: Copyright held by BAPS Swaminarayan Sanstha (web: www.baps.org, email: info@baps.org); Unknown photographer / CC BY-SA (https://creativecommons.org/licenses/by-sa/4.0)

OHDSI OMOP CDM is one of the most popular clinical data models for health data warehouses. The simple, but clinically motivated data structure is intuitively appealing to clinicians leading to its good adoption. In this respect, it has overtaken HL7-V3 which is more robust but has a steeper learning curve, especially for clinicians. The OHDSI OMOP CDM is widely used in the pharmaceutical industry for drug monitoring.

FHIR is emerging as the defacto standard for health system interoperability, owing largely to its simplicity and the use of existing and popular standards such as REST. As NoSQL databases become more and popular in healthcare, FHIR can also be a good persistence schema. It aligns well with search technologies such as elasticsearch.

As both standards are popular, conversion from one to the other may be commonly required. Researchers at Georgia Tech have an open-source tool – GT-FHIR2 – for mapping an existing OHDSI OMOP CDM database as FHIR endpoint. However, conversion between existing systems may not be easy with a full-stack solution. 

I have a simpler solution that I believe will be useful in the following scenarios:

  • To export a cohort to a FHIR based analytics tool.
  • To load new resources to OMOP CDM databases for incremental ETL.

Omopfhirmap is a command-line tool for mapping a OHDSI cohort, defined in ATLAS, to a FHIR bundle that can be optionally submitted to a FHIR server for processing. Conversely, it can process a FHIR bundle and add resources to an existing CDM database ignoring duplicates. Unlike GT-FHIR2, the OMOP on FHIR Project at Georgia Tech omopfhirmap does not expose OMOP database as FHIR endpoints. 

I have used spring-boot and JPA for easy wiring of services and abstraction of database and the hapi-fhir as it is an obvious choice for any java based FHIR applications. It is still a work in progress and any help will be appreciated (Refer to CONTRBUTING.md).

OHDSI OMOP CDM ETL Tools in Python, .Net and Go

TL;DR Here are few OHDSI OMOP CDM tools that may save you time if you are developing ETL tools!

Python: pyomop | pypi
.NET: omopcdmlib | NuGet
Golang: gocdm

OHDSI OMOP CDM Libraries

The COVID-19 pandemic brought to light many of the vulnerabilities in our data collection and analytics workflows. Lack of uniform data models limits the analytical capabilities of public health organizations and many of them have to re-invent the wheel even for basic analysis. As many other sectors embrace big data and machine learning, many healthcare analysts are still stuck with the basic data wrenching with Excel.

The OHDSI OMOP CDM (Common data model) for observational data is a popular initiative for bringing data into a common format that allows for collaborative research, large-scale analytics, and sharing of sophisticated tools and methodologies. Though OHDSI OMOP CDM is primarily for patient-centred observational analysis, mostly for clinical research, it can be used with minor tweaks for public health and epidemiologic data as well. We have written about some of the technical details here.

The OHDSI OMOP CDM is relatively simple and intuitive for clinical teams than emerging standards such as FHIR. Though the relational database approach and some of the software tools associated with OHDSI OMOP CDM are a bit old-fashioned, the data model is clinically motivated. There is an ecosystem of software tools for many of the analytics tools that can be used out of the box. The Observational Medical Outcomes Partnership (OMOP) CDM, now in its version 6.0, has simple but powerful vocabulary management. OHDSI OMOP CDM is a good choice for healthcare organizations moving towards health data warehousing and OLAP.

One weakness of OHDSI is the lack of tools for efficient ETL from existing EHR and HIS. Converting existing EHR data to the CDM is still a complex task that requires technical expertise. During the additional “home time” during the COVID pandemic, I have created three software libraries for ETL tool developers. These libraries in Python, .NET and Golang encapsulated the V6.0 CDM and helps in writing and reading data from a variety of databases with the V6.0 tables. The libraries also support creating the CDM tables for new databases and loading the vocabulary files.

Python: pyomop | pypi
.NET: omopcdmlib | NuGet
Golang: gocdm

These libraries might save you some time if you are building scripts for ETL to CDM. They are all open-source and free to use in your tools. Do give me a shout if you find these libraries useful and please star the repositories on GitHub.

FHIR and public health data warehouses

First posted on CanEHealth.com

The provincial government is building a connected health care system centred around patients, families and caregivers through the newly established OHTs. As disparate healthcare and public health teams move towards a unified structure, there is a growing need to reconsider our information system strategy. Most off the shelf solutions are pricey, while open-source solutions such as DHIS2 is not popular in Canada. Some of the public health units have existing systems, and it will be too resource-intensive to switch to another system. The interoperability challenge needs an innovative solution, beyond finding the single, provincial EMR.

artificial intelligence

We have written about the theoretical aspects, especially the need to envision public health information systems separate from an EMR. In this working paper, we propose a maturity model for PHIS and offer some pragmatic recommendations for dealing with the common challenges faced by public health teams. 

Below is a demo project on GitHub from the data-intel lab that showcases a potential solution for a scalable data warehouse for health information system integration. Public health databases are vital for the community for efficient planning, surveillance and effective interventions. Public health data needs to be integrated at various levels for effective policymaking. PHIS-DW adopts FHIR as the data model for storage with the integrated Elasticsearch stack. Kibana provides the visualization engine. PHIS-DW can support complex algorithms for disease surveillance such as machine learning methods, hidden Markov models, and Bayesian to multivariate analytics. PHIS-DW is work in progress and code contributions are welcome. We intend to use Bunsen to integrate PHIS-DW with Apache Spark for big data applications. 

FHIR has some advantages as a data persistence schema for public health. Apart from its popularity, the FHIR bundle makes it possible to send observations to FHIR servers without the associated patient resource, thereby ensuring reasonable privacy. This is especially useful in the surveillance of pandemics such as COVID19. Some useful yet complicated integrations with OSCAR EMR and DHIS2 is under consideration. If any of the OHTs find our approach interesting, give us a shout. 

BTW, have you seen Drishti, our framework for FHIR based behavioural intervention? 

How to deploy an h2o ai model using OpenFaaS on Digitalocean in 2 minutes

H2O is an open-source, distributed and scalable machine learning platform written in JAVA. H2O supports many of the statistical & machine learning algorithms, including gradient boosted machines, generalized linear models, deep learning and more.  OpenFaaS® (Functions as a Service) is a framework for building Serverless functions easily with Docker. Read my previous post to learn more about OpenFaaS and DO. 

H2O AI model deployment

H2O has a module aptly named sparkling water that allows users to combine the machine learning algorithms of H2O with the capabilities of Spark. Integrating these two open-source environments provides a seamless experience for users who want to make a query using Spark SQL, feed the results into H2O to build a model and make predictions, and then use the results again in Spark. For any given problem, better interoperability between tools provides a better experience.

H2O Driverless AI is a commercial package for automatic machine learning that automates some of the most difficult data science and machine learning workflows such as feature engineering, model validation, model tuning, model selection, and model deployment. H2O also has a popular open-source module called AutoML that automates the process of training a large selection of candidate models. H2O’s AutoML can be used for automating the machine learning workflow, which includes automatic training and tuning of many models within a user-specified time-limit. AutoML makes hyperparameter tuning accessible to everyone.

H2O allows you to convert the models to either a Plain Old Java Object (POJO) or a Model Object or an Optimized (MOJO) that can be easily embeddable in any Java environment. The only compilation and runtime dependency for a generated model is the h2o-genmodel.jar file produced as the build output of these packages. You can read more about deploying h2o models here.

I have created an OpenFaaS template for deploying the exported MOJO file using a base java container and the dependencies defined in the gradle build file. Using the OpenFaaS CLI (How to Install) pull my template as below:

mkdir watersplash
cd watersplash

faas-cli template pull https://github.com/dermatologist/java-ext --prefix your-docker-uname

faas-cli new --lang java-h2o watersplash

Copy the exported MOJO zip file to the root folder along with build.gradle and settings.gradle. Make appropriate changes to handle.java as per the needs of the model, as explained here. Add http://digitaloceanIP:8080 to watersplash.yml

 provider:
  	name: openfaas
  	gateway: http://digitaloceanIP:8080

and finally:

 faas-cli up -f watersplash.yml

That’s it! Congratulations! Your model is up and running! Access it at http://digitaloceanIP:8080/function/watersplash

If you get stuck at any stage, give me a shout below. 

Machine Learning on Diabetic Retinopathy Images

Artificial intelligence (AI) and Machine Learning (ML) are having a profound impact on the way medicine is being practiced. AI/ML algorithms and techniques fit imaging applications easily and can help with automation. Radiology is the specialty that has benefitted the most from the AI/ML revolution. Melanoma detection in Dermatology is another obvious winner.

Image credit: pixabay.com

Many of the machine learning algorithms are reasonably well known. The real challenge is to get the infrastructure to crunch massive amounts of data, getting the ideal dataset for a problem, optimizing the model for performance and deploying the model for use. If you are relatively new to ML, Kaggle is a useful resource for you to start.

I will briefly introduce Kaggle for those who have not used it before. Kaggle is a platform for posting datasets that you have collected. They also provide ‘kernels’ or computational resources (typically Jupyter Notebooks) for collaborative analysis. The datasets can be made private or public under a variety of license options. Organizations post competitions and reward teams that solve them. Solutions are typically posted as predictions on a test dataset or share the kernel code

I recently noticed a good competition on Kaggle that the eHealth community may find interesting. Aravind Eye Hospital in India has posted a dataset consisting of fundoscopic images of diabetic retinopathy with varying degrees of severity. The dataset consists of thousands of images collected in rural areas by the technicians of Aravind hospital from the rural areas of India. The challenge is to develop a model that can predict the severity of diabetic retinopathy from the fundoscopic image. Further, the successful solutions will be shared with other Ophthalmologists through the 4th Asia Pacific Tele-Ophthalmology Society (APTOS) Symposium.

The competition page is available here: https://www.kaggle.com/c/aptos2019-blindness-detection
Let me know if anybody wants to team up!

Hephestus: Health data warehousing tool for public health and clinical research

Health data warehousing is becoming an important requirement for deriving knowledge from the vast amount of health data that healthcare organizations collect. A data warehouse is vital for collaborative and predictive analytics. The first step in designing a data warehouse is to decide on a suitable data model. This is followed by the extract-transform-load (ETL) process that converts source data to the new data model amenable for analytics.

The OHDSI – OMOP Common Data Model is one such data model that allows for the systematic analysis of disparate observational databases and EMRs. The data from diverse systems needs to be extracted, transformed and loaded on to a CDM database. Once a database has been converted to the OMOP CDM, evidence can be generated using standardized analytics tools that are already available.

Each data source requires customized ETL tools for this conversion from the source data to CDM. The OHDSI ecosystem has made some tools available for helping the ETL process such as the White Rabbit and the Rabbit In a Hat. However, health data warehousing process is still challenging because of the variability of source databases in terms of structure and implementations.

Hephestus is an open-source python tool for this ETL process organized into modules to allow code reuse between various ETL tools for open-source EMR systems and data sources. Hephestus uses SqlAlchemy for database connection and automapping tables to classes and bonobo for managing ETL. The ultimate aim is to develop a tool that can translate the report from the OHDSI tools into an ETL script with minimal intervention. This is a good python starter project for eHealth geeks.

Anyone anywhere in the world can build their own environment that can store patient-level observational health data, convert their data to OHDSI’s open community data standards (including the OMOP Common Data Model), run open-source analytics using the OHDSI toolkit, and collaborate in OHDSI research studies that advance our shared mission toward reliable evidence generation. Join the journey! here

Disclaimer: Hephestus is just my experiment and is not a part of the official OHDSI toolset.

[github-clone username=”dermatologist” repository=”hephaestus”]

Natural language processing (NLP) tools for health analytics

Natural language processing (NLP) is the process of using computer algorithms to identify key elements in language and extract meaning from unstructured spoken or written text. NLP combines artificial intelligence, computational linguistics, and other machine learning disciplines.

natural language processing

In the healthcare industry, NLP has many applications such as interpreting clinical documents in an electronic health record. Natural language processing is important in clinical decision support systems by extracting meaningful information from free-text query interfaces. It may reduce transcription costs by allowing providers to dictate their notes, or generate tailored educational materials for patients ready for discharge. At a high-level NLP includes processes such as structure extraction, tokenization, tagging, part of speech identification and lemmatization.

“cTAKES is a natural language processing system for extraction of information from electronic medical record clinical free-text. Originally developed at the Mayo Clinic, it has expanded to being used by various institutions internationally.”

cTAKES is relatively difficult to install and use, especially if the service needs to be shared by several systems. I have integrated cTakes into an easy to use spring boot application that provides REST web services for clinical document annotation. The repository is here.

[github-clone username=”dermatologist” repository=”ctakes-spring-boot”]

You need a UMLS username and password for deploying the application. RysannMD is an efficient and fast system for annotating clinical documents developed at Ryerson University. Some of my other experiments with NLP are available here.

Are you working on any NLP projects in medicine?