Introducing Kotlin FHIR: A new library to bring FHIR to Multiplatform

Build once, deploy everywhere: multiplatform FHIR development on Android, iOS, and Web

by Jing Tang, Google Research

The mission of Google's Open Health Stack team is to accelerate digital health innovation by providing developers everywhere with critical building blocks for next-generation healthcare applications. Expanding its existing components, the team has released Kotlin FHIR (currently in alpha), a new open-source library now available on GitHub. It implements the HL7® FHIR® data model on Kotlin Multiplatform (KMP), enabling developers to build FHIR apps and tools for Android, iOS, and Web simultaneously.

Demo app launched as Android, iOS, and Web applications

Tools to support health data exchange using a modern standard

HL7® FHIR® (Fast Healthcare Interoperability Resources) is a global interoperability standard for healthcare data exchange. It enables healthcare systems to exchange data freely and securely, improving efficiency and transparency while reducing integration costs. Over the years, it has seen rapidly growing adoption, and its use has been mandated by health regulations in an increasing number of countries.

Since March 2023, the Open Health Stack team at Google has introduced a number of tools to support FHIR development. For example, the Android FHIR SDK helps developers to build offline capable FHIR-native apps that can help community health workers carry out data collection tasks in remote communities. With FHIR Data Pipes, developers can build analytics solutions more easily to generate critical insights for large healthcare programmes more easily. Today, apps powered by these tools are used by health workers covering over 75 million people across Sub-Saharan Africa, South and Southeast Asia.

A leap forward to multiplatform development

In low-resource settings, it is imperative to develop apps that can reach as many patients as possible at a low development cost. However, a lack of infrastructure and tooling often hinders this goal. For example, Kotlin Multiplatform (KMP) is a new and exciting technology rapidly gaining traction, but existing FHIR libraries are not suitable for KMP development due to their platform-specific dependencies. Consequently, developing FHIR apps on KMP has not been possible, causing developers to miss out on a significant opportunity to scale their solutions.

Introducing Kotlin FHIR. It is a modern and lightweight implementation of FHIR data models designed for use on KMP with no platform-specific dependencies. With Kotlin FHIR, developers can build FHIR apps once, and deploy them to Android, iOS, Web, and other platforms.

"Any library that helps implementers use FHIR is my favourite, but I'm particularly thrilled to see a new library from the awesome Open Health Stack team.

– Grahame Grieve, Creator of FHIR, Product Director at HL7

Modern, lightweight, and sustainable

Kotlin FHIR uses KotlinPoet to generate the FHIR data model directly from the specification. This ensures that the library is complete and maintainable. The data model classes it generates are minimalist to provide the best usability for developers: it has everything that you need, nothing less and nothing more. It uses modern language features in Kotlin such as sealed interfaces to ensure type-safety and to give developers the best coding experience. It supports all the FHIR versions: R4, R4B and R5, and will be updated when new FHIR versions are released.

The library is currently in alpha, but has received positive feedback from the developer community. To try FHIR multiplatform development using the library, head to the repository.

Beyond data models: more on multiplatform

Our mission is to empower the digital health community, and the Kotlin FHIR library is our latest step in that effort. But handling the FHIR data model on KMP is just the beginning. Rich features provided by the Android FHIR SDK libraries will also be needed on KMP. This is a collaborative effort, and we invite the FHIR community to join us in defining and building the cross-platform tools you need most. To learn more about how you can get involved, head to the Open Health Stack developer site.

Releasing the Healthcare Text Annotation Guidelines

The Healthcare Text Annotation Guidelines are blueprints for capturing a structured representation of the medical knowledge stored in digital text. In order to automatically map the textual insights to structured knowledge, the annotations generated using these guidelines are fed into a machine learning algorithm that learns to systematically extract the medical knowledge in the text. We’re pleased to release to the public the Healthcare Text Annotation Guidelines as a standard.

Google Cloud recently launched AutoML Entity Extraction for Healthcare, a low-code tool used to build information extraction models for healthcare applications. There remains a significant execution roadblock on AutoML DIY initiatives caused by the complexity of translating the human cognitive process into machine-readable instructions. Today, this translation occurs thanks to human annotators who annotate text for relevant insights. Yet, training human annotators is a complex endeavor which requires knowledge across fields like linguistics and neuroscience, as well as a good understanding of the business domain. With AutoML, Google wanted to democratize who can build AI. The Healthcare Text Annotation Guidelines are a starting point for annotation projects deployed for healthcare applications.

The guidelines provide a reference for training annotators in addition to explicit blueprints for several healthcare annotation tasks. The annotation guidelines cover the following:

• The task of medical entity extraction with examples from medical entity types like medications, procedures, and body vitals.
• Additional tasks with defined examples, such as entity relation annotation and entity attribute annotation. For instance, the guidelines specify how to relate a medical procedure entity to the source medical condition entity, or how to capture the attributes of a medication entity like dosage, frequency, and route of administration.
• Guidance for annotating an entity’s contextual information like temporal assessment (e.g., current, family history, clinical history), certainty assessment (e.g., unlikely, somewhat likely, likely), and subject (e.g., patient, family member, other).

Google consulted with industry experts and academic institutions in the process of assembling the Healthcare Text Annotation Guidelines. We took inspiration from other open source and research projects like i2b2 and added context to the guidelines to support information extraction needs for industry-applications like Healthcare Effectiveness Data and Information Set (HEDIS) quality reporting. The data types contained in the Healthcare Text Annotation Guidelines are a common denominator across information extraction applications. Each industry application can have additional information extraction needs that are not captured in the current version of the guidelines. We chose to open source this asset so the community can tailor this project to their needs.

We’re thrilled to open source this project. We hope the community will contribute to the refinement and expansion of the Healthcare Text Annotation Guidelines, so they mirror the ever-evolving nature of healthcare.

By Andreea Bodnari, Product Manager and Mikhail Begun, Program Manager—Google Cloud AI

DeepVariant: Highly Accurate Genomes With Deep Neural Networks

Crossposted on the Google Research Blog

Across many scientific disciplines, but in particular in the field of genomics, major breakthroughs have often resulted from new technologies. From Sanger sequencing, which made it possible to sequence the human genome, to the microarray technologies that enabled the first large-scale genome-wide experiments, new instruments and tools have allowed us to look ever more deeply into the genome and apply the results broadly to health, agriculture and ecology.

One of the most transformative new technologies in genomics was high-throughput sequencing (HTS), which first became commercially available in the early 2000s. HTS allowed scientists and clinicians to produce sequencing data quickly, cheaply, and at scale. However, the output of HTS instruments is not the genome sequence for the individual being analyzed — for humans this is 3 billion paired bases (guanine, cytosine, adenine and thymine) organized into 23 pairs of chromosomes. Instead, these instruments generate ~1 billion short sequences, known as reads. Each read represents just 100 of the 3 billion bases, and per-base error rates range from 0.1-10%. Processing the HTS output into a single, accurate and complete genome sequence is a major outstanding challenge. The importance of this problem, for biomedical applications in particular, has motivated efforts such as the Genome in a Bottle Consortium (GIAB), which produces high confidence human reference genomes that can be used for validation and benchmarking, as well as the precisionFDA community challenges, which are designed to foster innovation that will improve the quality and accuracy of HTS-based genomic tests.

CAPTION: For any given location in the genome, there are multiple reads among the ~1 billion that include a base at that position. Each read is aligned to a reference, and then each of the bases in the read is compared to the base of the reference at that location. When a read includes a base that differs from the reference, it may indicate a variant (a difference in the true sequence), or it may be an error.

Today, we announce the open source release of DeepVariant, a deep learning technology to reconstruct the true genome sequence from HTS sequencer data with significantly greater accuracy than previous classical methods. This work is the product of more than two years of research by the Google Brain team, in collaboration with Verily Life Sciences. DeepVariant transforms the task of variant calling, as this reconstruction problem is known in genomics, into an image classification problem well-suited to Google's existing technology and expertise.

CAPTION: Each of the four images above is a visualization of actual sequencer reads aligned to a reference genome. A key question is how to use the reads to determine whether there is a variant on both chromosomes, on just one chromosome, or on neither chromosome. There is more than one type of variant, with SNPs and insertions/deletions being the most common. A: a true SNP on one chromosome pair, B: a deletion on one chromosome, C: a deletion on both chromosomes, D: a false variant caused by errors. It's easy to see that these look quite distinct when visualized in this manner.

We started with GIAB reference genomes, for which there is high-quality ground truth (or the closest approximation currently possible). Using multiple replicates of these genomes, we produced tens of millions of training examples in the form of multi-channel tensors encoding the HTS instrument data, and then trained a TensorFlow-based image classification model to identify the true genome sequence from the experimental data produced by the instruments. Although the resulting deep learning model, DeepVariant, had no specialized knowledge about genomics or HTS, within a year it had won the the highest SNP accuracy award at the precisionFDA Truth Challenge, outperforming state-of-the-art methods. Since then, we've further reduced the error rate by more than 50%.

DeepVariant is being released as open source software to encourage collaboration and to accelerate the use of this technology to solve real world problems. To further this goal, we partnered with Google Cloud Platform (GCP) to deploy DeepVariant workflows on GCP, available today, in configurations optimized for low-cost and fast turnarounds using scalable GCP technologies like the Pipelines API. This paired set of releases provides a smooth ramp for users to explore and evaluate the capabilities of DeepVariant in their current compute environment while providing a scalable, cloud-based solution to satisfy the needs of even the largest genomics datasets.

DeepVariant is the first of what we hope will be many contributions that leverage Google's computing infrastructure and ML expertise to both better understand the genome and to provide deep learning-based genomics tools to the community. This is all part of a broader goal to apply Google technologies to healthcare and other scientific applications, and to make the results of these efforts broadly accessible.

By Mark DePristo and Ryan Poplin, Google Brain Team