Blogs

From Thin Ice to Solid Ground: How AI is Changing Clinical Practice for the Better

Hear first hand the challenges clinicians face working in primary care and the pivotal role that AI can have to transform patient care.

Blogs

Full Steam Ahead: How AI Can Transform the Genetics Journey in Precision Medicine

In the era of precision medicine, genetic information plays a foundational role in tailoring healthcare to individuals. However, significant gaps remain in the patient journey, particularly in Medical Genetics and Genomics, where access to specialists, delayed diagnoses, and healthcare costs hinder progress.

Publications

BiCAL: Bi-directional Contrastive Active Learning for Clinical Report Generation

This paper, published in BioNLP 2024, proposes a novel active learning method to train models with less labelled data in the medical domain.

Publications

The Potential and Pitfalls of using a LLM as a Clinical Assistant

This paper, published in the Journal of Medical Informatics Association, explores the application of ChatGPT and GPT-4 in the context of COPD, CKD, HSV and PBC.

Publications

A Systematic Comparison of Horizontal Federated Learning Algorithm Based On Random Forests In A Medical Setting

This paper, which was published in Machine Intelligence Research, systematically analyzes the random forest algorithms in federated learning scenarios with four medical datasets.

Blogs

The Meteoric Rise of Large Language Models: Helping Hand for Healthcare?

Delve into the transformative power of Large Language Models in clinical settings, while exploring their potential and addressing challenges to revolutionize healthcare.

Whitepapers

How can Pharma & Healthcare Collaborate in a Financially Sustainable, Scalable & Privacy-Preserving Manner?

Learn how Pangaea’s product platform is fostering collaborations between pharmaceuticals and healthcare providers to find more undiagnosed, misdiagnosed and miscoded patients.

Whitepapers

Characterizing Patients Across Hard-to-Diagnose Conditions in a Privacy-Preserving & Scalable Manner

Clinicians spend more than 35% of their time capturing patient data, symptoms, family histories, lab results and such key information in the form of digitized patient records. In spite of this, more than 60% of patients with rare and hard-to-diagnose conditions are not diagnosed in a timely manner. This is due to lack of scalable […]

Publications

Phenotyping in Clinical Text with Unsupervised Numerical Reasoning for Patient Stratification

This publication was selected to be presented at the AAAI 2022 conference. It has also been published in the Experimental Biology and Medicine (EBM) Journal and Multimodal AI in Healthcare Publication.

Publications

A Scalable Workflow to Build Machine Learning Classifiers with Clinician-in-the-Loop to Identify Patients in Specific Diseases

Clinicians may rely on medical coding systems such as International Classification of Diseases (ICD) to identify patients with diseases from Electronic Health Records (EHRs). However, due to the lack of detail and specificity as well as a probability of miscoding, recent studies suggest the ICD codes often cannot characterise patients accurately for specific diseases in […]

Blogs

Discover New Clinical Insights and Genomic Test Results from Breast Cancer Patients’ Records

Valuable Insights Trapped in Unstructured Data Electronic health records (EHRs) and related clinical documents are valuable sources of intelligence on patients’ health journeys including data on therapies, treatments, and outcomes as well as diagnostic tests. But extracting it remains challenging for clinicians and scientists since most of it exists as unstructured text. To address this […]

Publications

Medical Scientific Table-to-Text Generation with Human-in-the-Loop under the Data Sparsity Constraint

Structured tabular data in the pre-clinical and clinical domains contains valuable information about individuals and an efficient table-to-text summarization system can drastically reduce manual efforts to condense this data into regulatory reports in the biopharmaceutical industry. We introduce Pangaea’s Intelligence Extraction and Summarization (PIES), a neural architecture, which solves a challenging task of automatically generating […]

Blogs

Microsoft Interviews Pangaea’s Founder

Microsoft has published an article on Pangaea’s work, How Pangaea Data Uses Azure for a Medical AI Tool that Improves Patient Outcomes. Microsoft sat down with our founder, Dr. Vibhor Gupta, to learn more about how our AI-driven technology is helping to extract and summarize patient records in a privacy-preserving manner. The article features our […]

Publications

Self-Supervised Detection of Contextual Synonyms in a Multi-Class Setting: Phenotype Annotation Use Case

In this paper, we propose a self-supervised pre-training approach which is able to detect contextual synonyms of concepts being training on the data created by shallow matching.

Publications

Clinical Utility of the Automatic Phenotype Annotation in Unstructured Clinical Notes: ICU Use Cases

This publication discusses the clinical utility of the automatic phenotype annotation in unstructured clinical notes in intensive care units.

Whitepapers

Natural Language Generation is Helping Improve Patient Outcomes and Automatically Generate Regulatory Reports

This white paper discusses the application of NLG through Pangaea’s pioneering work.

Publications

PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization

Abstract: “Recent work pre-training Transformers with self-supervised objectives on large text corpora has shown great success when fine-tuned on downstream NLP tasks including text summarization.

Publications

Generation and evaluation of artificial mental health records for Natural Language Processing

Abstract: “A serious obstacle to the development of Natural Language Processing (NLP) methods in the clinical domain is the accessibility of textual data. The mental health domain is particularly challenging, partly because clinical documentation relies heavily on free text that is difficult to de-identify completely.

Publications

Unsupervised Annotation of Phenotypic Abnormalities via Semantic Latent Representations on Electronic Health Records

Abstract: “The extraction of phenotype information which is naturally contained in electronic health records (EHRs) has been found to be useful in various clinical informatics applications such as disease diagnosis.

Publications

Integrated Multi-omics Analysis Using Variational Autoencoders: Application to Pan-cancer Classification

Abstract: “Different aspects of a clinical sample can be revealed by multiple types of omics data. Integrated analysis of multi-omics data provides a comprehensive view of patients, which has the potential to facilitate more accurate clinical decision making.

Publications

Implementation and relevance of FAIR data principles in biopharmaceutical R&D

Abstract: “Biopharmaceutical industry R&D, and indeed other life sciences R&D such as biomedical, environmental, agricultural and food production, is becoming increasingly data-driven and can significantly improve its efficiency and effectiveness by implementing the FAIR (findable, accessible, interoperable, reusable) guiding principles for scientific data management and stewardship.

Publications

Integrating Semantic Knowledge to Tackle Zero-shot Text Classification

Abstract: “Insufficient or even unavailable training data of emerging classes is a big challenge of many classification tasks, including text classification.