Search Results for author: Peter Szolovits

Found 50 papers, 26 papers with code

emrKBQA: A Clinical Knowledge-Base Question Answering Dataset

1 code implementation NAACL (BioNLP) 2021 Preethi Raghavan, Jennifer J Liang, Diwakar Mahajan, Rachita Chandra, Peter Szolovits

We perform experiments to validate the quality of the dataset and set benchmarks for question to logical form learning that helps answer questions on this dataset.

Clinical Knowledge Knowledge Base Question Answering

Right, No Matter Why: AI Fact-checking and AI Authority in Health-related Inquiry Settings

no code implementations22 Oct 2023 Elena Sergeeva, Anastasia Sergeeva, Huiyun Tang, Kerstin Bongard-Blanchy, Peter Szolovits

Previous research on expert advice-taking shows that humans exhibit two contradictory behaviors: on the one hand, people tend to overvalue their own opinions undervaluing the expert opinion, and on the other, people often defer to other people's advice even if the advice itself is rather obviously wrong.

Fact Checking

Do We Still Need Clinical Language Models?

no code implementations16 Feb 2023 Eric Lehman, Evan Hernandez, Diwakar Mahajan, Jonas Wulff, Micah J. Smith, Zachary Ziegler, Daniel Nadler, Peter Szolovits, Alistair Johnson, Emily Alsentzer

To investigate this question, we conduct an extensive empirical analysis of 12 language models, ranging from 220M to 175B parameters, measuring their performance on 3 different clinical tasks that test their ability to parse and reason over electronic health records.

In-Context Learning

Using Machine Learning to Develop Smart Reflex Testing Protocols

no code implementations1 Feb 2023 Matthew McDermott, Anand Dighe, Peter Szolovits, Yuan Luo, Jason Baron

Here, using the analyte ferritin as an example, we propose an alternative machine learning-based approach to "smart" reflex testing with a wider scope and greater impact than traditional rule-based approaches.

Imputation Management

Structure Inducing Pre-Training

1 code implementation18 Mar 2021 Matthew B. A. McDermott, Brendan Yap, Peter Szolovits, Marinka Zitnik

Based on this review, we introduce a descriptive framework for pre-training that allows for a granular, comprehensive understanding of how relational structure can be induced.

Descriptive Inductive Bias +3

Adversarial Contrastive Pre-training for Protein Sequences

no code implementations31 Jan 2021 Matthew B. A. McDermott, Brendan Yap, Harry Hsu, Di Jin, Peter Szolovits

Recent developments in Natural Language Processing (NLP) demonstrate that large-scale, self-supervised pre-training can be extremely beneficial for downstream tasks.

Language Modelling

What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams

3 code implementations28 Sep 2020 Di Jin, Eileen Pan, Nassim Oufattole, Wei-Hung Weng, Hanyi Fang, Peter Szolovits

Open domain question answering (OpenQA) tasks have been recently attracting more and more attention from the natural language processing (NLP) community.

Multiple-choice Open-Domain Question Answering +1

Joint Modeling of Chest Radiographs and Radiology Reports for Pulmonary Edema Assessment

1 code implementation22 Aug 2020 Geeticka Chauhan, Ruizhi Liao, William Wells, Jacob Andreas, Xin Wang, Seth Berkowitz, Steven Horng, Peter Szolovits, Polina Golland

To take advantage of the rich information present in the radiology reports, we develop a neural network model that is trained on both images and free-text to assess pulmonary edema severity from chest radiographs at inference time.

Image Classification Representation Learning

TransINT: Embedding Implication Rules in Knowledge Graphs with Isomorphic Intersections of Linear Subspaces

1 code implementation AKBC 2020 So Yeon Min, Preethi Raghavan, Peter Szolovits

We propose TransINT, a novel and interpretable KG embedding method that isomorphically preserves the implication ordering among relations in the embedding space.

Knowledge Graphs Link Prediction +2

CheXpert++: Approximating the CheXpert labeler for Speed,Differentiability, and Probabilistic Output

1 code implementation26 Jun 2020 Matthew B. A. McDermott, Tzu Ming Harry Hsu, Wei-Hung Weng, Marzyeh Ghassemi, Peter Szolovits

CheXpert is very useful, but is relatively computationally slow, especially when integrated with end-to-end neural pipelines, is non-differentiable so can't be used in any applications that require gradients to flow through the labeler, and does not yield probabilistic outputs, which limits our ability to improve the quality of the silver labeler through techniques such as active learning.

Active Learning

Expert-Supervised Reinforcement Learning for Offline Policy Learning and Evaluation

2 code implementations NeurIPS 2020 Aaron Sonabend-W, Junwei Lu, Leo A. Celi, Tianxi Cai, Peter Szolovits

However, the adoption of such policies in practice is often challenging, as they are hard to interpret within the application context, and lack measures of uncertainty for the learned policy value and its decisions.

reinforcement-learning Reinforcement Learning (RL) +2

Entity-Enriched Neural Models for Clinical Question Answering

2 code implementations WS 2020 Bhanu Pratap Singh Rawat, Wei-Hung Weng, So Yeon Min, Preethi Raghavan, Peter Szolovits

We explore state-of-the-art neural models for question answering on electronic medical records and improve their ability to generalize better on previously unseen (paraphrased) questions at test time.

Question Answering

Hooks in the Headline: Learning to Generate Headlines with Controlled Styles

1 code implementation ACL 2020 Di Jin, Zhijing Jin, Joey Tianyi Zhou, Lisa Orii, Peter Szolovits

Current summarization systems only produce plain, factual headlines, but do not meet the practical needs of creating memorable titles to increase exposure.

Headline Generation

A Simple Baseline to Semi-Supervised Domain Adaptation for Machine Translation

1 code implementation22 Jan 2020 Di Jin, Zhijing Jin, Joey Tianyi Zhou, Peter Szolovits

State-of-the-art neural machine translation (NMT) systems are data-hungry and perform poorly on new domains with no supervised data.

Language Modelling Machine Translation +4

Neural Token Representations and Negation and Speculation Scope Detection in Biomedical and General Domain Text

no code implementations WS 2019 Elena Sergeeva, Henghui Zhu, Amir Tahmasebi, Peter Szolovits

Since the introduction of context-aware token representation techniques such as Embeddings from Language Models (ELMo) and Bidirectional Encoder Representations from Transformers (BERT), there has been numerous reports on improved performance on a variety of natural language tasks.

Negation Sentence

Representation Learning for Electronic Health Records

no code implementations19 Sep 2019 Wei-Hung Weng, Peter Szolovits

Information in electronic health records (EHR), such as clinical narratives, examination reports, lab measurements, demographics, and other patient encounter entries, can be transformed into appropriate data representations that can be used for downstream clinical machine learning tasks using representation learning.

BIG-bench Machine Learning Representation Learning

A Framework for Relation Extraction Across Multiple Datasets in Multiple Domains

no code implementations WS 2019 Geeticka Chauhan, Matthew McDermott, Peter Szolovits

Our framework will be open-sourced and will aid in performing systematic exploration on the effect of different modeling techniques, pre-processing, training methodologies and evaluation metrics on the 3 datasets to help establish a consensus.

Relation Relation Extraction

Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment

6 code implementations27 Jul 2019 Di Jin, Zhijing Jin, Joey Tianyi Zhou, Peter Szolovits

Machine learning algorithms are often vulnerable to adversarial examples that have imperceptible alterations from the original counterparts but can fool the state-of-the-art models.

Adversarial Text General Classification +2

REflex: Flexible Framework for Relation Extraction in Multiple Domains

1 code implementation WS 2019 Geeticka Chauhan, Matthew B. A. McDermott, Peter Szolovits

Systematic comparison of methods for relation extraction (RE) is difficult because many experiments in the field are not described precisely enough to be completely reproducible and many papers fail to report ablation studies that would highlight the relative contributions of their various combined techniques.

Relation Relation Extraction

Clinically Accurate Chest X-Ray Report Generation

1 code implementation4 Apr 2019 Guanxiong Liu, Tzu-Ming Harry Hsu, Matthew McDermott, Willie Boag, Wei-Hung Weng, Peter Szolovits, Marzyeh Ghassemi

The automatic generation of radiology reports given medical radiographs has significant potential to operationally and improve clinical patient care.

Text Generation

Unsupervised Clinical Language Translation

1 code implementation4 Feb 2019 Wei-Hung Weng, Yu-An Chung, Peter Szolovits

As patients' access to their doctors' clinical notes becomes common, translating professional, clinical jargon to layperson-understandable language is essential to improve patient-clinician communication.

Clinical Language Translation Representation Learning +3

Predicting Blood Pressure Response to Fluid Bolus Therapy Using Attention-Based Neural Networks for Clinical Interpretability

no code implementations3 Dec 2018 Uma M. Girkar, Ryo Uchimido, Li-wei H. Lehman, Peter Szolovits, Leo Celi, Wei-Hung Weng

Determining whether hypotensive patients in intensive care units (ICUs) should receive fluid bolus therapy (FBT) has been an extremely challenging task for intensive care physicians as the corresponding increase in blood pressure has been hard to predict.

regression Time Series +1

Unsupervised Multimodal Representation Learning across Medical Images and Reports

no code implementations21 Nov 2018 Tzu-Ming Harry Hsu, Wei-Hung Weng, Willie Boag, Matthew McDermott, Peter Szolovits

Joint embeddings between medical imaging modalities and associated radiology reports have the potential to offer significant benefits to the clinical community, ranging from cross-domain retrieval to conditional generation of reports to the broader goals of multimodal representation learning.

Representation Learning Retrieval

Implementing a Portable Clinical NLP System with a Common Data Model - a Lisp Perspective

no code implementations15 Nov 2018 Yuan Luo, Peter Szolovits

We also developed a utility to convert an inline annotation format to stand-off annotations to enable the reuse of clinical text datasets with inline annotations.

Computational Phenotyping Domain Adaptation +1

Advancing PICO Element Detection in Biomedical Text via Deep Neural Networks

1 code implementation30 Oct 2018 Di Jin, Peter Szolovits

One is the PubMed-PICO dataset, where our best results outperform the previous best by 5. 5%, 7. 9%, and 5. 8% for P, I, and O elements in terms of F1 score, respectively.

feature selection PICO +2

Hierarchical Neural Networks for Sequential Sentence Classification in Medical Scientific Abstracts

1 code implementation EMNLP 2018 Di Jin, Peter Szolovits

Prevalent models based on artificial neural network (ANN) for sentence classification often classify sentences in isolation without considering the context in which sentences appear.

Benchmarking Classification +4

Racial Disparities and Mistrust in End-of-Life Care

1 code implementation11 Aug 2018 Willie Boag, Harini Suresh, Leo Anthony Celi, Peter Szolovits, Marzyeh Ghassemi

There are established racial disparities in healthcare, including during end-of-life care, when poor communication and trust can lead to suboptimal outcomes for patients and their families.


PICO Element Detection in Medical Text via Long Short-Term Memory Neural Networks

2 code implementations WS 2018 Di Jin, Peter Szolovits

Successful evidence-based medicine (EBM) applications rely on answering clinical questions by analyzing large medical literature databases.

Benchmarking Decision Making +2

Modeling Mistrust in End-of-Life Care

1 code implementation30 Jun 2018 Willie Boag, Harini Suresh, Leo Anthony Celi, Peter Szolovits, Marzyeh Ghassemi

In this work, we characterize the doctor-patient relationship using a machine learning-derived trust score.

BIG-bench Machine Learning Sentiment Analysis

Mapping Unparalleled Clinical Professional and Consumer Languages with Embedding Alignment

no code implementations25 Jun 2018 Wei-Hung Weng, Peter Szolovits

In this work, we utilized the embeddings alignment method for the word mapping between unparalleled clinical professional and consumer language embeddings.

Retrieval Word Embeddings

Towards the Creation of a Large Corpus of Synthetically-Identified Clinical Notes

no code implementations7 Mar 2018 Willie Boag, Tristan Naumann, Peter Szolovits

Clinical notes often describe the most important aspects of a patient's physiology and are therefore critical to medical research.


Representation and Reinforcement Learning for Personalized Glycemic Control in Septic Patients

no code implementations2 Dec 2017 Wei-Hung Weng, Mingwu Gao, Ze He, Susu Yan, Peter Szolovits

This work aims to learn personalized optimal glycemic trajectories for severely ill septic patients by learning data-driven policies to identify optimal targeted blood glucose levels as a reference for clinicians.

reinforcement-learning Reinforcement Learning (RL)

Continuous State-Space Models for Optimal Sepsis Treatment - a Deep Reinforcement Learning Approach

no code implementations23 May 2017 Aniruddh Raghu, Matthieu Komorowski, Leo Anthony Celi, Peter Szolovits, Marzyeh Ghassemi

In this work, we propose a new approach to deduce optimal treatment policies for septic patients by using continuous state-space models and deep reinforcement learning.

Decision Making Reinforcement Learning (RL)

Clinical Intervention Prediction and Understanding using Deep Networks

no code implementations23 May 2017 Harini Suresh, Nathan Hunt, Alistair Johnson, Leo Anthony Celi, Peter Szolovits, Marzyeh Ghassemi

Real-time prediction of clinical interventions remains a challenge within intensive care units (ICUs).

Transfer Learning for Named-Entity Recognition with Neural Networks

no code implementations LREC 2018 Ji Young Lee, Franck Dernoncourt, Peter Szolovits

In particular, we demonstrate that transferring an ANN model trained on a large labeled dataset to another dataset with a limited number of labels improves upon the state-of-the-art results on two different datasets for patient note de-identification.

De-identification named-entity-recognition +3

The Use of Autoencoders for Discovering Patient Phenotypes

no code implementations20 Mar 2017 Harini Suresh, Peter Szolovits, Marzyeh Ghassemi

We use autoencoders to create low-dimensional embeddings of underlying patient phenotypes that we hypothesize are a governing factor in determining how different patients will react to different interventions.

Neural Networks for Joint Sentence Classification in Medical Paper Abstracts

5 code implementations EACL 2017 Franck Dernoncourt, Ji Young Lee, Peter Szolovits

Existing models based on artificial neural networks (ANNs) for sentence classification often do not incorporate the context in which sentences appear, and classify sentences individually.

General Classification Sentence +2

Feature-Augmented Neural Networks for Patient Note De-identification

no code implementations WS 2016 Ji Young Lee, Franck Dernoncourt, Ozlem Uzuner, Peter Szolovits

In this work, we explore a method to incorporate human-engineered features as well as features derived from EHRs to a neural-network-based de-identification system.


De-identification of Patient Notes with Recurrent Neural Networks

1 code implementation10 Jun 2016 Franck Dernoncourt, Ji Young Lee, Ozlem Uzuner, Peter Szolovits

It yields an F1-score of 97. 85 on the i2b2 2014 dataset, with a recall 97. 38 and a precision of 97. 32, and an F1-score of 99. 23 on the MIMIC de-identification dataset, with a recall 99. 25 and a precision of 99. 06.

De-identification Feature Engineering

MIMIC-III, a freely accessible critical care database

2 code implementations Nature 2016 Alistair E.W. Johnson, Tom J. Pollard, Lu Shen, Li-wei H. Lehman, Mengling Feng, Mohammad Ghassemi, Benjamin Moody, Peter Szolovits, Leo Anthony Celi, Roger G. Mark

MIMIC-III (‘Medical Information Mart for Intensive Care’) is a large, single-center database comprising information relating to patients admitted to critical care units at a large tertiary care hospital.

Blood pressure estimation Data Integration +6

Cannot find the paper you are looking for? You can Submit a new open access paper.