Neural transfer learning for assigning diagnosis codes to EMRs

Asymmetric cross-modal attention network with multimodal augmented mixup for medical visual question answering

Insufficient training data is a common barrier to effectively learn multimodal information interactions and question semantics in existing medical Visual Question Answering (VQA) models. This paper proposes a new Asymmetric Cross Modal Attention network called ACMA, which constructs an image-guided attention and a question-guided attention to improve multimodal interactions from insufficient data. In addition, a Semantic Understanding Auxiliary (SUA) in the question-guided attention is newly designed to learn rich semantic embeddings for improving model performance on question understanding by integrating word-level and sentence-level information. Moreover, we propose a new data augmentation method called Multimodal Augmented Mixup (MAM) to train the ACMA, denoted as ACMA-MAM. The MAM incorporates various data augmentations and a vanilla mixup strategy to generate more non-repetitive data, which avoids time-consuming artificial data annotations and improves model generalization capability. Our ACMA-MAM outperforms state-of-the-art models on three publicly accessible medical VQA datasets (VQA-Rad, VQA-Slake, and PathVQA) with accuracies of 76.14 %, 83.13 %, and 53.83 % respectively, achieving improvements of 2.00 %, 1.32 %, and 1.59 % accordingly. Moreover, our model achieves F1 scores of 78.33 %, 82.83 %, and 51.86 %, surpassing the state-of-the-art models by 2.80 %, 1.15 %, and 1.37 % respectively.

What Is Machine Learning, Artificial Neural Networks and Deep Learning?-Examples of Practical Applications in Medicine

Machine learning (ML), artificial neural networks (ANNs), and deep learning (DL) are all topics that fall under the heading of artificial intelligence (AI) and have gained popularity in recent years. ML involves the application of algorithms to automate decision-making processes using models that have not been manually programmed but have been trained on data. ANNs that are a part of ML aim to simulate the structure and function of the human brain. DL, on the other hand, uses multiple layers of interconnected neurons. This enables the processing and analysis of large and complex databases. In medicine, these techniques are being introduced to improve the speed and efficiency of disease diagnosis and treatment. Each of the AI techniques presented in the paper is supported with an example of a possible medical application. Given the rapid development of technology, the use of AI in medicine shows promising results in the context of patient care. It is particularly important to keep a close eye on this issue and conduct further research in order to fully explore the potential of ML, ANNs, and DL, and bring further applications into clinical use in the future.

Integrating domain knowledge for biomedical text analysis into deep learning: A survey

The past decade has witnessed an explosion of textual information in the biomedical field. Biomedical texts provide a basis for healthcare delivery, knowledge discovery, and decision-making. Over the same period, deep learning has achieved remarkable performance in biomedical natural language processing, however, its development has been limited by well-annotated datasets and interpretability. To solve this, researchers have considered combining domain knowledge (such as biomedical knowledge graph) with biomedical data, which has become a promising means of introducing more information into biomedical datasets and following evidence-based medicine. This paper comprehensively reviews more than 150 recent literature studies on incorporating domain knowledge into deep learning models to facilitate typical biomedical text analysis tasks, including information extraction, text classification, and text generation. We eventually discuss various challenges and future directions.

Applications of Artificial Intelligence in the Radiology Roundtrip: Process Streamlining, Workflow Optimization, and Beyond

There are many impactful applications of artificial intelligence (AI) in the electronic radiology roundtrip and the patient's journey through the healthcare system that go beyond diagnostic applications. These tools have the potential to improve quality and safety, optimize workflow, increase efficiency, and increase patient satisfaction. In this article, we review the role of AI for process improvement and workflow enhancement which includes applications beginning from the time of order entry, scan acquisition, applications supporting the image interpretation task, and applications supporting tasks after image interpretation such as result communication. These non-diagnostic workflow and process optimization tasks are an important part of the arsenal of potential AI tools that can streamline day to day clinical practice and patient care.

Automated detection of mild cognitive impairment and dementia from voice recordings: A natural language processing approach

INTRODUCTION

Automated computational assessment of neuropsychological tests would enable widespread, cost-effective screening for dementia.

METHODS

A novel natural language processing approach is developed and validated to identify different stages of dementia based on automated transcription of digital voice recordings of subjects' neuropsychological tests conducted by the Framingham Heart Study (n = 1084). Transcribed sentences from the test were encoded into quantitative data and several models were trained and tested using these data and the participants' demographic characteristics.

RESULTS

Average area under the curve (AUC) on the held-out test data reached 92.6%, 88.0%, and 74.4% for differentiating Normal cognition from Dementia, Normal or Mild Cognitive Impairment (MCI) from Dementia, and Normal from MCI, respectively.

DISCUSSION

The proposed approach offers a fully automated identification of MCI and dementia based on a recorded neuropsychological test, providing an opportunity to develop a remote screening tool that could be adapted easily to any language.

[Artificial intelligence for medical information departments : construction and evaluation of a decision-making tool to identify and prioritize stays of which the PMSI coding could be optimized, and to ensure the revenues generated by activity-based pricing]

BACKGROUND

Medical Information Departments help to optimize the hospital revenues generated by activity-based pricing. A review of medical files, selected after the targeting of coding summaries, is organized. The aim is to make any corrections to the diagnoses or coded procedures with a potential impact on the pricing of the stay. Targeting is of major importance as a means of concentrating resources on the files for which coding can be effectively improved. The tools available for targeting can be optimized. We have developed a decision-making support tool to make targeting more efficient. The objective of our study was to evaluate the performance of this tool.

METHODS

The tool combines an artificial intelligence module with a rule-based expert module. A predictive score is assigned to each coding summary that reflects the probability of a revalued stay. Evaluation of the performance of this tool was based on a sample of 400 stays of at least 3 nights of patients hospitalized at the Paris Saint-Joseph Hospital from 1^st November to 31^st December 2019. Each stay was reviewed by a coding expert, without knowledge of the score assigned and without help from expert queries. Two main assessment criteria were used: area under the ROC curve and positive predictive value (PPV).

RESULTS

The area under the ROC curve was 0.70 (CI 95% [0.64-0.76]). With a revalued coding rate of 32%, PPV was 41% for scores above 5, 65% for scores above 8, 88% for scores above 9.

CONCLUSION

The study made it possible to validate the performance of the tool. The implementation of new variables could further increase its performance. This is an area of development to be considered, particularly with in view of generalizing individual invoicing in hospitals.

Towards the Development of a Substance Abuse Index (SEI) through Informatics

Substance abuse or drug dependence is a prevalent phenomenon, and is on the rise in United States. Important contributing factors for the prevalence are the addictive nature of certain medicinal/prescriptive drugs, individual dispositions (biological, physiological, and psychological), and other external influences (e.g., pharmaceutical advertising campaigns). However, currently there is no comprehensive computational or machine learning framework that allows systematic studies of substance abuse and its factors with majority of the works using subjective surveys questionnaires and focusing on classification techniques. Lacking standardized methods and/or measures to prescribe medication and to study substance abuse makes it difficult to advance through collective research efforts. Thus, in this paper, we propose to test the feasibility of developing a, objective substance effect index, SEI, that can measure the tendency of an individual towards substance abuse. To that end, we combine the benefits of Electronics Medical Records (EMR) with machine learning technology by defining SEI as a function of EMR data and using logistics regression to obtain a closed form expression for SEI. We conduct various evaluations to validate the proposed model, and the results show that further work towards the development of SEI will not only provide researchers with standard computational measure for substance abuse, but may also allow them to study certain attribute interactions to gain further insights into substance abuse tendencies.

Explainable ICD multi-label classification of EHRs in Spanish with convolutional attention

BACKGROUND

This work deals with Natural Language Processing applied to Electronic Health Records (EHRs). EHRs are coded following the International Classification of Diseases (ICD) leading to a multi-label classification problem. Previously proposed approaches act as black-boxes without giving further insights. Explainable Artificial Intelligence (XAI) helps to clarify what brought the model to make the predictions.

GOAL

This work aims to obtain explainable predictions of the diseases and procedures contained in EHRs. As an application, we show visualizations of the attention stored and propose a prototype of a Decision Support System (DSS) that highlights the text that motivated the choice of each of the proposed ICD codes.

METHODS

Convolutional Neural Networks (CNNs) with attention mechanisms were used. Attention mechanisms allow to detect which part of the input (EHRs) motivate the output (medical codes), producing explainable predictions.

RESULTS

We successfully applied methods in a Spanish corpus getting challenging results. Finally, we presented the idea of extracting the chronological order of the ICDs in a given EHR by anchoring the codes to different stages of the clinical admission.

CONCLUSIONS

We found that explainable deep learning models applied to predict medical codes store helpful information that could be used to assist medical experts while reaching a solid performance. In particular, we show that the information stored in the attention mechanisms enables DSS and a shallow chronology of diagnoses.

A Review of Recent Work in Transfer Learning and Domain Adaptation for Natural Language Processing of Electronic Health Records

Objectives: We survey recent work in biomedical NLP on building more adaptable or generalizable models, with a focus on work dealing with electronic health record (EHR) texts, to better understand recent trends in this area and identify opportunities for future research.

Methods: We searched PubMed, the Institute of Electrical and Electronics Engineers (IEEE), the Association for Computational Linguistics (ACL) anthology, the Association for the Advancement of Artificial Intelligence (AAAI) proceedings, and Google Scholar for the years 2018-2020. We reviewed abstracts to identify the most relevant and impactful work, and manually extracted data points from each of these papers to characterize the types of methods and tasks that were studied, in which clinical domains, and current state-of-the-art results.

Results: The ubiquity of pre-trained transformers in clinical NLP research has contributed to an increase in domain adaptation and generalization-focused work that uses these models as the key component. Most recently, work has started to train biomedical transformers and to extend the fine-tuning process with additional domain adaptation techniques. We also highlight recent research in cross-lingual adaptation, as a special case of adaptation.

Conclusions: While pre-trained transformer models have led to some large performance improvements, general domain pre-training does not always transfer adequately to the clinical domain due to its highly specialized language. There is also much work to be done in showing that the gains obtained by pre-trained transformers are beneficial in real world use cases. The amount of work in domain adaptation and transfer learning is limited by dataset availability and creating datasets for new domains is challenging. The growing body of research in languages other than English is encouraging, and more collaboration between researchers across the language divide would likely accelerate progress in non-English clinical NLP.

Neural Machine Translation-Based Automated Current Procedural Terminology Classification System Using Procedure Text: Development and Validation Study

BACKGROUND

Administrative costs for billing and insurance-related activities in the United States are substantial. One critical cause of the high overhead of administrative costs is medical billing errors. With advanced deep learning techniques, developing advanced models to predict hospital and professional billing codes has become feasible. These models can be used for administrative cost reduction and billing process improvements.

OBJECTIVE

In this study, we aim to develop an automated anesthesiology current procedural terminology (CPT) prediction system that translates manually entered surgical procedure text into standard forms using neural machine translation (NMT) techniques. The standard forms are calculated using similarity scores to predict the most appropriate CPT codes. Although this system aims to enhance medical billing coding accuracy to reduce administrative costs, we compare its performance with that of previously developed machine learning algorithms.

METHODS

We collected and analyzed all operative procedures performed at Michigan Medicine between January 2017 and June 2019 (2.5 years). The first 2 years of data were used to train and validate the existing models and compare the results from the NMT-based model. Data from 2019 (6-month follow-up period) were then used to measure the accuracy of the CPT code prediction. Three experimental settings were designed with different data types to evaluate the models. Experiment 1 used the surgical procedure text entered manually in the electronic health record. Experiment 2 used preprocessing of the procedure text. Experiment 3 used preprocessing of the combined procedure text and preoperative diagnoses. The NMT-based model was compared with the support vector machine (SVM) and long short-term memory (LSTM) models.

RESULTS

The NMT model yielded the highest top-1 accuracy in experiments 1 and 2 at 81.64% and 81.71% compared with the SVM model (81.19% and 81.27%, respectively) and the LSTM model (80.96% and 81.07%, respectively). The SVM model yielded the highest top-1 accuracy of 84.30% in experiment 3, followed by the LSTM model (83.70%) and the NMT model (82.80%). In experiment 3, the addition of preoperative diagnoses showed 3.7%, 3.2%, and 1.3% increases in the SVM, LSTM, and NMT models in top-1 accuracy over those in experiment 2, respectively. For top-3 accuracy, the SVM, LSTM, and NMT models achieved 95.64%, 95.72%, and 95.60% for experiment 1, 95.75%, 95.67%, and 95.69% for experiment 2, and 95.88%, 95.93%, and 95.06% for experiment 3, respectively.

CONCLUSIONS

This study demonstrates the feasibility of creating an automated anesthesiology CPT classification system based on NMT techniques using surgical procedure text and preoperative diagnosis. Our results show that the performance of the NMT-based CPT prediction system is equivalent to that of the SVM and LSTM prediction models. Importantly, we found that including preoperative diagnoses improved the accuracy of using the procedure text alone.

An Artificial Intelligence-Assisted Method for Dementia Detection Using Images from the Clock Drawing Test

BACKGROUND

Widespread dementia detection could increase clinical trial candidates and enable appropriate interventions. Since the Clock Drawing Test (CDT) can be potentially used for diagnosing dementia-related disorders, it can be leveraged to develop a computer-aided screening tool.

OBJECTIVE

To evaluate if a machine learning model that uses images from the CDT can predict mild cognitive impairment or dementia.

METHODS

Images of an analog clock drawn by 3,263 cognitively intact and 160 impaired subjects were collected during in-person dementia evaluations by the Framingham Heart Study. We processed the CDT images, participant's age, and education level using a deep learning algorithm to predict dementia status.

RESULTS

When only the CDT images were used, the deep learning model predicted dementia status with an area under the receiver operating characteristic curve (AUC) of 81.3% ± 4.3%. A composite logistic regression model using age, level of education, and the predictions from the CDT-only model, yielded an average AUC and average F1 score of 91.9% ±1.1% and 94.6% ±0.4%, respectively.

CONCLUSION

Our modeling framework establishes a proof-of-principle that deep learning can be applied on images derived from the CDT to predict dementia status. When fully validated, this approach can offer a cost-effective and easily deployable mechanism for detecting cognitive impairment.

Literature Retrieval for Precision Medicine with Neural Matching and Faceted Summarization

Information retrieval (IR) for precision medicine (PM) often involves looking for multiple pieces of evidence that characterize a patient case. This typically includes at least the name of a condition and a genetic variation that applies to the patient. Other factors such as demographic attributes, comorbidities, and social determinants may also be pertinent. As such, the retrieval problem is often formulated as ad hoc search but with multiple facets (e.g., disease, mutation) that may need to be incorporated. In this paper, we present a document reranking approach that combines neural query-document matching and text summarization toward such retrieval scenarios. Our architecture builds on the basic BERT model with three specific components for reranking: (a). document-query matching (b). keyword extraction and (c). facet-conditioned abstractive summarization. The outcomes of (b) and (c) are used to essentially transform a candidate document into a concise summary that can be compared with the query at hand to compute a relevance score. Component (a) directly generates a matching score of a candidate document for a query. The full architecture benefits from the complementary potential of document-query matching and the novel document transformation approach based on summarization along PM facets. Evaluations using NIST's TREC-PM track datasets (2017-2019) show that our model achieves state-of-the-art performance. To foster reproducibility, our code is made available here: https://github.com/bionlproc/text-summ-for-doc-retrieval.

Artificial Intelligence Applications for Workflow, Process Optimization and Predictive Analytics

There is great potential for artificial intelligence (AI) applications, especially machine learning and natural language processing, in medical imaging. Much attention has been garnered by the image analysis tasks for diagnostic decision support and precision medicine, but there are many other potential applications of AI in radiology and have potential to enhance all levels of the radiology workflow and practice, including workflow optimization and support for interpretation tasks, quality and safety, and operational efficiency. This article reviews the important potential applications of informatics and AI related to process improvement and operations in the radiology department.

Automated ICD-10 code assignment of nonstandard diagnoses via a two-stage framework

An electronic medical record (EMR) is a rich source of clinical information for medical studies. Each physician usually has his or her own way to describe a patient's diagnosis. This results in many different ways to describe the same disease, which produces a large number of informal nonstandard diagnoses in EMRs. The Tenth Revision of International Classification of Diseases (ICD-10) is a medical classification list of codes for diagnoses. Automated ICD-10 code assignment of the nonstandard diagnosis is an important way to improve the quality of the medical study. However, manual coding is expensive, time-consuming and inefficient. Moreover, terminology in the standard diagnostic library comprises approximately 23,000 subcategory (6-digit) codes. Classifying the entire set of subcategory codes is extremely challenging. ICD-10 codes in the standard diagnostic library are organized hierarchically, and each category code (3-digit) relates to several or dozens of subcategory (6-digit) codes. Based on the hierarchical structure of the ICD-10 code, we propose a two-stage ICD-10 code assignment framework, which examines the entire category codes (approximately 1900) and searches the subcategory codes under the specific category code. Furthermore, since medical coding datasets are plagued with a training data sparsity issue, we introduce more supervised information to overcome this issue. Compared with the method that searches within approximately 23,000 subcategory codes, our approach requires examination of a considerably reduced number of codes. Extensive experiments show that our framework can improve the performance of the automated code assignment.

Construction of a semi-automatic ICD-10 coding system

Background

The International Classification of Diseases, 10th Revision (ICD-10) has been widely used to describe the diagnosis information of patients. Automatic ICD-10 coding is important because manually assigning codes is expensive, time consuming and error prone. Although numerous approaches have been developed to explore automatic coding, few of them have been applied in practice. Our aim is to construct a practical, automatic ICD-10 coding machine to improve coding efficiency and quality in daily work.

Methods

In this study, we propose the use of regular expressions (regexps) to establish a correspondence between diagnosis codes and diagnosis descriptions in outpatient settings and at admission and discharge. The description models of the regexps were embedded in our upgraded coding system, which queries a diagnosis description and assigns a unique diagnosis code. Like most studies, the precision (P), recall (R), F-measure (F) and overall accuracy (A) were used to evaluate the system performance. Our study had two stages. The datasets were obtained from the diagnosis information on the homepage of the discharge medical record. The testing sets were from October 1, 2017 to April 30, 2018 and from July 1, 2018 to January 31, 2019.

Results

The values of P were 89.27 and 88.38% in the first testing phase and the second testing phase, respectively, which demonstrate high precision. The automatic ICD-10 coding system completed more than 160,000 codes in 16 months, which reduced the workload of the coders. In addition, a comparison between the amount of time needed for manual coding and automatic coding indicated the effectiveness of the system-the time needed for automatic coding takes nearly 100 times less than manual coding.

Conclusions

Our automatic coding system is well suited for the coding task. Further studies are warranted to perfect the description models of the regexps and to develop synthetic approaches to improve system performance.

Cross-registry neural domain adaptation to extract mutational test results from pathology reports

OBJECTIVE

We study the performance of machine learning (ML) methods, including neural networks (NNs), to extract mutational test results from pathology reports collected by cancer registries. Given the lack of hand-labeled datasets for mutational test result extraction, we focus on the particular use-case of extracting Epidermal Growth Factor Receptor mutation results in non-small cell lung cancers. We explore the generalization of NNs across different registries where our goals are twofold: (1) to assess how well models trained on a registry's data port to test data from a different registry and (2) to assess whether and to what extent such models can be improved using state-of-the-art neural domain adaptation techniques under different assumptions about what is available (labeled vs unlabeled data) at the target registry site.

MATERIALS AND METHODS

We collected data from two registries: the Kentucky Cancer Registry (KCR) and the Fred Hutchinson Cancer Research Center (FH) Cancer Surveillance System. We combine NNs with adversarial domain adaptation to improve cross-registry performance. We compare to other classifiers in the standard supervised classification, unsupervised domain adaptation, and supervised domain adaptation scenarios.

RESULTS

The performance of ML methods varied between registries. To extract positive results, the basic convolutional neural network (CNN) had an F1 of 71.5% on the KCR dataset and 95.7% on the FH dataset. For the KCR dataset, the CNN F1 results were low when trained on FH data (Positive F1: 23%). Using our proposed adversarial CNN, without any labeled data, we match the F1 of the models trained directly on each target registry's data. The adversarial CNN F1 improved when trained on FH and applied to KCR dataset (Positive F1: 70.8%). We found similar performance improvements when we trained on KCR and tested on FH reports (Positive F1: 45% to 96%).

CONCLUSION

Adversarial domain adaptation improves the performance of NNs applied to pathology reports. In the unsupervised domain adaptation setting, we match the performance of models that are trained directly on target registry's data by using source registry's labeled data and unlabeled examples from the target registry.