Development of message passing-based graph convolutional networks for classifying cancer pathology reports.

BACKGROUND: Applying graph convolutional networks (GCN) to the classification of free-form natural language texts leveraged by graph-of-words features (TextGCN) was studied and confirmed to be an effective means of describing complex natural language texts. However, the text classification models based on the TextGCN possess weaknesses in terms of memory consumption and model dissemination and distribution. In this paper, we present a fast message passing network (FastMPN), implementing a GCN with message passing architecture that provides versatility and flexibility by allowing trainable node embedding and edge weights, helping the GCN model find the better solution. We applied the FastMPN model to the task of clinical information extraction from cancer pathology reports, extracting the following six properties: main site, subsite, laterality, histology, behavior, and grade. RESULTS: We evaluated the clinical task performance of the FastMPN models in terms of micro- and macro-averaged F1 scores. A comparison was performed with the multi-task convolutional neural network (MT-CNN) model. Results show that the FastMPN model is equivalent to or better than the MT-CNN. CONCLUSIONS: Our implementation revealed that our FastMPN model, which is based on the PyTorch platform, can train a large corpus (667,290 training samples) with 202,373 unique words in less than 3 minutes per epoch using one NVIDIA V100 hardware accelerator. Our experiments demonstrated that using this implementation, the clinical task performance scores of information extraction related to tumors from cancer pathology reports were highly competitive.

Automated extraction of information from free text of Spanish oncology pathology reports.

Background: Pathology reports are stored as unstructured, ungrammatical, fragmented, and abbreviated free text with linguistic variability among pathologists. For this reason, tumor information extraction requires a significant human effort. Recording data in an efficient and high-quality format is essential in implementing and establishing a hospital-based-cancer registry. Objective: This study aimed to describe implementing a natural language processing algorithm for oncology pathology reports. Methods: An algorithm was developed to process oncology pathology reports in Spanish to extract 20 medical descriptors. The approach is based on the successive coincidence of regular expressions. Results: The validation was performed with 140 pathological reports. The topography identification was performed manually by humans and the algorithm in all reports. The human identified morphology in 138 reports and by the algorithm in 137. The average fuzzy matching score was 68.3 for Topography and 89.5 for Morphology. Conclusions: A preliminary algorithm validation against human extraction was performed over a small set of reports with satisfactory results. This shows that a regular-expression approach can accurately and precisely extract multiple specimen attributes from free-text Spanish pathology reports. Additionally, we developed a website to facilitate collaborative validation at a larger scale which may be helpful for future research on the subject.

Introducción: Los reportes de patología están almacenados como texto libre sin estructura, gramática, fragmentados o abreviados, con variabilidad lingüística entre patólogos. Por esta razón, la extracción de información de tumores requiere un esfuerzo humano significativo. Almacenar información en un formato eficiente y de alta calidad es esencial para implementar y establecer un registro hospitalario de cáncer. Objetivo: Este estudio busca describir la implementación de un algoritmo de Procesamiento de Lenguaje Natural para reportes de patología oncológica. Métodos: Desarrollamos un algoritmo para procesar reportes de patología oncológica en Español, con el objetivo de extraer 20 descriptores médicos. El abordaje se basa en la coincidencia sucesiva de expresiones regulares. Resultados: La validación se hizo con 140 reportes de patología. La identificación topográfica se realizó por humanos y por el algoritmo en todos los reportes. La morfología fue identificada por humanos en 138 reportes y por el algoritmo en 137. El valor de coincidencias parciales (fuzzy matches) promedio fue de 68.3 para Topografía y 89.5 para Morfología. Conclusiones: Se hizo una validación preliminar del algoritmo contra extracción humana sobre un pequeño grupo de reportes, con resultados satisfactorios. Esto muestra que múltiples atributos del espécimen pueden ser extraídos de manera precisa de texto libre de reportes de patología en Español, usando un abordaje de expresiones regulares. Adicionalmente, desarrollamos una página web para facilitar la validación colaborativa a gran escala, lo que puede ser beneficioso para futuras investigaciones en el tema.

Automated extraction of information from free text of Spanish oncology pathology reports

Background: Pathology reports are stored as unstructured, ungrammatical, fragmented, and abbreviated free text with linguistic variability among pathologists. For this reason, tumor information extraction requires a significant human effort. Recording data in an efficient and high-quality format is essential in implementing and establishing a hospital-based-cancer registry Objective: This study aimed to describe implementing a natural language processing algorithm for oncology pathology reports. Methods: An algorithm was developed to process oncology pathology reports in Spanish to extract 20 medical descriptors. The approach is based on the successive coincidence of regular expressions. Results: The validation was performed with 140 pathological reports. The topography identification was performed manually by humans and the algorithm in all reports. The human identified morphology in 138 reports and by the algorithm in 137. The average fuzzy matching score was 68.3 for Topography and 89.5 for Morphology. Conclusions: A preliminary algorithm validation against human extraction was performed over a small set of reports with satisfactory results. This shows that a regular-expression approach can accurately and precisely extract multiple specimen attributes from free-text Spanish pathology reports. Additionally, we developed a website to facilitate collaborative validation at a larger scale which may be helpful for future research on the subject.

Introducción: Los reportes de patología están almacenados como texto libre sin estructura, gramática, fragmentados o abreviados, con variabilidad lingüística entre patólogos. Por esta razón, la extracción de información de tumores requiere un esfuerzo humano significativo. Almacenar información en un formato eficiente y de alta calidad es esencial para implementar y establecer un registro hospitalario de cáncer. Objetivo: Este estudio busca describir la implementación de un algoritmo de Procesamiento de Lenguaje Natural para reportes de patología oncológica. Métodos: Desarrollamos un algoritmo para procesar reportes de patología oncológica en Español, con el objetivo de extraer 20 descriptores médicos. El abordaje se basa en la coincidencia sucesiva de expresiones regulares. Resultados: La validación se hizo con 140 reportes de patología. La identificación topográfica se realizó por humanos y por el algoritmo en todos los reportes. La morfología fue identificada por humanos en 138 reportes y por el algoritmo en 137. El valor de coincidencias parciales (fuzzy matches) promedio fue de 68.3 para Topografía y 89.5 para Morfología. Conclusiones: Se hizo una validación preliminar del algoritmo contra extracción humana sobre un pequeño grupo de reportes, con resultados satisfactorios. Esto muestra que múltiples atributos del espécimen pueden ser extraídos de manera precisa de texto libre de reportes de patología en Español, usando un abordaje de expresiones regulares. Adicionalmente, desarrollamos una página web para facilitar la validación colaborativa a gran escala, lo que puede ser beneficioso para futuras investigaciones en el tema.

Automatic information extraction from childhood cancer pathology reports.

Objectives: The International Classification of Childhood Cancer (ICCC) facilitates the effective classification of a heterogeneous group of cancers in the important pediatric population. However, there has been no development of machine learning models for the ICCC classification. We developed deep learning-based information extraction models from cancer pathology reports based on the ICD-O-3 coding standard. In this article, we describe extending the models to perform ICCC classification. Materials and Methods: We developed 2 models, ICD-O-3 classification and ICCC recoding (Model 1) and direct ICCC classification (Model 2), and 4 scenarios subject to the training sample size. We evaluated these models with a corpus consisting of 29 206 reports with age at diagnosis between 0 and 19 from 6 state cancer registries. Results: Our findings suggest that the direct ICCC classification (Model 2) is substantially better than reusing the ICD-O-3 classification model (Model 1). Applying the uncertainty quantification mechanism to assess the confidence of the algorithm in assigning a code demonstrated that the model achieved a micro-F1 score of 0.987 while abstaining (not sufficiently confident to assign a code) on only 14.8% of ambiguous pathology reports. Conclusions: Our experimental results suggest that the machine learning-based automatic information extraction from childhood cancer pathology reports in the ICCC is a reliable means of supplementing human annotators at state cancer registries by reading and abstracting the majority of the childhood cancer pathology reports accurately and reliably.

Deep active learning for classifying cancer pathology reports.

BACKGROUND: Automated text classification has many important applications in the clinical setting; however, obtaining labelled data for training machine learning and deep learning models is often difficult and expensive. Active learning techniques may mitigate this challenge by reducing the amount of labelled data required to effectively train a model. In this study, we analyze the effectiveness of 11 active learning algorithms on classifying subsite and histology from cancer pathology reports using a Convolutional Neural Network as the text classification model. RESULTS: We compare the performance of each active learning strategy using two differently sized datasets and two different classification tasks. Our results show that on all tasks and dataset sizes, all active learning strategies except diversity-sampling strategies outperformed random sampling, i.e., no active learning. On our large dataset (15K initial labelled samples, adding 15K additional labelled samples each iteration of active learning), there was no clear winner between the different active learning strategies. On our small dataset (1K initial labelled samples, adding 1K additional labelled samples each iteration of active learning), marginal and ratio uncertainty sampling performed better than all other active learning techniques. We found that compared to random sampling, active learning strongly helps performance on rare classes by focusing on underrepresented classes. CONCLUSIONS: Active learning can save annotation cost by helping human annotators efficiently and intelligently select which samples to label. Our results show that a dataset constructed using effective active learning techniques requires less than half the amount of labelled data to achieve the same performance as a dataset constructed using random sampling.

Privacy-Preserving Deep Learning NLP Models for Cancer Registries.

Population cancer registries can benefit from Deep Learning (DL) to automatically extract cancer characteristics from the high volume of unstructured pathology text reports they process annually. The success of DL to tackle this and other real-world problems is proportional to the availability of large labeled datasets for model training. Although collaboration among cancer registries is essential to fully exploit the promise of DL, privacy and confidentiality concerns are main obstacles for data sharing across cancer registries. Moreover, DL for natural language processing (NLP) requires sharing a vocabulary dictionary for the embedding layer which may contain patient identifiers. Thus, even distributing the trained models across cancer registries causes a privacy violation issue. In this paper, we propose DL NLP model distribution via privacy-preserving transfer learning approaches without sharing sensitive data. These approaches are used to distribute a multitask convolutional neural network (MT-CNN) NLP model among cancer registries. The model is trained to extract six key cancer characteristics - tumor site, subsite, laterality, behavior, histology, and grade - from cancer pathology reports. Using 410,064 pathology documents from two cancer registries, we compare our proposed approach to conventional transfer learning without privacy-preserving, single-registry models, and a model trained on centrally hosted data. The results show that transfer learning approaches including data sharing and model distribution outperform significantly the single-registry model. In addition, the best performing privacy-preserving model distribution approach achieves statistically indistinguishable average micro- and macro-F1 scores across all extraction tasks (0.823,0.580) as compared to the centralized model (0.827,0.585).

Automatic extraction of cancer registry reportable information from free-text pathology reports using multitask convolutional neural networks.

OBJECTIVE: We implement 2 different multitask learning (MTL) techniques, hard parameter sharing and cross-stitch, to train a word-level convolutional neural network (CNN) specifically designed for automatic extraction of cancer data from unstructured text in pathology reports. We show the importance of learning related information extraction (IE) tasks leveraging shared representations across the tasks to achieve state-of-the-art performance in classification accuracy and computational efficiency. MATERIALS AND METHODS: Multitask CNN (MTCNN) attempts to tackle document information extraction by learning to extract multiple key cancer characteristics simultaneously. We trained our MTCNN to perform 5 information extraction tasks: (1) primary cancer site (65 classes), (2) laterality (4 classes), (3) behavior (3 classes), (4) histological type (63 classes), and (5) histological grade (5 classes). We evaluated the performance on a corpus of 95 231 pathology documents (71 223 unique tumors) obtained from the Louisiana Tumor Registry. We compared the performance of the MTCNN models against single-task CNN models and 2 traditional machine learning approaches, namely support vector machine (SVM) and random forest classifier (RFC). RESULTS: MTCNNs offered superior performance across all 5 tasks in terms of classification accuracy as compared with the other machine learning models. Based on retrospective evaluation, the hard parameter sharing and cross-stitch MTCNN models correctly classified 59.04% and 57.93% of the pathology reports respectively across all 5 tasks. The baseline models achieved 53.68% (CNN), 46.37% (RFC), and 36.75% (SVM). Based on prospective evaluation, the percentages of correctly classified cases across the 5 tasks were 60.11% (hard parameter sharing), 58.13% (cross-stitch), 51.30% (single-task CNN), 42.07% (RFC), and 35.16% (SVM). Moreover, hard parameter sharing MTCNNs outperformed the other models in computational efficiency by using about the same number of trainable parameters as a single-task CNN. CONCLUSIONS: The hard parameter sharing MTCNN offers superior classification accuracy for automated coding support of pathology documents across a wide range of cancers and multiple information extraction tasks while maintaining similar training and inference time as those of a single task-specific model.

Classifying cancer pathology reports with hierarchical self-attention networks.

We introduce a deep learning architecture, hierarchical self-attention networks (HiSANs), designed for classifying pathology reports and show how its unique architecture leads to a new state-of-the-art in accuracy, faster training, and clear interpretability. We evaluate performance on a corpus of 374,899 pathology reports obtained from the National Cancer Institute's (NCI) Surveillance, Epidemiology, and End Results (SEER) program. Each pathology report is associated with five clinical classification tasks - site, laterality, behavior, histology, and grade. We compare the performance of the HiSAN against other machine learning and deep learning approaches commonly used on medical text data - Naive Bayes, logistic regression, convolutional neural networks, and hierarchical attention networks (the previous state-of-the-art). We show that HiSANs are superior to other machine learning and deep learning text classifiers in both accuracy and macro F-score across all five classification tasks. Compared to the previous state-of-the-art, hierarchical attention networks, HiSANs not only are an order of magnitude faster to train, but also achieve about 1% better relative accuracy and 5% better relative macro F-score.