Temporal Segmentation for Capturing Snapshots of Patient Histories in Korean Clinical Narrative / 대한의료정보학회지

OBJECTIVES: Clinical discharge summaries provide valuable information about patients' clinical history, which is helpful for the realization of intelligent healthcare applications. The documents tend to take the form of separate segments based on temporal or topical information. If a patient's clinical history can be seen as a consecutive sequence of clinical events, then each temporal segment can be seen as a snapshot, providing a certain clinical context at a specific moment. This study aimed to demonstrate a temporal segmentation method of Korean clinical narratives for identifying textual snapshots of patient history as a proof-of-a-concept. METHODS: Our method uses pattern-based segmentation to approximate human recognition of the temporal or topical shifts in clinical documents. We utilized rheumatic patients' discharge summaries and transformed them into sequences of constituent chunks. We built 97 single pattern functions to denote whether a certain chunk has attributes that indicate that it can be a segment boundary. We manually defined the relationships between the pattern functions to resolve multiple pattern matchings and to make a final decision. RESULTS: The algorithm segmented 30 discharge summaries and processed 1,849 decision points. Three human judges were asked whether they agreed with the algorithm's prediction, and the agreement percentage on the judges' majority opinion was 89.61%. CONCLUSIONS: Although this method is based on manually constructed rules, our findings demonstrate that the proposed algorithm can achieve fairly good segmentation results, and it may be the basis for methodological improvement in the future.

Classificação de coloração imuno-histoquímica combinando cor e textura como descritor / Staining Immunohistochemistry classification blending color and texture as descriptor

O presente trabalho teve por objetivo demonstrar a melhora no desempenho da classificação de coloração imuno-histoquímica em imagens microscópicas, utilizando a abordagem de aprendizado supervisionada que emprega a projeção polinomial da distância de Mahalanobis. Foi definido um descritor de características híbrido, combinando core textura baseada no método Local Binary Pattern, proporcionado inicialmente um descritor 23-dimensional para cada píxel. Uma análise de componentes principais foi realizada e um segundo descritor 12-dimensional foi empregado na avaliação. Os testes foram realizados em imagens e metadados obtidos no The Human Protein Atlas, avaliando uma série de medidas de acerto e erro. Com os resultados encontrados percebeu-se que a utilização do descritor híbrido tornou o processo de classificação mais específico e restritivo nas predições positivas.

This study aimed to demonstrate the improvement in performance of immunohistochemical staining classification in microscopic images using a supervised learning approach that employs the polynomial projection of the Mahalanobis distance. A hybrid feature descriptor was defined by combining color and texture based on Local Binary Pattern method, initially provided a 23-dimensional descriptor, for each pixel. A principal component analysis was performed and a second 12-dimensional descriptor was used in the assay. The tests were performed on images and metadata, obtained on The Human Protein Atlas. With the results it can be seen that the use of hybrid descriptor has made the classification process more specific and restrictive on the positive predictions.

Challenges and Practical Approaches with Word Sense Disambiguation of Acronyms and Abbreviations in the Clinical Domain / 대한의료정보학회지

OBJECTIVES: Although acronyms and abbreviations in clinical text are used widely on a daily basis, relatively little research has focused upon word sense disambiguation (WSD) of acronyms and abbreviations in the healthcare domain. Since clinical notes have distinctive characteristics, it is unclear whether techniques effective for acronym and abbreviation WSD from biomedical literature are sufficient. METHODS: The authors discuss feature selection for automated techniques and challenges with WSD of acronyms and abbreviations in the clinical domain. RESULTS: There are significant challenges associated with the informal nature of clinical text, such as typographical errors and incomplete sentences; difficulty with insufficient clinical resources, such as clinical sense inventories; and obstacles with privacy and security for conducting research with clinical text. Although we anticipated that using sophisticated techniques, such as biomedical terminologies, semantic types, part-of-speech, and language modeling, would be needed for feature selection with automated machine learning approaches, we found instead that simple techniques, such as bag-of-words, were quite effective in many cases. Factors, such as majority sense prevalence and the degree of separateness between sense meanings, were also important considerations. CONCLUSIONS: The first lesson is that a comprehensive understanding of the unique characteristics of clinical text is important for automatic acronym and abbreviation WSD. The second lesson learned is that investigators may find that using simple approaches is an effective starting point for these tasks. Finally, similar to other WSD tasks, an understanding of baseline majority sense rates and separateness between senses is important. Further studies and practical solutions are needed to better address these issues.

Lifelog Agent for Human Activity Pattern Analysis on Health Avatar Platform / 대한의료정보학회지

OBJECTIVES: To provide accurate personalized medical care, it is necessary to gather individual-related data or contextual information regarding the target person. Nowadays a large number of people possess smartphones, which enables sensors in the smartphones to be used for lifelogging. The objective of the study is to analyze human activity pattern by using lifelog agent cooperating with the Health Avatar platform. METHODS: Using the lifelog measured by accelerometer and gyroscope in a smartphone at a 50 Hz rate, the agent reveals how long the user walks, runs, sits, stands, and lies down, and this information is summarized by hours. The summaries are sent to the Health Avatar platform and finally are written in the Continuity of Care Record (CCR) format. RESULTS: The lifelog agent is successfully operated with the Health Avatar platform. In addition, we implement an application that displays the user's activity patterns in a graph and calculates the metabolic equivalent of task based calorie burned by hour or by day using the lifelog of the CCR form to show that the lifelog can be used as medical records. CONCLUSIONS: The agent shows how lifelogs are analyzed and summarized to help activity recognition. We believe that our agent demonstrates a way of incorporating lifelogs into medical care and a way of exploiting lifelogs in a medical format.

Recognizing Temporal Information in Korean Clinical Narratives through Text Normalization / 대한의료정보학회지

OBJECTIVES: Acquiring temporal information is important because knowledge in clinical narratives is time-sensitive. In this paper, we describe an approach that can be used to extract the temporal information found in Korean clinical narrative texts. METHODS: We developed a two-stage system, which employs an exhaustive text analysis phase and a temporal expression recognition phase. Since our target document may include tokens that are made up of both Korean and English text joined together, the minimal semantic units are analyzed and then separated from the concatenated phrases and linguistic derivations within a token using a corpus-based approach to decompose complex tokens. A finite state machine is then used on the minimal semantic units in order to find phrases that possess time-related information. RESULTS: In the experiment, the temporal expressions within Korean clinical narratives were extracted using our system. The system performance was evaluated through the use of 100 discharge summaries from Seoul National University Hospital containing a total of 805 temporal expressions. Our system scored a phrase-level precision and recall of 0.895 and 0.919, respectively. CONCLUSIONS: Finding information in Korean clinical narrative is challenging task, since the text is written in both Korean and English and frequently omits syntactic elements and word spacing, which makes it extremely noisy. This study presents an effective method that can be used to aquire the temporal information found in Korean clinical documents.