Understanding headache classification coding within the veterans health administration using ICD-9-CM and ICD-10-CM in fiscal years 2014-2017.

OBJECTIVES: Understand the continuity and changes in headache not-otherwise-specified (NOS), migraine, and post-traumatic headache (PTH) diagnoses after the transition from ICD-9-CM to ICD-10-CM in the Veterans Health Administration (VHA). BACKGROUND: Headache is one of the most commonly diagnosed chronic conditions managed within primary and specialty care clinics. The VHA transitioned from ICD-9-CM to ICD-10-CM on October-1-2015. The effect transitioning on coding of specific headache diagnoses is unknown. Accuracy of headache diagnosis is important since different headache types respond to different treatments. METHODS: We mapped headache diagnoses from ICD-9-CM (FY 2014/2015) onto ICD-10-CM (FY 2016/2017) and computed coding proportions two years before/after the transition in VHA. We used queries to determine the change in transition pathways. We report the odds of ICD-10-CM coding associated with ICD-9-CM controlling for provider type, and patient age, sex, and race/ethnicity. RESULTS: Only 37%, 58% and 34% of patients with ICD-9-CM coding of NOS, migraine, and PTH respectively had an ICD-10-CM headache diagnosis. Of those with an ICD-10-CM diagnosis, 73-79% had a single headache diagnosis. The odds ratios for receiving the same code in both ICD-9-CM and ICD-10-CM after adjustment for ICD-9-CM and ICD-10-CM headache comorbidities and sociodemographic factors were high (range 6-26) and statistically significant. Specifically, 75% of patients with headache NOS had received one headache diagnoses (Adjusted headache NOS-ICD-9-CM OR for headache NOS-ICD-10-CM = 6.1, 95% CI 5.89-6.32. 79% of migraineurs had one headache diagnoses, mostly migraine (Adjusted migraine-ICD-9-CM OR for migraine-ICD-10-CM = 26.43, 95% CI 25.51-27.38). The same held true for PTH (Adjusted PTH-ICD-9-CM OR for PTH-ICD-10-CM = 22.92, 95% CI: 18.97-27.68). These strong associations remained after adjustment for specialist care in ICD-10-CM follow-up period. DISCUSSION: The majority of people with ICD-9-CM headache diagnoses did not have an ICD-10-CM headache diagnosis. However, a given diagnosis in ICD-9-CM by a primary care provider (PCP) was significantly predictive of its assignment in ICD-10-CM as was seeing either a neurologist or physiatrist (compared to a generalist) for an ICD-10-CM headache diagnosis. CONCLUSION: When a veteran had a specific diagnosis in ICD-9-CM, the odds of being coded with the same diagnosis in ICD-10-CM were significantly higher. Specialist visit during the ICD-10-CM period was independently associated with all three ICD-10-CM headaches.

Utilizing a multi-class classification approach to detect therapeutic and recreational misuse of opioids on Twitter.

BACKGROUND: Opioid misuse (OM) is a major health problem in the United States, and can lead to addiction and fatal overdose. We sought to employ natural language processing (NLP) and machine learning to categorize Twitter chatter based on the motive of OM. MATERIALS AND METHODS: We collected data from Twitter using opioid-related keywords, and manually annotated 6988 tweets into three classes-No-OM, Pain-related-OM, and Recreational-OM-with the No-OM class representing tweets indicating no use/misuse, and the Pain-related misuse and Recreational-misuse classes representing misuse for pain or recreation/addiction. We trained and evaluated multi-class classifiers, and performed term-level k-means clustering to assess whether there were terms closely associated with the three classes. RESULTS: On a held-out test set of 1677 tweets, a transformer-based classifier (XLNet) achieved the best performance with F1-score of 0.71 for the Pain-misuse class, and 0.79 for the Recreational-misuse class. Macro- and micro-averaged F1-scores over all classes were 0.82 and 0.92, respectively. Content-analysis using clustering revealed distinct clusters of terms associated with each class. DISCUSSION: While some past studies have attempted to automatically detect opioid misuse, none have further characterized the motive for misuse. Our multi-class classification approach using XLNet showed promising performance, including in detecting the subtle differences between pain-related and recreation-related misuse. The distinct clustering of class-specific keywords may help conduct targeted data collection, overcoming under-representation of minority classes. CONCLUSION: Machine learning can help identify pain-related and recreational-related OM contents on Twitter to potentially enable the study of the characteristics of individuals exhibiting such behavior.

Exploiting MEDLINE for gene molecular function prediction via NMF based multi-label classification.

Gene ontology (GO) provides a representation of terms and categories used to describe genes and their molecular functions, cellular components and biological processes. GO has been the standard for describing the functions of specific genes in different model organisms. GO annotation, or the tagging of genes with GO terms, has mostly been a manual and time-consuming curation process. Although many automated approaches have been proposed for annotation, few have utilized knowledge available in the literature. In this manuscript, we describe the development and evaluation of an innovative predictive system to automatically assign molecular functions (GO terms) to genes using the biomedical literature. Because genes could be associated with multiple molecular functions, we posed the GO molecular function annotation as a multi-label classification problem with several classes. We used non-negative matrix factorization (NMF) for feature reduction and then classified the genes. To address the multi-label aspect of the data, we used the binary-relevance method. Although we experimented with several classifiers, the combination of binary-relevance and K-nearest neighbor (KNN) classifier performed best. Our evaluation on UniProtKB/Swiss-Prot dataset showed the best performance of 0.84 in terms of F1-measure.

Classifying clinical notes with pain assessment using machine learning.

Pain is a significant public health problem, affecting millions of people in the USA. Evidence has highlighted that patients with chronic pain often suffer from deficits in pain care quality (PCQ) including pain assessment, treatment, and reassessment. Currently, there is no intelligent and reliable approach to identify PCQ indicators inelectronic health records (EHR). Hereby, we used unstructured text narratives in the EHR to derive pain assessment in clinical notes for patients with chronic pain. Our dataset includes patients with documented pain intensity rating ratings > = 4 and initial musculoskeletal diagnoses (MSD) captured by (ICD-9-CM codes) in fiscal year 2011 and a minimal 1 year of follow-up (follow-up period is 3-yr maximum); with complete data on key demographic variables. A total of 92 patients with 1058 notes was used. First, we manually annotated qualifiers and descriptors of pain assessment using the annotation schema that we previously developed. Second, we developed a reliable classifier for indicators of pain assessment in clinical note. Based on our annotation schema, we found variations in documenting the subclasses of pain assessment. In positive notes, providers mostly documented assessment of pain site (67%) and intensity of pain (57%), followed by persistence (32%). In only 27% of positive notes, did providers document a presumed etiology for the pain complaint or diagnosis. Documentation of patients' reports of factors that aggravate pain was only present in 11% of positive notes. Random forest classifier achieved the best performance labeling clinical notes with pain assessment information, compared to other classifiers; 94, 95, 94, and 94% was observed in terms of accuracy, PPV, F1-score, and AUC, respectively. Despite the wide spectrum of research that utilizes machine learning in many clinical applications, none explored using these methods for pain assessment research. In addition, previous studies using large datasets to detect and analyze characteristics of patients with various types of pain have relied exclusively on billing and coded data as the main source of information. This study, in contrast, harnessed unstructured narrative text data from the EHR to detect pain assessment clinical notes. We developed a Random forest classifier to identify clinical notes with pain assessment information. Compared to other classifiers, ours achieved the best results in most of the reported metrics. Graphical abstract Framework for detecting pain assessment in clinical notes.

Electronic approaches to making sense of the text in the adverse event reporting system.

INTRODUCTION: Health care organizations working to eliminate preventable harm and to improve patient safety must have robust programs to collect and to analyze data on adverse events in order to use the information to affect improvement. Such adverse event reporting systems are based on frontline personnel reporting issues that arise in the course of their daily work. Limitations in how existing software systems handle these reports mean that use of this potentially rich information is resource intensive and prone to variable results. AIM: The aim of this study was to develop an electronic approach to processing the text in medical event reports that would be reliable enough to be used to improve patient safety. METHODS: At Connecticut Children's Medical Center, staff manually enter reports of adverse events into a web-based software tool. We evaluated the ability of 2 electronic methods-rule-based query and semi-supervised machine learning-to identify specific types of events ("use cases") versus a reference standard. Rule-based query was tested on 5 use cases and machine learning on a subset of 2 using 9164 events reported from February 2012-January 2014. RESULTS: Machine learning found 93% of the weight-based errors and 92% of the errors in patient-identification. Rule-based query had accuracy of 99% or greater, high precision, and high recall for all use cases. CONCLUSIONS: Electronic approaches to streamlining the use of adverse event reports are feasible to automate and valuable for categorizing this important data for use in improving patient safety.

Complementary ensemble clustering of biomedical data.

The rapidly growing availability of electronic biomedical data has increased the need for innovative data mining methods. Clustering in particular has been an active area of research in many different application areas, with existing clustering algorithms mostly focusing on one modality or representation of the data. Complementary ensemble clustering (CEC) is a recently introduced framework in which Kmeans is applied to a weighted, linear combination of the coassociation matrices obtained from separate ensemble clustering of different data modalities. The strength of CEC is its extraction of information from multiple aspects of the data when forming the final clusters. This study assesses the utility of CEC in biomedical data, which often have multiple data modalities, e.g., text and images, by applying CEC to two distinct biomedical datasets (PubMed images and radiology reports) that each have two modalities. Referent to five different clustering approaches based on the Kmeans algorithm, CEC exhibited equal or better performance in the metrics of micro-averaged precision and Normalized Mutual Information across both datasets. The reference methods included clustering of single modalities as well as ensemble clustering of separate and merged data modalities. Our experimental results suggest that CEC is equivalent or more efficient than comparable Kmeans based clustering methods using either single or merged data modalities.

Enhancing Clustering by Exploiting Complementary Data Modalities in the Medical Domain.

Data Clustering has been an active area of research in many different application areas, with existing clustering algorithms mostly focusing on partitioning one modality or representation of the data. In this study, we delineate and demonstrate a new, enhanced data clustering approach whose innovation is its exploitation of multiple data modalities. We propose BI-NMF, a bi-modal clustering approach based on Non Negative Matrix Factorization (NMF) that clusters two differing data modalities simultaneously. The strength of our approach is its combining of multiple aspects of the data when forming the final clusters. To assess the utility of our approach, we performed several experiments on two distinct biomedical datasets with two modalities each. Comparing the clusters of BI-NMF with NMF clusters of single data modality, we observed consistent performance enhancement across both datasets. Our experimental results suggest that BI-NMF is advantageous for boosting data clustering.