Patient Dossier: Healthcare queries over distributed resources.

As with many other aspects of the modern world, in healthcare, the explosion of data and resources opens new opportunities for the development of added-value services. Still, a number of specific conditions on this domain greatly hinders these developments, including ethical and legal issues, fragmentation of the relevant data in different locations, and a level of (meta)data complexity that requires great expertise across technical, clinical, and biological domains. We propose the Patient Dossier paradigm as a way to organize new innovative healthcare services that sorts the current limitations. The Patient Dossier conceptual framework identifies the different issues and suggests how they can be tackled in a safe, efficient, and responsible way while opening options for independent development for different players in the healthcare sector. An initial implementation of the Patient Dossier concepts in the Rbbt framework is available as open-source at https://github.com/mikisvaz and https://github.com/Rbbt-Workflows.

Structured reporting of x-rays for atraumatic shoulder pain: advantages over free text?

BACKGROUND: To analyse structured and free text reports of shoulder X-ray examinations evaluating the quality of reports and potential contributions to clinical decision-making. METHODS: We acquired both standard free text and structured reports of 31 patients with a painful shoulder without history of previous trauma who received X-ray exams. A template was created for the structured report based on the template ID 0000154 (Shoulder X-ray) from radreport.org using online software with clickable decision trees with concomitant generation of structured semantic reports. All reports were evaluated regarding overall quality and key features: content, information extraction and clinical relevance. RESULTS: Two experienced orthopaedic surgeons reviewed and rated structured and free text reports of 31 patients independently. The structured reports achieved significantly higher median ratings in all key features evaluated (P < 0.001), including facilitation of information extraction (P < 0.001) and better contribution to subsequent clinical decision-making (P < 0.001). The overall quality of structured reports was significantly higher than in free text report (P < 0.001). CONCLUSIONS: A comprehensive structured template may be a useful tool to assist in clinical decision-making and is, thus, recommended for the reporting of degenerative changes regarding X-ray examinations of the shoulder.

Adaptation and Validation of the Combined Comorbidity Score for ICD-10-CM.

BACKGROUND: The combined comorbidity score, which merges the Charlson and Elixhauser comorbidity indices, uses the ninth revision of the International Classification of Diseases, Clinical Modification (ICD-9-CM). In October 2015, the United States adopted the 10th revision (ICD-10-CM). OBJECTIVE: The objective of this study is to examine different coding algorithms for the ICD-10-CM combined comorbidity score and compare their performance to the original ICD-9-CM score. METHODS: Four ICD-10-CM coding algorithms were defined: 2 using General Equivalence Mappings (GEMs), one based on ICD-10-CA (Canadian modification) codes for Charlson and Elixhauser measures, and one including codes from all 3 algorithms. We used claims data from the Clinfomatics Data Mart to identify 2 cohorts. The ICD-10-CM cohort comprised patients who had a hospitalization between January 1, 2016 and March 1, 2016. The ICD-9-CM cohort comprised patients who had a hospitalization between January 1, 2015 and March 1, 2015. We used logistic regression models to predict 30-day hospital readmission for the original score in the ICD-9-CM cohort and for each ICD-10-CM algorithm in the ICD-10-CM cohort. RESULTS: Distributions of each version of the score were similar. The algorithm based on ICD-10-CA codes [c-statistic, 0.646; 95% confidence interval (CI), 0.640-0.653] had the most similar discrimination for readmission to the ICD-9-CM version (c, 0.646; 95% CI, 0.639-0.653), but combining all identified ICD-10-CM codes had the highest c-statistic (c, 0.651; 95% CI, 0.644-0.657). CONCLUSIONS: We propose an ICD-10-CM version of the combined comorbidity score that includes codes identified by ICD-10-CA and GEMs. Compared with the original score, it has similar performance in predicting readmission in a population of United States commercially insured individuals.

How to identify potentially preventable readmissions by classifying them using a national administrative database.

IMPORTANCE: Hospital readmissions are being used increasingly as an indicator of quality of care. However, it remains difficult to identify potentially preventable readmissions. OBJECTIVES: To evaluate the identification of potentially preventable hospital readmissions by using a classification of readmissions based on administrative data. DESIGN AND SETTING: We classified a random sample of 455 readmissions to a Dutch university hospital in 2014 using administrative data. We compared these results to a classification based on reviewing the medical records of these readmissions to evaluate the accuracy of classification by administrative data. MAIN OUTCOME MEASURES: Frequencies of categories of readmissions based on reviewing records versus those based on administrative data. Cohen's kappa for the agreement between both methods. The sensitivity and specificity of the identification of potentially preventable readmissions with classification by administrative data. RESULTS: Reviewing the medical records of acute readmissions resulted in 28.5% of the records being classified as potentially preventable. With administrative data this was 44.1%. There was slight agreement between both methods: ƙ 0.08 (95% CI: 0.02-0.15, P < 0.05). The sensitivity of the classification of potentially preventable readmissions by administrative data was 63.1% and the specificity was 63.5%. CONCLUSIONS: This explorative study demonstrated differences between categorizing readmissions based on reviewing records compared to using administrative data. Therefore, this tool can only be used in practice with great caution. It is not suitable for penalizing hospitals based on their number of potentially preventable readmissions. However, hospitals might use this classification as a screening tool to identify potentially preventable readmissions more efficiently.

Determine the therapeutic role of radiotherapy in administrative data: a data mining approach.

BACKGROUND: Clinical data gathered for administrative purposes often lack sufficient information to separate the records of radiotherapy given for palliation from those given for cure. An absence, incompleteness, or inaccuracy of such information could hinder or bias the study of the utilization and outcome of radiotherapy. This study has three specific purposes: 1) develop a method to determine the therapeutic role of radiotherapy (TRR); 2) assess the accuracy of the method; 3) report the quality of the information on treatment "intent" recorded in the clinical data in Ontario, Canada. A general purpose is to use this study as a prototype to demonstrate and test a method to assess the quality of administrative data. METHODS: This is a population based retrospective study. A random sample was drawn from the treatment records with "intent" assigned in treating hospitals. A decision tree is grown using treatment parameters as predictors and "intent" as outcome variable to classify the treatments into curative or palliative. The tree classifier was applied to the entire dataset, and the classification results were compared with those identified by "intent". A manual audit was conducted to assess the accuracy of the classification. RESULTS: The following parameters predicted the TRR, from the strongest to the weakest: radiation dose per fraction, treated body-region, disease site, and time of treatment. When applied to the records of treatments given between 1990 and 2008 in Ontario, Canada, the classification rules correctly classified 96.1% of the records. The quality of the "intent" variable was as follows: 77.5% correctly classified, 3.7% misclassified, and 18.8% did not have an "intent" assigned. CONCLUSIONS: The classification rules derived in this study can be used to determine the TRR when such information is unavailable, incomplete, or inaccurate in administrative data. The study demonstrates that data mining approach can be used to effectively assess and improve the quality of large administrative datasets.

Evaluating latent class models with conditional dependence in record linkage.

Record linkage methods commonly use a traditional latent class model to classify record pairs from different sources as true matches or non-matches. This approach was first formally described by Fellegi and Sunter and assumes that the agreement in fields is independent conditional on the latent class. Consequences of violating the conditional independence assumption include bias in parameter estimates from the model. We sought to further characterize the impact of conditional dependence on the overall misclassification rate, sensitivity, and positive predictive value in the record linkage problem when the conditional independence assumption is violated. Additionally, we evaluate various methods to account for the conditional dependence. These methods include loglinear models with appropriate interaction terms identified through the correlation residual plot as well as Gaussian random effects models. The proposed models are used to link newborn screening data obtained from a health information exchange. On the basis of simulations, loglinear models with interaction terms demonstrated the best misclassification rate, although this type of model cannot accommodate other data features such as continuous measures for agreement. Results indicate that Gaussian random effects models, which can handle additional data features, perform better than assuming conditional independence and in some situations perform as well as the loglinear model with interaction terms.

ICD-10: are you ready for a brave new world?

The ICD-10 transition will be an evolutionary process. Relying on the EHR or certified coding staff alone will not be sufficient. The EHR can facilitate easy search tools that assist the provider in selecting a diagnosis. Billing staff are an invaluable resource to help validate that coding and documentation are in sync but the burden will clearly rest on the provider. The provider will be juggling a new code structure, drilling down to new levels of complexity and ensuring their documentation supports the specificity of the new codes selected, all while managing a full patient schedule. Education for the provider will be of paramount importance as they navigate this brave new world.

Implementation of ICD-10 in Canada: how has it impacted coded hospital discharge data?

BACKGROUND: The purpose of this study was to assess whether or not the change in coding classification had an impact on diagnosis and comorbidity coding in hospital discharge data across Canadian provinces. METHODS: This study examined eight years (fiscal years 1998 to 2005) of hospital records from the Hospital Person-Oriented Information database (HPOI) derived from the Canadian national Discharge Abstract Database. The average number of coded diagnoses per hospital visit was examined from 1998 to 2005 for provinces that switched from International Classifications of Disease 9(th) version (ICD-9-CM) to ICD-10-CA during this period. The average numbers of type 2 and 3 diagnoses were also described. The prevalence of the Charlson comorbidities and distribution of the Charlson score one year before and one year after ICD-10 implementation for each of the 9 provinces was examined. The prevalence of at least one of the seventeen Charlson comorbidities one year before and one year after ICD-10 implementation were described by hospital characteristics (teaching/non-teaching, urban/rural, volume of patients). RESULTS: Nine Canadian provinces switched from ICD-9-CM to ICD-I0-CA over a 6 year period starting in 2001. The average number of diagnoses coded per hospital visit for all code types over the study period was 2.58. After implementation of ICD-10-CA a decrease in the number of diagnoses coded was found in four provinces whereas the number of diagnoses coded in the other five provinces remained similar. The prevalence of at least one of the seventeen Charlson conditions remained relatively stable after ICD-10 was implemented, as did the distribution of the Charlson score. When stratified by hospital characteristics, the prevalence of at least one Charlson condition decreased after ICD-10-CA implementation, particularly for low volume hospitals. CONCLUSION: In conclusion, implementation of ICD-10-CA in Canadian provinces did not substantially change coding practices, but there was some coding variation in the average number of diagnoses per hospital visit across provinces.

Research strategies that result in optimal data collection from the patient medical record.

Data obtained from the patient medical record are often a component of clinical research led by nurse investigators. The rigor of the data collection methods correlates to the reliability of the data and, ultimately, the analytical outcome of the study. Research strategies for reliable data collection from the patient medical record include the development of a precise data collection tool, the use of a coding manual, and ongoing communication with research staff.

Data Definition Ontology for clinical data integration and querying.

This paper describes an approach to build a Data Definition Ontology (DDO) in the context of full domain ontology integration with datasets in order to share and query clinical heterogeneous data repositories. We have adapted an existing semantic web tool (D2RQ) to implement a process that automatically generates the DDO from a database information model, thanks to reverse engineering and schema mapping approaches. This study has been performed in the context of the DebugIT European project (Detecting and Eliminating Bacteria UsinG Information Technology) that aims to control and monitor the bacterial growth via a semantic interoperability platform (IP). The evaluation of the process is based, first, on the accuracy of the produced DDO for different samples of database storage and second, by checking the congruency between the DDO and the D2RQ database mapping file.

The development, evolution, and modifications of ICD-10: challenges to the international comparability of morbidity data.

BACKGROUND: The United States is about to make a major nationwide transition from ICD-9-CM coding of hospital discharges to ICD-10-CM, a country-specific modification of the World Health Organization's ICD-10. As this transition occurs, the WHO is already in the midst of developing ICD-11. Given this context, we undertook this review to discuss: (1) the history of the International Classification of Diseases (a core information "building block" for health systems everywhere) from its introduction to the current era of ICD-11 development; (2) differences across country-specific ICD-10 clinical modifications and the challenges that these differences pose to the international comparability of morbidity data; (3) potential strategic approaches to achieving better international ICD-11 comparability. LITERATURE REVIEW AND DISCUSSION: A literature review and stakeholder consultation was carried out. The various ICD-10 clinical modifications (ICD-10-AM [Australia], ICD-10-CA [Canada], ICD-10-GM [Germany], ICD-10-TM [Thailand], ICD-10-CM [United States]) were compared. These ICD-10 modifications differ in their number of codes, chapters, and subcategories. Specific conditions are present in some but not all of the modifications. ICD-11, with a similar structure to ICD-10, will function in an electronic health records environment and also provide disease descriptive characteristics (eg, causal properties, functional impact, and treatment). CONCLUSION: The threat to the comparability of international clinical morbidity is growing with the development of many country-specific ICD-10 versions. One solution to this threat is to develop a meta-database including all country-specific modifications to ensure more efficient use of people and resources, decrease omissions and errors but most importantly provide a platform for future ICD updates.

Hospital discharge data: can it serve as the sole source of case ascertainment for population-based birth defects surveillance programs?

INTRODUCTION: Because of the relatively high expense of collecting primary data and limited resources, electronically available, population-based hospital discharge data have been increasingly used for disease surveillance by public health researchers. The objective of this study was to compare the New York State Congenital Malformations Registry (CMR) data, which relies on hospital reports, with the hospital discharge files to identify cases in the CMR that were missed in the hospital discharge data files. The ultimate goal was to evaluate whether hospital discharge data can serve as the sole source of case ascertainment for a population-based birth defects surveillance program. METHODS: CMR cases that were born to the New York State residents for the years 2000 to 2005 were selected and matched to the hospital discharge files from the New York Statewide Planning and Research Cooperative System (SPARCS) for the same birth year period. Since the SPARCS database does not contain patient's name, extensive database matching and manual review by staff members were performed using identifying variables such as the hospital's permanent facility identifier, child's date of birth and medical record number, and mother's medical record number and residential address. RESULTS: Out of 66 757 CMR cases selected for the study period, 62 118 cases (93.1%) were matched to SPARCS hospital discharge records with International Classification of Diseases, Ninth Revision (ICD-9) codes that were reportable to the CMR, 3 444 cases (5.2%) were matched to SPARCS records with ICD-9 codes that were not reportable to the CMR, and 1 195 cases (1.8%) were not matched. The percentage of cases with multiple congenital malformations was significantly higher (21.3%) for the matched cases that had reportable ICD-9 codes in SPARCS, compared with that for matched CMR cases that had no reportable ICD-9 codes in SPARCS (10.2%). CONCLUSION: The study found that 93% of CMR infants selected for the study were matched to hospital discharge records with at least one ICD-9 code that was reportable to the CMR; 87 percent had reportable ICD codes in SPARCS that were exactly matched to those in the CMR, that is, all the birth defect codes in SPARCS were matched to those in the CMR. Thus, about 7 percent of CMR children with birth defects would have been missed if only hospital discharge files were used to ascertain the birth defect cases, indicating that there are limitations to using hospital discharge files as the sole source of case ascertainment for population-based birth defects surveillance programs.

Identifying main finding sentences in clinical case reports.

Clinical case reports are the 'eyewitness reports' of medicine and provide a valuable, unique, albeit noisy and underutilized type of evidence. Generally, a case report has a single main finding that represents the reason for writing up the report in the first place. However, no one has previously created an automatic way of identifying main finding sentences in case reports. We previously created a manual corpus of main finding sentences extracted from the abstracts and full text of clinical case reports. Here, we have utilized the corpus to create a machine learning-based model that automatically predicts which sentence(s) from abstracts state the main finding. The model has been evaluated on a separate manual corpus of clinical case reports and found to have good performance. This is a step toward setting up a retrieval system in which, given one case report, one can find other case reports that report the same or very similar main findings. The code and necessary files to run the main finding model can be downloaded from https://github.com/qi29/main_ finding_recognition, released under the Apache License, Version 2.0.

Identification of hospital-acquired catheter-associated urinary tract infections from Medicare claims: sensitivity and positive predictive value.

BACKGROUND AND OBJECTIVE: Hospital-acquired catheter-associated urinary tract infection (CAUTI) is one of the first 6 conditions Medicare is targeting to reduce payment associated with hospital-acquired conditions under Congressional mandate. This study was to determine the positive predictive value (PPV) and sensitivity in identifying patients in Medicare claims who had urinary catheterization and who had hospital-acquired CAUTIs. RESEARCH DESIGN: CAUTIs identified by ICD-9-CM codes in Medicare claims were compared with those revealed by medical record abstraction in random samples of Medicare discharges in 2005 to 2006. Hospital discharge abstracts (2005) from the states of New York and California were used to estimate the potential impact of a present-on-admission (POA) indicator on PPV. RESULTS: ICD-9-CM procedure codes for urinary catheterization appeared in only 1.4% of Medicare claims for patients who had urinary catheters. As a proxy, claims with major surgery had a PPV of 75% and sensitivity of 48%, and claims with any surgical procedure had a PPV of 53% and sensitivity of 79% in identifying urinary catheterization. The PPV and sensitivity for identifying hospital-acquired CAUTIs varied, with the PPV at 30% and sensitivity at 65% in claims with major surgery. About 80% of the secondary diagnosis codes indicating UTIs were flagged as POA, suggesting that the addition of POA indicators in Medicare claims would increase PPV up to 86% and sensitivity up to 79% in identifying hospital-acquired CAUTIs. CONCLUSIONS: The validity in identifying urinary catheter use and CAUTIs from Medicare claims is limited, but will be increased substantially upon addition of a POA indicator.

LOINC codes for hospital information systems documents: a case study.

Hospital Information Systems (HIS) handle a large number of different types of documents. Exchange and analysis of data from different HIS is facilitated by the use of standardized codes to identify document types. HL7's Clinical Document Architecture (CDA) uses LOINC (logical observation identifiers names and Codes) codes for clinical documents. The authors assessed the coverage of LOINC codes for document types in a German HIS. The authors analyzed document types that occurred more than 10 times in approximately 1.3 million documents in a commercial HIS at a major German University Hospital. Document types were mapped manually to LOINC using the Regenstrief LOINC Mapping Assistant (RELMA). Each document type was coded by two physicians. In case of discrepancies a third expert was consulted to reach consensus. For 76 of 86 document categories a LOINC code was identified, but for 38 of these categories, the LOINC code was not specific as deemed necessary. More than 93% of our local HIS documents had local document types that could be assigned a LOINC code.

Machine learning and rule-based approaches to assertion classification.

OBJECTIVES: The authors study two approaches to assertion classification. One of these approaches, Extended NegEx (ENegEx), extends the rule-based NegEx algorithm to cover alter-association assertions; the other, Statistical Assertion Classifier (StAC), presents a machine learning solution to assertion classification. DESIGN: For each mention of each medical problem, both approaches determine whether the problem, as asserted by the context of that mention, is present, absent, or uncertain in the patient, or associated with someone other than the patient. The authors use these two systems to (1) extend negation and uncertainty extraction to recognition of alter-association assertions, (2) determine the contribution of lexical and syntactic context to assertion classification, and (3) test if a machine learning approach to assertion classification can be as generally applicable and useful as its rule-based counterparts. MEASUREMENTS: The authors evaluated assertion classification approaches with precision, recall, and F-measure. RESULTS: The ENegEx algorithm is a general algorithm that can be directly applied to new corpora. Despite being based on machine learning, StAC can also be applied out-of-the-box to new corpora and achieve similar generality. CONCLUSION: The StAC models that are developed on discharge summaries can be successfully applied to radiology reports. These models benefit the most from words found in the +/- 4 word window of the target and can outperform ENegEx.

The Royal College of Radiologists Breast Group breast imaging classification.

Standardisation of the classification of breast imaging reports will improve communication between the referrer and the radiologist and avoid ambiguity, which may otherwise lead to mismanagement of patients. Following wide consultation, the Royal College of Radiologists Breast Group has produced a scoring system for the classification of breast imaging. This will facilitate audit and the development of nationally agreed standards for the investigation of women with breast disease. This five-point system is as follows: 1, normal; 2, benign findings; 3, indeterminate/probably benign findings; 4, findings suspicious of malignancy; 5, findings highly suspicious of malignancy. It is recommended that this be used in the reporting of all breast imaging examinations in the UK.

Traditional Chinese medicine clinical records classification with BERT and domain specific corpora.

Traditional Chinese Medicine (TCM) has been developed for several thousand years and plays a significant role in health care for Chinese people. This paper studies the problem of classifying TCM clinical records into 5 main disease categories in TCM. We explored a number of state-of-the-art deep learning models and found that the recent Bidirectional Encoder Representations from Transformers can achieve better results than other deep learning models and other state-of-the-art methods. We further utilized an unlabeled clinical corpus to fine-tune the BERT language model before training the text classifier. The method only uses Chinese characters in clinical text as input without preprocessing or feature engineering. We evaluated deep learning models and traditional text classifiers on a benchmark data set. Our method achieves a state-of-the-art accuracy 89.39% ± 0.35%, Macro F1 score 88.64% ± 0.40% and Micro F1 score 89.39% ± 0.35%. We also visualized attention weights in our method, which can reveal indicative characters in clinical text.

Taylor and Gradient Descent-Based Actor Critic Neural Network for the Classification of Privacy Preserved Medical Data.

Classification of the privacy preserved medical data is the domain of the researchers as it stirs the importance behind hiding the sensitive data from the third-party authenticator. Ensuring the privacy of the medical records and using the disease prediction mechanisms played a remarkable role in peoples' lives such that the earlier detection of the diseases is required for earlier diagnosis. Accordingly, this article proposes a method, named Taylor gradient descent (TGD)-based actor critic neural network (ACNN), which concentrates on performing the medical data classification. Initially, the privacy of the medical data is ensured by using the key matrix developed based on the privacy utility coefficient matrix using the chronological-Whale optimization algorithm. The privacy protected data are subjected to classification by using ACNN that performs the optimal classification using the proposed TGD algorithm. The proposed TGD algorithm is the integration of Taylor series in the gradient descent algorithm that updates the optimal weight of ACNN based on the weights in the previous iterations. The analysis using the Cleveland, Switzerland, and Hungarian dataset proves that the proposed classification strategy obtains an accuracy of 0.9252, a sensitivity of 0.8419, and a specificity of 0.8387, respectively.