Determination of Minimum Data Set (MSD) in Echocardiography Reporting System to Exchange with Iran's Electronic Health Record (EHR) System

e17112 Background: For endometrial cancer (EC), laparoscopic hysterectomy (LH) is an effective, minimally invasive surgical treatment; however, this approach may not be recommended for obese patients due to increased risk for complications. Methods: This retrospective study utilized insurance claims linked to electronic health record (EHR) data contained in the IBM MarketScan Explorys Claims-EHR Data Set. Newly diagnosed EC patients (1/1/2007 - 6/30/2017) with continuous enrollment during a 12-month baseline and 6-month follow-up period were selected. Patients were stratified into four BMI subgroups based on baseline BMI on the EHR: normal or underweight (BMI < 25), overweight (BMI 25- < 30), obese (BMI 30- < 40), morbidly obese (BMI > 40), and were required to have had a hysterectomy within the follow-up period. Emergency room visits and rehospitalization within 30 days of hysterectomy were measured. Results: A total of 1,090 newly-diagnosed EC patients met the selection criteria, of whom, 16% were normal/underweight, 19% were overweight, 39% were obese, and 26% were morbidly obese. The proportion of patients receiving LH increased as BMI category increased (Table 1). Among those with LH between 6% and 15% had an ER visit or rehospitalization in 30 days, and rates were higher among other hysterectomy modalities. Conclusions: This real-world analysis shows that LH is utilized in a high proportion of morbidly obese EC patients, despite that it is frequently deemed infeasible in this patient population. Although the rate of ER visits and rehospitalization is lower among LH patients than those undergoing traditional hysterectomy across all BMI strata, further research is needed to determine the optimal patient population to receive LH.[Table: see text]

Download Full-text

Machine Learning Electronic Health Record Identification of Patients with Rheumatoid Arthritis: Algorithm Pipeline Development and Validation Study (Preprint)

10.2196/preprints.23930 ◽

2020 ◽

Author(s):

Tjardo D Maarseveen ◽

Timo Meinderink ◽

Marcel J T Reinders ◽

Johannes Knitza ◽

Tom W J Huizinga ◽

...

Keyword(s):

Rheumatoid Arthritis ◽

Machine Learning ◽

Electronic Health Record ◽

Support Vector ◽

Free Text ◽

Health Record ◽

Electronic Health Record Data ◽

Data Set ◽

Record Data ◽

Electronic Health

BACKGROUND Financial codes are often used to extract diagnoses from electronic health records. This approach is prone to false positives. Alternatively, queries are constructed, but these are highly center and language specific. A tantalizing alternative is the automatic identification of patients by employing machine learning on format-free text entries. OBJECTIVE The aim of this study was to develop an easily implementable workflow that builds a machine learning algorithm capable of accurately identifying patients with rheumatoid arthritis from format-free text fields in electronic health records. METHODS Two electronic health record data sets were employed: Leiden (n=3000) and Erlangen (n=4771). Using a portion of the Leiden data (n=2000), we compared 6 different machine learning methods and a naïve word-matching algorithm using 10-fold cross-validation. Performances were compared using the area under the receiver operating characteristic curve (AUROC) and the area under the precision recall curve (AUPRC), and F1 score was used as the primary criterion for selecting the best method to build a classifying algorithm. We selected the optimal threshold of positive predictive value for case identification based on the output of the best method in the training data. This validation workflow was subsequently applied to a portion of the Erlangen data (n=4293). For testing, the best performing methods were applied to remaining data (Leiden n=1000; Erlangen n=478) for an unbiased evaluation. RESULTS For the Leiden data set, the word-matching algorithm demonstrated mixed performance (AUROC 0.90; AUPRC 0.33; F1 score 0.55), and 4 methods significantly outperformed word-matching, with support vector machines performing best (AUROC 0.98; AUPRC 0.88; F1 score 0.83). Applying this support vector machine classifier to the test data resulted in a similarly high performance (F1 score 0.81; positive predictive value [PPV] 0.94), and with this method, we could identify 2873 patients with rheumatoid arthritis in less than 7 seconds out of the complete collection of 23,300 patients in the Leiden electronic health record system. For the Erlangen data set, gradient boosting performed best (AUROC 0.94; AUPRC 0.85; F1 score 0.82) in the training set, and applied to the test data, resulted once again in good results (F1 score 0.67; PPV 0.97). CONCLUSIONS We demonstrate that machine learning methods can extract the records of patients with rheumatoid arthritis from electronic health record data with high precision, allowing research on very large populations for limited costs. Our approach is language and center independent and could be applied to any type of diagnosis. We have developed our pipeline into a universally applicable and easy-to-implement workflow to equip centers with their own high-performing algorithm. This allows the creation of observational studies of unprecedented size covering different countries for low cost from already available data in electronic health record systems.

Download Full-text

Using Machine Learning and the Electronic Health Record to Predict Complicated Clostridium difficile Infection

Open Forum Infectious Diseases ◽

10.1093/ofid/ofz186 ◽

2019 ◽

Vol 6 (5) ◽

Cited By ~ 14

Author(s):

Benjamin Y Li ◽

Jeeheh Oh ◽

Vincent B Young ◽

Krishna Rao ◽

Jenna Wiens

Keyword(s):

Machine Learning ◽

Electronic Health Record ◽

Characteristic Curve ◽

Model Performance ◽

Health Record ◽

Data Set ◽

Icu Admission ◽

Clostridioides Difficile ◽

Electronic Health ◽

Health Care Associated Infection

Abstract Background Clostridium (Clostridioides) difficile infection (CDI) is a health care–associated infection that can lead to serious complications. Potential complications include intensive care unit (ICU) admission, development of toxic megacolon, need for colectomy, and death. However, identifying the patients most likely to develop complicated CDI is challenging. To this end, we explored the utility of a machine learning (ML) approach for patient risk stratification for complications using electronic health record (EHR) data. Methods We considered adult patients diagnosed with CDI between October 2010 and January 2013 at the University of Michigan hospitals. Cases were labeled complicated if the infection resulted in ICU admission, colectomy, or 30-day mortality. Leveraging EHR data, we trained a model to predict subsequent complications on each of the 3 days after diagnosis. We compared our EHR-based model to one based on a small set of manually curated features. We evaluated model performance using a held-out data set in terms of the area under the receiver operating characteristic curve (AUROC). Results Of 1118 cases of CDI, 8% became complicated. On the day of diagnosis, the model achieved an AUROC of 0.69 (95% confidence interval [CI], 0.55–0.83). Using data extracted 2 days after CDI diagnosis, performance increased (AUROC, 0.90; 95% CI, 0.83–0.95), outperforming a model based on a curated set of features (AUROC, 0.84; 95% CI, 0.75–0.91). Conclusions Using EHR data, we can accurately stratify CDI cases according to their risk of developing complications. Such an approach could be used to guide future clinical studies investigating interventions that could prevent or mitigate complicated CDI.

Download Full-text

User Evaluation of the Swedish Patient Accessible Electronic Health Record: System Usability Scale (Preprint)

10.2196/preprints.24927 ◽

2020 ◽

Author(s):

Maria Hägglund ◽

Isabella Scandurra

Keyword(s):

Electronic Health Record ◽

Ease Of Use ◽

Survey Study ◽

Health Record ◽

Patient Portal ◽

Data Set ◽

System Usability Scale ◽

System Usability ◽

National Patient ◽

Electronic Health

BACKGROUND Transparency is increasingly called for in health care, especially, when it comes to patients’ access to their electronic health records. In Sweden, the e-service Journalen is a national patient accessible electronic health record (PAEHR), accessible online via the national patient portal. User characteristics and perceived benefits of using a PAEHR influence behavioral intention for use and adoption, but poor usability that increases the effort expectancy can have a negative impact. It is, therefore, of interest to explore how users of the PAEHR Journalen perceive its usability and usefulness. OBJECTIVE The aim of this study was to explore how the users of the Swedish PAEHR experience the usability of the system and to identify differences in these experiences based on the level of transparency of the region. METHODS A survey study was conducted to elicit opinions and experiences of patients using Journalen. The data were collected from June to October 2016. The questionnaire included questions regarding the usability of the system from the System Usability Scale (SUS). The SUS analysis was the focus of this paper. Analysis was performed on different levels: nationally looking at the whole data set and breaking it down by focusing on 2 different regions to explore differences in experienced usability based on the level of transparency. RESULTS During the survey period, 423,141 users logged into Journalen, of which 2587 unique users completed the survey (response rate 0.61%). The total mean score for all respondents to the SUS items was 79.81 (SD 14.25), which corresponds to a system with good usability. To further explore whether the level of transparency in a region would affect the user’s experience of the usability of the system, we analyzed the 2 regions with the most respondents: Region Uppsala (the first to launch, with a high level of transparency), and Region Skåne (an early implementer, with a low level of transparency at the time of the survey). Of the participants who responded to at least 1 SUS statement, 520 stated that they had received care in Region Skåne, whereas 331 participants had received care in Region Uppsala. Uppsala’s mean SUS score was 80.71 (SD 13.41), compared with Skåne’s mean of 79.37 (SD 13.78). CONCLUSIONS The Swedish national PAEHR Journalen has a reasonably good usability (mean SUS score 79.81, SD 14.25); however, further research into more specific usability areas are needed to ensure usefulness and ease of use in the future. A somewhat higher SUS score for the region with high transparency compared with the region with low transparency could indicate a relationship between the perceived usability of a PAEHR and the level of transparency offered, but further research on the relationship between transparency and usability is required.

Download Full-text

Artificial Intelligence–Based Traditional Chinese Medicine Assistive Diagnostic System: Validation Study

JMIR Medical Informatics ◽

10.2196/17608 ◽

2020 ◽

Vol 8 (6) ◽

pp. e17608 ◽

Cited By ~ 1

Author(s):

Hong Zhang ◽

Wandong Ni ◽

Jing Li ◽

Jiajun Zhang

Keyword(s):

Artificial Intelligence ◽

Chinese Medicine ◽

Traditional Chinese Medicine ◽

Electronic Health Record ◽

Diagnostic System ◽

Prediction Method ◽

Disease Type ◽

Health Record ◽

Data Set ◽

Electronic Health

Background Artificial intelligence–based assistive diagnostic systems imitate the deductive reasoning process of a human physician in biomedical disease diagnosis and treatment decision making. While impressive progress in this area has been reported, most of the reported successes are applications of artificial intelligence in Western medicine. The application of artificial intelligence in traditional Chinese medicine has lagged mainly because traditional Chinese medicine practitioners need to perform syndrome differentiation as well as biomedical disease diagnosis before a treatment decision can be made. Syndrome, a concept unique to traditional Chinese medicine, is an abstraction of a variety of signs and symptoms. The fact that the relationship between diseases and syndromes is not one-to-one but rather many-to-many makes it very challenging for a machine to perform syndrome predictions. So far, only a handful of artificial intelligence–based assistive traditional Chinese medicine diagnostic models have been reported, and they are limited in application to a single disease-type. Objective The objective was to develop an artificial intelligence–based assistive diagnostic system capable of diagnosing multiple types of diseases that are common in traditional Chinese medicine, given a patient’s electronic health record notes. The system was designed to simultaneously diagnose the disease and produce a list of corresponding syndromes. Methods Unstructured freestyle electronic health record notes were processed by natural language processing techniques to extract clinical information such as signs and symptoms which were represented by named entities. Natural language processing used a recurrent neural network model called bidirectional long short-term memory network–conditional random forest. A convolutional neural network was then used to predict the disease-type out of 187 diseases in traditional Chinese medicine. A novel traditional Chinese medicine syndrome prediction method—an integrated learning model—was used to produce a corresponding list of probable syndromes. By following a majority-rule voting method, the integrated learning model for syndrome prediction can take advantage of four existing prediction methods (back propagation, random forest, extreme gradient boosting, and support vector classifier) while avoiding their respective weaknesses which resulted in a consistently high prediction accuracy. Results A data set consisting of 22,984 electronic health records from Guanganmen Hospital of the China Academy of Chinese Medical Sciences that were collected between January 1, 2017 and September 7, 2018 was used. The data set contained a total of 187 diseases that are commonly diagnosed in traditional Chinese medicine. The diagnostic system was designed to be able to detect any one of the 187 disease-types. The data set was partitioned into a training set, a validation set, and a testing set in a ratio of 8:1:1. Test results suggested that the proposed system had a good diagnostic accuracy and a strong capability for generalization. The disease-type prediction accuracies of the top one, top three, and top five were 80.5%, 91.6%, and 94.2%, respectively. Conclusions The main contributions of the artificial intelligence–based traditional Chinese medicine assistive diagnostic system proposed in this paper are that 187 commonly known traditional Chinese medicine diseases can be diagnosed and a novel prediction method called an integrated learning model is demonstrated. This new prediction method outperformed all four existing methods in our preliminary experimental results. With further improvement of the algorithms and the availability of additional electronic health record data, it is expected that a wider range of traditional Chinese medicine disease-types could be diagnosed and that better diagnostic accuracies could be achieved.

Download Full-text

Machine Learning Electronic Health Record Identification of Patients with Rheumatoid Arthritis: Algorithm Pipeline Development and Validation Study

JMIR Medical Informatics ◽

10.2196/23930 ◽

2020 ◽

Vol 8 (11) ◽

pp. e23930

Author(s):

Tjardo D Maarseveen ◽

Timo Meinderink ◽

Marcel J T Reinders ◽

Johannes Knitza ◽

Tom W J Huizinga ◽

...

Keyword(s):

Rheumatoid Arthritis ◽

Machine Learning ◽

Electronic Health Record ◽

Support Vector ◽

Free Text ◽

Health Record ◽

Electronic Health Record Data ◽

Data Set ◽

Record Data ◽

Electronic Health

Background Financial codes are often used to extract diagnoses from electronic health records. This approach is prone to false positives. Alternatively, queries are constructed, but these are highly center and language specific. A tantalizing alternative is the automatic identification of patients by employing machine learning on format-free text entries. Objective The aim of this study was to develop an easily implementable workflow that builds a machine learning algorithm capable of accurately identifying patients with rheumatoid arthritis from format-free text fields in electronic health records. Methods Two electronic health record data sets were employed: Leiden (n=3000) and Erlangen (n=4771). Using a portion of the Leiden data (n=2000), we compared 6 different machine learning methods and a naïve word-matching algorithm using 10-fold cross-validation. Performances were compared using the area under the receiver operating characteristic curve (AUROC) and the area under the precision recall curve (AUPRC), and F1 score was used as the primary criterion for selecting the best method to build a classifying algorithm. We selected the optimal threshold of positive predictive value for case identification based on the output of the best method in the training data. This validation workflow was subsequently applied to a portion of the Erlangen data (n=4293). For testing, the best performing methods were applied to remaining data (Leiden n=1000; Erlangen n=478) for an unbiased evaluation. Results For the Leiden data set, the word-matching algorithm demonstrated mixed performance (AUROC 0.90; AUPRC 0.33; F1 score 0.55), and 4 methods significantly outperformed word-matching, with support vector machines performing best (AUROC 0.98; AUPRC 0.88; F1 score 0.83). Applying this support vector machine classifier to the test data resulted in a similarly high performance (F1 score 0.81; positive predictive value [PPV] 0.94), and with this method, we could identify 2873 patients with rheumatoid arthritis in less than 7 seconds out of the complete collection of 23,300 patients in the Leiden electronic health record system. For the Erlangen data set, gradient boosting performed best (AUROC 0.94; AUPRC 0.85; F1 score 0.82) in the training set, and applied to the test data, resulted once again in good results (F1 score 0.67; PPV 0.97). Conclusions We demonstrate that machine learning methods can extract the records of patients with rheumatoid arthritis from electronic health record data with high precision, allowing research on very large populations for limited costs. Our approach is language and center independent and could be applied to any type of diagnosis. We have developed our pipeline into a universally applicable and easy-to-implement workflow to equip centers with their own high-performing algorithm. This allows the creation of observational studies of unprecedented size covering different countries for low cost from already available data in electronic health record systems.

Download Full-text