DRCNNTLe: A deep recurrent convolutional neural network with transfer learning through pre-trained embeddings for automated ICD coding.

International Classification of Diseases (ICD) coding plays a pivotal role in healthcare systems with its provision of a standard method for classifying medical diagnoses, treatments, and procedures. However, the process of manually applying ICD codes to clinical records is both time-consuming and error-prone, particularly considering the large magnitude of medical terminologies and the periodic changes to the coding system. This work introduces a Hierarchical Multi-Head Attention Network (HMHAN) that aims to automate ICD coding using domain-related embeddings with an attention mechanism. The proposed method uses BioClinicalBERT for feature extraction from clinical text and then a two-level attention mechanism to learn hierarchical dependencies between labels. BioClinicalBERT is pre-trained on large biomedical and clinical corpora that enable it to capture complex contextual relationships specific to medical language more effectively. The multi-head attention mechanism enables the model to focus on different parts of the input text simultaneously, learning intricate associations between medical terms and corresponding ICD codes at various levels. This method uses SMOTE (Synthetic Minority Oversampling Technique) based multi-label resampling to solve class imbalance. SMOTE generates synthetic examples for underrepresented classes, allowing the model to learn better from imbalanced data without overfitting. For this work, MIMIC-IV dataset of de-identified radiology reports and corresponding ICD codes are used. The performance of the model is assessed with F1 score, Hamming loss, and ROC-AUC metrics. Results obtained from the model with an F1 score of 0.91, Hamming loss of 0.07, and ROC-AUC of 0.92 show promising research directions to automate the ICD coding process. This system will improve the effectiveness of healthcare workflows by automating ICD code generation for advanced clinical care.

To determine whether the discharge diagnosis codes used within tertiary hospitals accurately identified patients with Giant Cell Arteritis (GCA), as determined by expert opinion at 6 months. The study was performed across three major hospitals within Perth, Western Australia. Patients with an International Classification of Diseases (ICD) code for GCA (M31.5 and M31.6) at discharge on first inpatient presentation were identified. Review of case notes, discharge summaries, letters, pathology, and imaging results were undertaken. The percentage of patients with an ICD code for GCA at initial discharge with confirmed GCA by expert opinion at 6 months (as the anchor diagnosis) was calculated. As validation of the anchor diagnosis, the percentage who fulfilled the 2022 ACR/EULAR criteria was also calculated, the number of hospital discharges per patient with an ICD code for GCA was calculated, to determine if multiple discharges with an ICD code for GCA increased the specificity of the ICD coding. 93 out of 157 admissions with an ICD for GCA were identified as a first inpatient presentation. At 6 months follow up, 65.6%, 95 CI [55.0%, 75.1%] had confirmed GCA by expert opinion. 88.2%, 95 CI [79.8%, 93.9%] met the 2022 ACR/EULAR criteria for GCA. The specificity of the ICD coding increased with increasing number of discharges– 67.4% with single episode, 80% with two episodes, and 100% with three or more episodes (p = 0.1373). Only 43.8%, 95 CI [26.4%, 62.3%] of patients who did not have GCA had an alternative diagnosis provided. 31.3%, 95 CI [16.1%, 50.0%] of patients who did not have GCA still have the GCA diagnosis listed in their subsequent clinical records and discharge summaries. Only 2/3rds of those patients with an initial discharge ICD code for GCA were found to have confirmed GCA at follow-up. This poor correlation between the ICD coding and confirmed diagnosis of GCA will impact the quality of data extracted from administrative health datasets for epidemiological and longitudinal studies. Selecting patients with two or more GCA coded episodes could improve the homogeneity of the cohort for recruitment into GCA studies, but a larger sample size study is required.

Diagnostic coding of abuse related fractures at two children's emergency departments

Neural transfer learning for assigning diagnosis codes to EMRs

International Classification of Diseases(ICD) is an authoritative health care classification system of different diseases and conditions for clinical and management purposes. Considering the complicated and dedicated process to assign correct codes to each patient admission based on overall diagnosis, we propose a hierarchical deep learning model with attention mechanism which can automatically assign ICD diagnostic codes given written diagnosis. We utilize character-aware neural language models to generate hidden representations of written diagnosis descriptions and ICD codes, and design an attention mechanism to address the mismatch between the numbers of descriptions and corresponding codes. Our experimental results show the strong potential of automated ICD coding from diagnosis descriptions. Our best model achieves 0.53 and 0.90 of F1 score and area under curve of receiver operating characteristic respectively. The result outperforms those achieved using character-unaware encoding method or without attention mechanism. It indicates that our proposed deep learning model can code automatically in a reasonable way and provide a framework for computer-auxiliary ICD coding.

Widespread lack of awareness and limited real-world prevalence evidence have impeded cachexia care and research. We hypothesized that healthcare professionals may identify the term cachexia, leading to International Classification of Diseases (ICD) coding for this term, with or without records of body weight loss for diagnosing cancer cachexia, and that frequently, ICD coding does not accurately reflect weight data. We assessed cachexia prevalence in patients diagnosed with cancer, using the Clinical Data Warehouse of a French hospital containing two types of real-world digitized data: (a) 'structured': coded diagnoses and electronic records; (b) 'unstructured': uncoded clinical narratives/reports: discharge summaries, procedure results, letters. Two sequential searches covering 2018-2023 (1) determined the prevalence of cachexia in all patients with a diagnosis of cancer using ICD-10 code R64 (cachexia), electronic records of body weight and unstructured narrative data; and (2) examined data of cancers of high-prevalence cachexia: colorectal, pancreatic and bronchial/lung cancers, determining (a) prevalence of cachexia by these criteria; (b) extent to which a diagnosis of cachexia was supported by weight loss data; and (c) extent to which the diagnosis of cachexia was not made despite objective weight data indicating its presence. A total of 76 547 of 737 906 patients had cancer of any primary type; 1856 (2.42%) of these had a cachexia diagnosis: 620 identified by ICD code, 1507 by unstructured data, including 271 by both. Of 6946 patients with colorectal, pancreatic or bronchial/lung cancer, 2033 patients (29.3%) were identified with cachexia by structured and/or unstructured data; both approaches were required to discover cachexia cases. From structured data an ICD-R64 search found only 254 patients described by the term cachexia, of which 127 had weight data supporting the diagnosis in the electronic medical record. An additional 1340 patients with BMI < 20 kg/m2 or weight loss > 5% were not coded as cachectic. Unstructured data for the three cancers identified 439 additional cachexic patients. (1) Standard ICD code-searching underestimated cachexia prevalence in all patients and those with high-prevalence-cachexia cancers; (2) Many cachexia cases were not diagnosed, although data indicated its presence; (3) Many cachexia cases diagnosed by judgement were not supported by data; (4) Increasing provider awareness of cancer cachexia definitions would likely improve cachexia care and research.

The processing of textual medical data is difficult because they are structurally free, diverse in style, and have subjective factors. Medical records are primarily designed for archiving patient clinical information and administrative healthcare tasks. They are encoded following the International Classification of Diseases (ICD) standard by medical informaticians. Such manual encoding task is error-prone because of a load of abbreviations, miswriting, and medical terms in medical records. In this paper, a multi-channel convolutional attentional network is presented to automatically predict ICD codes from clinic records. The multi-channel CNN generates the multiple representations of medical records and meets the needs of a huge number of labels. An attention mechanism is designed to address the correlation between the multiple medical records representations and corresponding codes. The results show that F1 score increases by 6.9% over the state of art. This coding task eases the burden of hospital manual coding task and improve the secondary use for clinical informatics.

Text recognition in natural scene images is a challenging problem in computer vision. Different than the optical character recognition (OCR), text recognition in natural scene images is more complex due to variations in text size, colors, fonts, orientations, complex backgrounds, occlusion, illuminations and uneven lighting conditions. In this paper, we propose a segmentation-free method based on a deep convolutional recurrent neural network to solve the problem of cursive text recognition, particularly focusing on Urdu text in natural scenes. Compared to the non-cursive scripts, Urdu text recognition is more complex due to variations in the writing styles, several shapes of the same character, connected text, ligature overlapping, stretched, diagonal and condensed text. The proposed model gets a whole word image as an input without pre-segmenting into individual characters, and then transforms into the sequence of the relevant features. Our model is based on three components: a deep convolutional neural network (CNN) with shortcut connections to extract and encode the features, a recurrent neural network (RNN) to decode the convolutional features, and a connectionist temporal classification (CTC) to map the predicted sequences into the target labels. To increase the text recognition accuracy further, we explore deeper CNN architectures like VGG-16, VGG-19, ResNet-18 and ResNet-34 to extract more appropriate Urdu text features, and compare the recognition results. To conduct the experiments, a new large-scale benchmark dataset of cropped Urdu word images in natural scenes is developed. The experimental results show that the proposed deep CRNN network with shortcut connections outperform than other network architectures. The dataset is publicly available and can be downloaded from <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://data.mendeley.com/datasets/k5fz57zd9z/1</uri> .

One challenge in transgender research is reliably identifying patients through electronic medical records data, as there is no universal transgender International Classification of Diseases (ICD) code, but rather multiple ICD codes that can be used. To explore the sensitivity and specificity of 5 commonly used ICD codes to identify transgender patients overall and transgender women specifically (assigned male sex at birth) by using data from the Veterans Affairs (VA), the largest integrated health system in the United States. Patients aged ≥18 years were identified via ICD-9 codes 302.5 and 302.6 (Ninth Revision) and ICD-10 codes F64.0, F64.8, and F64.9 (Tenth Revision) using VA health records from 2000 to 2021 and stratified by bilateral orchiectomy status. Detailed chart review was performed on 32 randomly selected patients for each code (half with and half without orchiectomy) to confirm transgender status and to perform descriptive analyses. For each ICD code, rates of confirmed transgender status ranged from 88% to 100% for those with and without an orchiectomy, with the majority being transgender women (consistent with most veterans being assigned male sex at birth). Most transgender women (66%-100%) were undergoing estrogen gender-affirming therapy. The majority of provider-driven entries of transgender status took place from 2011 to 2020, with 75% of entries made from 2011 to 2020, consistent with increased recognition and societal acceptance of this population. False negatives were detected at a rate of 15%. Based upon these 5 ICD codes alone, we estimate that the VA has records for 9,449 to 10,738 transgender individuals. All 5 codes are very sensitive in identifying transgender patients, and the combination of these codes with orchiectomy is extremely sensitive in identifying transgender women, specifically. Major strengths of the study are the use of universal ICD codes and a large patient sample size that spans health records nationally and across multiple decades, potentially making our data more generalizable. The main limitation of this study is that subanalyses were performed on a limited number of patients, which prevented us from capturing all false positives and thus from calculating specificity for each code. Similarly, our true negatives were derived from a small, random subset of the population; as such, our calculation for specificity is an estimate. This study highlights a novel method to identify transgender women and paves the way for further research.

Confusion surrounding cardiovascular disease trends arises when measurement and reporting of classification systems such as the International Classification of Diseases (ICD) code are revised. The current study examined the impact of ICD code revision on mortality trends for heart disease, cerebrovascular disease, and diabetes in 16 Southeast states using data published in the 1994-2005 Centers for Disease Control National Vital Statistics Reports. Data were averaged by year and analyzed separately before (1994-1998) and after (1999-2005) the ICD code change, pooled across codes using comparability ratios (1994-2005), and further compared at the year of ICD code change using standard error of 1998 data to determine whether corresponding 1999 rates fell within 95% confidence intervals. The change in classification did not alter Southeast US trends regarding a decrease in heart disease and cerebrovascular disease rates and an increase in diabetes mortality in years 1994-2005. On the other hand, the change in ICD code classification systems did impact mortality rates for heart disease, cerebrovascular disease, and diabetes, suggesting that change in code to ICD-10 in 1999 underestimates heart disease and cerebrovascular disease and overestimates diabetes mortality rates in the Southeast United States. Health and disease burden profiles, which use mortality data to measure health status, need to carefully evaluate and report the influence of ICD code revisions as they draw conclusions. Primary care health providers should question the impact and comparability of ICD revision before accepting mortality trend conclusions.

Defining suspected child maltreatment using International Classification of Diseases codes: A scoping literature review

BackgroundImmune checkpoint inhibitors (ICIs) have revolutionized cancer treatment, yet their use is associated with immune-related Adverse Events (irAEs). Estimating prevalence and patient impact of these irAEs in the Real-World Data...

Faults that are often invisible to existing inspection methods can significantly impact the reliability and efficiency of Photovoltaic (PV) systems. This study introduces an innovative framework for identifying PV panel faults using advanced machine learning algorithms and thermal images captured by unmanned aerial vehicles. The proposed Deep Recurrent Convolutional Neural Network (DRCNN) combines the strengths of Recurrent Neural Networks (RNNs) for learning temporal sequences and Convolutional Neural Networks (CNNs) for feature extraction. The DRCNN is designed to analyze thermal images of PV panels by capturing spatial and temporal patterns associated with fault-induced anomalies, such as hot spots, cracked cells or broken electrical connections. By leveraging CNN layers to extract critical features from thermal images and RNN layers to model the temporal dependencies and variations in thermal processes over time, the proposed approach integrates thermal image data collected under diverse environmental conditions.This dual strategy not only identifies faults based on spatial features but forecasts potential fault progression or the End-of-Life (EoL) for the panels by analyzing the evolution of thermal anomalies. The research aims to develop a highly accurate and efficient system for preventive maintenance and early problem detection, thereby improving the efficiency and durability of PV systems.The results demonstrate the DRCNN model's effectiveness in detecting various types of defects and delivering highly accurate real-time fault detection. By incorporating both spatial and temporal information, the proposed model significantly outperforms existing methods providing more robust and reliable defect identification.

Assessing the Accuracy of Emergency Department International Classification of Diseases Coding

The goal of this study was to evaluate an artificial intelligence approach, namely deep learning, on clinical text in electronic health records (EHRs) to identify patients with cirrhosis. Accurate identification of cirrhosis in EHR is important for epidemiological, health services, and outcomes research. Currently, such efforts depend on International Classification of Diseases (ICD) codes, with limited success. We trained several machine learning models using discharge summaries from patients with known cirrhosis from a patient registry and random controls without cirrhosis or its complications based on ICD codes. Models were validated on patients for whom discharge summaries were manually reviewed and used as the gold standard test set. We tested Naive Bayes and Random Forest as baseline models and a deep learning model using word embedding and a convolutional neural network (CNN). The training set included 446 cirrhosis patients and 689 controls, while the gold standard test set included 139 cirrhosis patients and 152 controls. Among the machine learning models, the CNN achieved the highest area under the receiver operating characteristic curve (0.993), with a precision of 0.965 and recall of 0.978, compared with 0.879 and 0.981 for the Naive Bayes and Random Forest, respectively (precision 0.787 and 0.958, and recalls 0.878 and 0.827). The precision by ICD codes for cirrhosis was 0.883 and recall was 0.978. A CNN model trained on discharge summaries identified cirrhosis patients with high precision and recall. This approach for phenotyping cirrhosis in the EHR may provide a more accurate assessment of disease burden in a variety of studies.