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

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.

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.

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.

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...

IntroductionObservational studies constitute an important evidence base for hypoglycemia in diabetes management. This requires consistent and reliable ascertainment and reporting methodology, particularly in studies of type 2 diabetes where hypoglycemia...

Recognition of congenital heart disease in subsequent hospital visits among children with a prenatal diagnosis

February 28, 2013 marks the sixth international “Rare Disease Day”. On and around this day, hundreds of patient organizations from more than 60 countries and regions worldwide plan to host awareness campaigns in line with this year's theme, “Rare Disorders without Borders”. Public awareness of intractable and rare diseases has heightened in recent decades. Much progress has also been made worldwide, such as specific legislation to encourage discovery and development of orphan drugs in the United States (US), the European Union (EU), and some parts of Asia. However, there are still many gaps in knowledge with regard to therapeutic tools and strategies. Intractable and rare diseases cause patients substantial physical suffering, psychological despair, and economic hardships due to bleak therapeutic outcomes and the lack of practical support in everyday life. The features of intractable and rare diseases and the increasing number of types of identified diseases make these diseases an important public health issue and a challenge to medical care worldwide. The following are specific aspects of research on intractable and rare diseases that need to be promptly promoted. An International Classification of Diseases (ICD) code to promote the definition and classification of intractable and rare diseases Intractable diseases, or “nanbyo” (literally “hard-to-treat diseases” in Japanese), mainly refer to rare diseases that have resulted mostly from unidentifiable causes and/or a lack of clearly established or curative treatments. According to the World Health Organization (WHO), rare diseases are rare and often debilitating or even life-threatening diseases or conditions with a prevalence of 0.65–1‰. The conventional view is that rare diseases as a whole affect around 10% of individuals worldwide, but the definition and categorization of rare diseases differ slightly by region. In the US, rare diseases are defined as diseases that affect fewer than 200,000 Americans (prevalence of < 0.75‰), while stipulated prevalence rates in other regions are < 0.5‰ in the EU, fewer than 2,000 patients (prevalence of < 0.11‰) in Australia, fewer than 50,000 patients (prevalence of < 0.4‰) in Japan, fewer than 20,000 patients (prevalence of < 0.4‰) in South Korea, or a prevalence of < 0.1‰ in Taiwan. The current outlook for identification of a specific rare disease and estimation of the true burden of rare diseases is bleak given the lack of proper classification and coding of rare diseases. Currently, there is no special coding system for rare diseases. The current ICD code that is used in most countries is not suitable for rare diseases. The absence of a universally recognized coding system is an obstacle for reliable registration of patients in national or international databases, preventing assessment of the economic and social effects of rare diseases. Fortunately, the good news is that the European Rare Disease Task Force of the Health and Consumers Protection Directorate General of the European Commission has set up a working group to collaborate with the WHO on the ICD-10, and the group is considering all other existing classifications to provide the rare disease community with a uniform system. A revised ICD code is urgently needed to both promote the definition and classification of intractable and rare diseases and to obtain accurate epidemiological data on these diseases at the national and international levels. Specific legislation to encourage discovery and development of orphan drugs Currently, orphan drugs — the medicinal products intended for the diagnosis, prevention, or treatment of rare diseases — are a major facet of how rare diseases are dealt with. In the past few decades, many countries have realized that orphan drugs will not lead to substantial sales under normal market conditions because of the high costs and risks of drug development, insufficient knowledge of the pathophysiological mechanisms of rare diseases that the drugs diagnose or treat, and difficulties in conducting clinical trials with small patient populations and a small potential market. Therefore, specific legislation to encourage the discovery and development of orphan drugs was enacted in many countries and regions, including the US in 1983, Japan in 1993, Australia in 1997, the EU in 1999, Taiwan in 2000, and South Korea in 2003. Incentives include financial subsidies, market exclusivity, tax credits, fee waivers, fast track approval, and protocol assistance, resulting in substantial improvements in the treatment of patients with a range of rare diseases. While China is actively preparing to regulate and encourage the development of orphan drugs, it still lags far behind the US, the EU, Japan, and other countries and regions with orphan drug legislation. Evidence has shown that all of the incentives have successfully encouraged the development of new pharmaceutical products to treat rare diseases. Prior to 2010, 352 orphan drugs were approved in the US, helping an estimated 12 million Americans, compared to only 10 such drugs in the decade preceding the Orphan Drug Act (1983). Similarly, 720 drugs had received orphan drug designation from the European Medicines Agency (EMA) and 63 designated orphan medicinal products have been authorized for marketing in the EU. Furthermore, data have shown that an average of 15 new orphan drugs are approved annually in the US and 10-12 new orphan drugs are approved annually in the EU. Thus, China and other countries without orphan drug legislation need to promptly establish domestic legislative regulations and incentives to encourage discovery and development of orphan drugs. Government-funded special biomedical research programs to enhance basic and applied research on intractable and rare diseases Biomedical research on intractable and rare diseases has provided insights into the pathologies of these diseases and revealed their underlying mechanisms. Such work may ultimately reveal possible avenues to therapeutics. Moreover, once biomedical research identifies suitable drug candidates and becomes more translational, it will garner industry attention, potentially leading to safe and effective orphan drugs. In Western countries, many research centers or projects have been established to support special biomedical research programs on rare diseases and development of orphan drugs, such as the Office of Rare Diseases Research (ORDR) established in the US in 1993 within the National Institutes of Health (NIH) and the Rare Disease Task Force (RDTF) established in EU in 2004 within the European Commission Public Health Directorate. In Asian countries, biomedical research on intractable and rare diseases has made great advances in Japan due to the systematic Specified Disease Treatment Research Program established in 1972 with the support of the Ministry of Health, Labor, and Welfare. As a result, special research programs and research grants from government sources to study 130 diseases increased to 10 billion Japanese yen in 2010. Recently, 214 diseases were designated for a second round of special research programs. In China, support for special biomedical programs on intractable and rare disease research comes mainly from the National Natural Science Foundation of China (NSFC). Data showed that 366 projects (involving 32 rare diseases) were funded by the NSFC from 1999 to 2007 with total funding of 89.358 million RMB and annual funding of about 10 million RMB, accounting for just 1/10th of similar funding in the US. Special biomedical research programs that enhance basic and applied research on intractable and rare diseases would benefit patients through better diagnosis and more treatment choices. Government-funded special biomedical research programs need to be promptly implemented in China and other countries to promote research on intractable and rare diseases. Patients' advocacy organizations and disease registry networks to provide vast information on intractable and rare diseases In recent years, progress has been made in the dissemination of knowledge and information by established patients' advocacy organizations, such as the National Organization for Rare Disorders (NORD) in the US and the European Organization for Rare Diseases (EURORDIS) in Europe, but the delay in diagnosis and treatment is still a huge challenge to cope with. A survey of 18,000 individuals found that 25% of patients waited for 5-30 years before being correctly diagnosed and 40% of patients were diagnosed incorrectly before they were correctly diagnosed. Furthermore, clinical studies on orphan drugs also face challenges due to the small size of the trial population and the fact that patients are often geographically dispersed. Disease registry networks need to be established to promote epidemiological and basic research and improve the clinical outcome for patients with intractable and rare diseases. In Western countries, some web-based resources, such as the Rare Diseases Clinical Research Network (RDCRN) in the US and the Orphanet in Europe, have been established in order to facilitate collaboration on clinical outcomes and to share accumulated experience so that patients with intractable and rare diseases are not delayed access to orphan drugs. More patients' advocacy organizations and disease registry networks need to be promptly established to facilitate interaction among patients, clinicians, researchers, the pharmaceutical industry, and governmental bodies with the ultimate goal of promoting intractable and rare disease research worldwide. (February 28, 2013)

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

23. Natural language processing for automated identification of intraoperative vascular injury in anterior lumbar spine surgery

Fat grafting is commonly utilized to enhance outcomes in breast reconstruction. Despite their routine implementation, perioperative antibiotics lack sufficient evidence in reducing rates of surgical site infection (SSI). Leveraging the largest patient cohort to date, this study examines the association between perioperative antibiotics and SSI after fat grafting for breast reconstruction. The Epic Cosmos database (Verona, Wisconsin) was queried for patients who underwent fat grafting within one year following either implant-based or autologous breast reconstruction from January 2017 to January 2025. SSIs within 30 days were identified using either International Classification of Diseases (ICD) codes or identification of a new antibiotic prescription starting >7 days post-surgery. Perioperative antibiotics, age, body mass index (BMI), diabetes, smoking status, intraoperative intravenous antibiotics, and volume of fat grafted were included for multivariable regression. We analyzed 12,247 fat grafting procedures (8416 implant-based, 3831 autologous). In the implant-based cohort, perioperative antibiotics (OR, 1.21; P = 0.031), diabetes (OR, 1.65; P < 0.0001), higher BMI (OR, 1.02; P = 0.001), and younger age (OR, 0.99; P = 0.021) were significant risk factors for infection, defined by additional postoperative antibiotic prescriptions. For infections defined by ICD codes, only BMI was significantly associated with SSI (OR, 1.04; P = 0.001). In the autologous cohort, diabetes was the only significant risk factor for SSI (OR, 1.3; P = 0.033). Perioperative antibiotic prescriptions do not decrease SSI after fat grafting in either implant or autologous breast reconstruction patients. However, they are associated with increased additional postoperative antibiotic prescriptions in implant-based breast reconstruction patients. These data suggest reconsidering routine perioperative antibiotic prophylaxis and focusing on patient-specific risk factors.

AimsHeart failure (HF) is a clinical syndrome with no definitive diagnostic tests. HF registries are often based on manual reviews of medical records of hospitalized HF patients identified using International Classification of Diseases (ICD) codes. However, most HF patients are not hospitalized, and manual review of big electronic health record (EHR) data is not practical. The US Department of Veterans Affairs (VA) has the largest integrated healthcare system in the nation, and an estimated 1.5 million patients have ICD codes for HF (HF ICD‐code universe) in their VA EHR. The objective of our study was to develop artificial intelligence (AI) models to phenotype HF in these patients.Methods and resultsThe model development cohort (n = 20 000: training, 16 000; validation 2000; testing, 2000) included 10 000 patients with HF and 10 000 without HF who were matched by age, sex, race, inpatient/outpatient status, hospital, and encounter date (within 60 days). HF status was ascertained by manual chart reviews in VA's External Peer Review Program for HF (EPRP‐HF) and non‐HF status was ascertained by the absence of ICD codes for HF in VA EHR. Two clinicians annotated 1000 random snippets with HF‐related keywords and labelled 436 as HF, which was then used to train and test a natural language processing (NLP) model to classify HF (positive predictive value or PPV, 0.81; sensitivity, 0.77). A machine learning (ML) model using linear support vector machine architecture was trained and tested to classify HF using EPRP‐HF as cases (PPV, 0.86; sensitivity, 0.86). From the ‘HF ICD‐code universe’, we randomly selected 200 patients (gold standard cohort) and two clinicians manually adjudicated HF (gold standard HF) in 145 of those patients by chart reviews. We calculated NLP, ML, and NLP + ML scores and used weighted F scores to derive their optimal threshold values for HF classification, which resulted in PPVs of 0.83, 0.77, and 0.85 and sensitivities of 0.86, 0.88, and 0.83, respectively. HF patients classified by the NLP + ML model were characteristically and prognostically similar to those with gold standard HF. All three models performed better than ICD code approaches: one principal hospital discharge diagnosis code for HF (PPV, 0.97; sensitivity, 0.21) or two primary outpatient encounter diagnosis codes for HF (PPV, 0.88; sensitivity, 0.54).ConclusionsThese findings suggest that NLP and ML models are efficient AI tools to phenotype HF in big EHR data to create contemporary HF registries for clinical studies of effectiveness, quality improvement, and hypothesis generation.

Conceptual-driven classification for coding advise in health insurance reimbursement

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.

Background: Adult studies demonstrated that extremes of nutritional status adversely impact clinical outcomes in acute pancreatitis (AP). With rising prevalence of undernutrition/obesity in children, we analyzed the effect of nutritional status on the clinical outcomes in children and adolescents with acute pancreatitis. Methodology: We analyzed the Kids’ Inpatient Database (KID) between 2003 and 2016 to include all patients with a primary diagnosis of AP using specific International Classification of Diseases (ICD) codes. We classified into (1) undernutrition, (2) obesity and (3) control groups, based on ICD codes, and we compared severe acute pancreatitis and healthcare utilization (length of stay and hospitalization costs). Results: Total number of AP admissions was 39,805. The prevalence of severe AP was higher in the undernutrition and obesity groups than the control group (15.7% vs. 5.8% vs. 3.5% respectively, p < 0.001). Multivariate analyses demonstrated that undernutrition and obesity were associated with 2.5 and 1.6 times increased risk of severe AP, p < 0.001. Undernutrition was associated with an additional six days of hospitalization and almost $16,000 in hospitalization costs. Obesity was associated with an additional 0.5 day and almost $2000 in hospitalization costs, p < 0.001. Conclusion: Undernutrition and obesity were associated with greater severity of AP, as well as prolonged hospitalization stay and costs. It is imperative for treating clinicians to be aware of these high-risk groups to tailor management and strive for improved outcomes.

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.