There are strong incentives to computerize medical records in the present health care environment, yet medical information is frequently personal and is protected by privacy law and by centuries of a tradition of confidentiality. It is not possible to eliminate all risk of inappropriate disclosure and use of medical information, either in a paper or an electronic system. Computerization of records increases the potential for abuse, but with appropriate attention to security measures, medical data can be made reasonably secure while preserving accessibility for those who truly need the information. Both for technical and legal reasons, paper records are still necessary in 1995, to back up electronic medical databases.

Increasing reliance on electronic medical records at large medical centers provides unique opportunities to perform population level analyses exploring disease progression and etiology. The massive accumulation of diagnostic, procedure, and laboratory codes in one place has enabled the exploration of co-occurring conditions, their risk factors, and potential prognostic factors. While most of the readily identifiable associations in medical records are (now) well known to the scientific community, there is no doubt many more relationships are still to be uncovered in EMR data. In this paper, we introduce a novel finding index to help with that task. This new index uses data mined from real-time PubMed abstracts to indicate the extent to which empirically discovered associations are already known (i.e., present in the scientific literature). Our methods leverage second-generation p-values, which better identify associations that are truly clinically meaningful. We illustrate our new method with three examples: Autism Spectrum Disorder, Alzheimer's Disease, and Optic Neuritis. Our results demonstrate wide utility for identifying new associations in EMR data that have the highest priority among the complex web of correlations and causalities. Data scientists and clinicians can work together more effectively to discover novel associations that are both empirically reliable and clinically understudied.

Randomized clinical trials (RCT) are the gold standard for informing treatment decisions. Observational studies are often plagued by selection bias, and expert-selected covariates may insufficiently adjust for confounding. We explore how unstructured clinical text can be used to reduce selection bias and improve medical practice. We develop a framework based on natural language processing to uncover interpretable potential confounders from text. We validate our method by comparing the estimated hazard ratio (HR) with and without the confounders against established RCTs. We apply our method to four cohorts built from localized prostate and lung cancer datasets from the Stanford Cancer Institute and show that our method shifts the HR estimate towards the RCT results. The uncovered terms can also be interpreted by oncologists for clinical insights. We present this proof-of-concept study to enable more credible causal inference using observational data, uncover meaningful insights from clinical text, and inform high-stakes medical decisions.

No abstract available

Oncology outcomes research could benefit from the use of an oncology-specific electronic medical record (EMR) network. The benefits and challenges of using EMR in general health research have been investigated; however, the utility of EMR for oncology outcomes research has not been explored. Compared to current available oncology databases and registries, an oncology-specific EMR could provide comprehensive and accurate information on clinical diagnoses, personal and medical histories, planned and actual treatment regimens, and post-treatment outcomes, to address research questions from patients, policy makers, the pharmaceutical industry, and clinicians/researchers. Specific challenges related to structural (eg, interoperability, data format/entry), clinical (eg, maintenance and continuity of records, variety of coding schemes), and research-related (eg, missing data, generalizability, privacy) issues must be addressed when building an oncology-specific EMR system. Researchers should engage with medical professional groups to guide development of EMR systems that would ultimately help improve the quality of cancer care through oncology outcomes research.

The surge in deep learning-driven EMR research has centered on harnessing diverse data forms. Yet, the amalgamation of diverse modalities within time series data remains an underexplored realm. This study probes a multimodal fusion approach, merging temporal and non-temporal clinical notes along with tabular data. We leveraged data from 1271 myocardial infarction and 6450 stroke inpatients at a Beijing tertiary hospital. Our dataset encompassed static, and time series note data, coupled with static and time series table data. The temporal data underwent a preprocessing phase, padding to a 30-day interval, and segmenting into 3-day sub-sequences. These were fed into a long short-term memory (LSTM) network for sub-sequence representation. Multimodal attention gates were implemented for both static and temporal subsequence representations, culminating in fused representations. An attention-backtracking module was introduced for the latter, adept at capturing enduring dependencies in temporal fused representations. The concatenated results were channeled into an LSTM to yield the ultimate fused representation. Initially, two note modalities were designated as primary modes, and subsequently, the proposed fusion model was compared with comparative models including recent models such as Crossformer. The proposed model consistently exhibited superior predictive prowess in both tasks. Removing the attention-backtracking module led to performance decline. The proposed model consistently shows excellent predictive capabilities in both tasks. The proposed method not only effectively integrates data from the four modalities, but also has a good understanding of how to handle irregular time series data and lengthy clinical texts. An effective method is provided, which is expected to be more widely used in multimodal medical data representation.

Hormones control the major biological functions of stress response, growth, metabolism, and reproduction. In animals, these hormones show pronounced seasonality, with different set-points for different seasons. In humans, the seasonality of these hormones remains unclear, due to a lack of datasets large enough to discern common patterns and cover all hormones. Here, we analyze an Israeli health record on 46 million person-years, including millions of hormone blood tests. We find clear seasonal patterns: The effector hormones peak in winter-spring, whereas most of their upstream regulating pituitary hormones peak only months later, in summer. This delay of months is unexpected because known delays in the hormone circuits last hours. We explain the precise delays and amplitudes by proposing and testing a mechanism for the circannual clock: The gland masses grow with a timescale of months due to trophic effects of the hormones, generating a feedback circuit with a natural frequency of about a year that can entrain to the seasons. Thus, humans may show coordinated seasonal set-points with a winter-spring peak in the growth, stress, metabolism, and reproduction axes.

This paper is an extension of the work originally presented in the 16th International Conference on Wearable, Micro and Nano Technologies for Personalized Health. Despite using electronic medical records, free narrative text is still widely used for medical records. To make data from texts available for decision support systems, supervised machine learning algorithms might be successfully applied. In this work, we developed and compared a prototype of a medical data extraction system based on different artificial neural network architectures to process free medical texts in the Russian language. Three classifiers were applied to extract entities from snippets of text. Multi-layer perceptron (MLP) and convolutional neural network (CNN) classifiers showed similar results to all three embedding models. MLP exceeded convolutional network on pipelines that used the embedding model trained on medical records with preliminary lemmatization. Nevertheless, the highest F-score was achieved by CNN. CNN slightly exceeded MLP when the biggest word2vec model was applied (F-score 0.9763).

De-identification is the first step to use these records for data processing or further medical investigations in electronic medical records. Consequently, a reliable automated de-identification system would be of high value.

A lot of effort is being done in the electronic medical record (EMR) system. However, it has not been implemented and used at the expected scale for maximal effectiveness. There is limited evidence on the factors affecting the utilization of EMR in this particular context, which are critical for targeted strategies.

Electronic health records (EHRs) have become ubiquitous in medicine and continue to grow in informational content. Little has been documented regarding patient safety from the resultant information overload. The objective of this literature review is to better understand how information overload in EHR affects patient safety.

Globally, ovarian cancer (OC) is the leading cause of gynecological cancer-associated deaths. Metastasis, especially multi-organ metastasis, determines the speed of disease progression. A multicenter retrospective study was performed to identify the factors that drive metastasis, from medical records of 534 patients with OC. The average number of target organs per patient was 3.66, indicating multi-organ metastasis. The most common sites of metastasis were large intestine and greater omentum, which were prone to co-metastasis. Results indicated that ascites and laterality, rather than age and menopausal status, were the potential drivers for multi-organ metastasis. Cancer antigen (CA) 125 (CA-125) and nine other blood indicators were found to show a significant, but weak correlation with multi-organ metastasis. A neural network cascade-multiple linear regression hybrid model was built to create an ovarian cancer metastasis index (OCMI) by integration of six multi-organ metastasis drivers including CA-125, blood platelet count, lymphocytes percentage, prealbumin, ascites, and laterality. In an independent set of 267 OC medical records, OCMI showed a moderate correlation with multi-organ metastasis (Spearman ρ = 0.67), the value being 0.72 in premenopausal patients, and good performance in identifying multi-organ metastasis (area under the receiver operating characteristic curve = 0.832), implying a potential prognostic marker for OC.

Capgras delusion is scientifically important but most commonly reported as single case studies. Studies analysing large clinical records databases focus on common disorders but none have investigated rare syndromes.

Postpartum hemorrhage (PPH) remains a leading cause of preventable maternal mortality in the United States. We sought to develop a novel risk assessment tool and compare its accuracy to tools used in current practice.

Medical records scoring is important in a health care system. Artificial intelligence (AI) with projection word embeddings has been validated in its performance disease coding tasks, which maintain the vocabulary diversity of open internet databases and the medical terminology understanding of electronic health records (EHRs). We considered that an AI-enhanced system might be also applied to automatically score medical records. This study aimed to develop a series of deep learning models (DLMs) and validated their performance in medical records scoring task. We also analyzed the practical value of the best model. We used the admission medical records from the Tri-Services General Hospital during January 2016 to May 2020, which were scored by our visiting staffs with different levels from different departments. The medical records were scored ranged 0 to 10. All samples were divided into a training set (n = 74,959) and testing set (n = 152,730) based on time, which were used to train and validate the DLMs, respectively. The mean absolute error (MAE) was used to evaluate each DLM performance. In original AI medical record scoring, the predicted score by BERT architecture is closer to the actual reviewer score than the projection word embedding and LSTM architecture. The original MAE is 0.84 ± 0.27 using the BERT model, and the MAE is 1.00 ± 0.32 using the LSTM model. Linear mixed model can be used to improve the model performance, and the adjusted predicted score was closer compared to the original score. However, the project word embedding with the LSTM model (0.66 ± 0.39) provided better performance compared to BERT (0.70 ± 0.33) after linear mixed model enhancement (p < 0.001). In addition to comparing different architectures to score the medical records, this study further uses a mixed linear model to successfully adjust the AI medical record score to make it closer to the actual physician's score.

Developments in machine learning in recent years have precipitated a surge in research on the applications of artificial intelligence within medicine. Machine learning algorithms are beginning to impact medicine broadly, and the field of spine surgery is no exception. Electronic medical records are a key source of medical data that can be leveraged for the creation of clinically valuable machine learning algorithms. This review examines the current state of machine learning using electronic medical records as it applies to spine surgery. Studies across the electronic medical record data domains of imaging, text, and structured data are reviewed. Discussed applications include clinical prognostication, preoperative planning, diagnostics, and dynamic clinical assistance, among others. The limitations and future challenges for machine learning research using electronic medical records are also discussed.

The success of electronic medical records (EMRs) is dependent on implementation features, such as usability and fit with clinical processes. The use of EMRs in mental health settings brings additional and specific challenges owing to the personal, detailed, narrative, and exploratory nature of the assessment, diagnosis, and treatment in this field. Understanding the determinants of successful EMR implementation is imperative to guide the future design, implementation, and investment of EMRs in the mental health field.

The ability of caregivers and investigators to share patient data is fundamental to many areas of clinical practice and biomedical research. Prior to sharing, it is often necessary to remove identifiers such as names, contact details, and dates in order to protect patient privacy. Deidentification, the process of removing identifiers, is challenging, however. High-quality annotated data for developing models is scarce; many target identifiers are highly heterogenous (for example, there are uncountable variations of patient names); and in practice anything less than perfect sensitivity may be considered a failure. As a result, patient data is often withheld when sharing would be beneficial, and identifiable patient data is often divulged when a deidentified version would suffice. In recent years, advances in machine learning methods have led to rapid performance improvements in natural language processing tasks, in particular with the advent of large-scale pretrained language models. In this paper we develop and evaluate an approach for deidentification of clinical notes based on a bidirectional transformer model. We propose human interpretable evaluation measures and demonstrate state of the art performance against modern baseline models. Finally, we highlight current challenges in deidentification, including the absence of clear annotation guidelines, lack of portability of models, and paucity of training data. Code to develop our model is open source, allowing for broad reuse.

Medicine 2.0-the adoption of Web 2.0 technologies such as social networks in health care-creates the need for apps that can find other patients with similar experiences and health conditions based on a patient's electronic health record (EHR). Concurrently, there is an increasing number of longitudinal EHR data sets with rich information, which are essential to fulfill this need.

Padua linear model is widely used for the risk assessment of venous thromboembolism (VTE), a common but preventable complication for inpatients. However, genetic and environmental differences between Western and Chinese population limit the validity of Padua model in Chinese patients. Medical records which contain rich information about disease progression, are useful in mining new risk factors related to Chinese VTE patients. Furthermore, machine learning (ML) methods provide new opportunities to build precise risk prediction model by automatic selection of risk factors based on original medical records.