EHR-BERT: A BERT-based model for effective anomaly detection in electronic health records.

OBJECTIVE: Physicians and clinicians rely on data contained in electronic health records (EHRs), as recorded by health information technology (HIT), to make informed decisions about their patients. The reliability of HIT systems in this regard is critical to patient safety. Consequently, better tools are needed to monitor the performance of HIT systems for potential hazards that could compromise the collected EHRs, which in turn could affect patient safety. In this paper, we propose a new framework for detecting anomalies in EHRs using sequence of clinical events. This new framework, EHR-Bidirectional Encoder Representations from Transformers (BERT), is motivated by the gaps in the existing deep-learning related methods, including high false negatives, sub-optimal accuracy, higher computational cost, and the risk of information loss. EHR-BERT is an innovative framework rooted in the BERT architecture, meticulously tailored to navigate the hurdles in the contemporary BERT method; thus, enhancing anomaly detection in EHRs for healthcare applications. METHODS: The EHR-BERT framework was designed using the Sequential Masked Token Prediction (SMTP) method. This approach treats EHRs as natural language sentences and iteratively masks input tokens during both training and prediction stages. This method facilitates the learning of EHR sequence patterns in both directions for each event and identifies anomalies based on deviations from the normal execution models trained on EHR sequences. RESULTS: Extensive experiments on large EHR datasets across various medical domains demonstrate that EHR-BERT markedly improves upon existing models. It significantly reduces the number of false positives and enhances the detection rate, thus bolstering the reliability of anomaly detection in electronic health records. This improvement is attributed to the model's ability to minimize information loss and maximize data utilization effectively. CONCLUSION: EHR-BERT showcases immense potential in decreasing medical errors related to anomalous clinical events, positioning itself as an indispensable asset for enhancing patient safety and the overall standard of healthcare services. The framework effectively overcomes the drawbacks of earlier models, making it a promising solution for healthcare professionals to ensure the reliability and quality of health data.

Preoperative Dyeing Technique for Decreasing Radiation Exposure in Unilateral Biportal Endoscopic Spine Surgery.

BACKGROUND: Minimally invasive surgery has many advantages, including early recovery and cosmetic preservation. However, the higher radiation exposure to physicians and patients has drawbacks. Preoperative tissue dyeing techniques are feasible options for reducing radiation exposure and procedure time, but their efficacy has not yet been evaluated. Therefore, this study aimed to evaluate surgical outcomes and reduce radiation exposure during unilateral biportal endoscopy surgery. METHODS: This was a prospective, case-controlled analysis in a tertiary hospital. Patients receiving experimental tissue dye and controls in the nondye group were compared from May 2020 to September 2021. The ipsilateral posterolateral approach (IPA) and the far lateral approach (FLA) were analyzed separately among all single-level spinal procedures without instrumentation. Operative details (operation time, improvement of back and leg pain, and length of hospital stay) and radiation exposure (dose and duration) were compared. RESULTS: A total of 88 cases were included, consisting of 64 interlaminar approaches (experimental: 33, control: 31) and 24 FLAs (experimental: 13 and control: 11). In the IPA approach, the patient and physician radiation exposure doses and duration decreased significantly. Conversely, for the FLA, only the duration of the physician exposure decreased significantly. CONCLUSIONS: Preoperative tissue dyeing techniques using IPA can reduce radiation exposure for physicians and patients. However, a decrease in the duration of radiation was observed only in physicians using the FLA. The dyeing technique is effective in IPA, but the efficacy of FLA is doubtful.

Endoscopic-assisted Surgery in the Treatment of Isolated Frontosphenoidal Craniosynostosis.

Isolated frontosphenoidal craniosynostosis is extremely rare, due to which diagnosis can be challenging. All the isolated cases reported have been treated by open surgical technique. We present a unique case report of an infant with an isolated frontosphenoidal synostosis corrected by a novel endoscopic surgical technique. The patient was a 5-month-old boy with worsening abnormal head shape indicating progressive right frontal bossing, left orbital displacement, and right occipital plagiocephaly. Computed tomography scan confirmed the diagnosis of left isolated frontosphenoidal craniosynostosis. Endoscopic-assisted surgical release was done starting with a 2.5-cm incision in the left temple area followed by a 2-cm strip osteotomy to excise the fused frontosphenoidal suture. Custom-made orthotic helmet therapy was started 2-weeks postsurgery, with excellent progress noted in the head shape confirmed by laser scans. The benefits of the endoscopic technique include smaller incision, decreased blood loss and need for blood transfusion, and decreased stay in hospital. This is the first case report showing the application of a novel endoscopic-assisted surgical treatment in an isolated frontosphenoidal craniosynostosis with no complications noted.

Detecting anomalous sequences in electronic health records using higher-order tensor networks.

Detecting anomalous sequences is an integral part of building and protecting modern large-scale health information technology (HIT) systems. These HIT systems generate a large volume of records of patients' state and significant events, which provide a valuable resource to help improve clinical decisions, patient care processes, and other issues. However, detecting anomalous sequences in electronic health records (EHR) remains a challenge in healthcare applications for several reasons, including imbalances in the data, complexity of relationships between events in the sequence, and the curse of dimensionality. Conventional anomaly detection methods use the finite sequence of events to discriminate sequences. They fail to incorporate salient event details under variable higher-order dependencies (e.g., duration between events) that can provide better discrimination of sequences in their models. To address this problem, we propose event sequence and subsequence anomaly detection algorithms that (1) use network-based representations of interactions in the data, (2) account for variable higher-order dependencies in the data, and (3) incorporate events duration for adequate discrimination of the data. The proposed approach identifies anomalies by monitoring the change in the graph after the test sequence is removed from the network. The change is quantified using graph distance metrics so that dramatic changes in the network can be attributed to the removed sequence. Furthermore, the proposed subsequence algorithm recommends plausible paths and salient information for the detected anomalous subsequences. Our results show that the proposed event sequence anomaly detection algorithm outperforms the baseline methods for both synthetic data and real-world EHR data.

COVID-19-associated meningoencephalitis complicated with intracranial hemorrhage: a case report.

The coronavirus pandemic that started in December 2019 is mainly related to clinical pictures consistent with respiratory symptoms; nevertheless, reports about neurological complications have recently appeared in the medical literature. We describe a case of a 36-year-old coronavirus-positive patient that was admitted on emergency basis; his clinical presentation included neurological symptoms such as drowsiness and mild confusion. Imaging revealed findings consistent with meningoencephalitis complicated by intracerebral hematoma and subdural hematoma. The latter was surgically evacuated after it became chronic and evidence of coronavirus was found in the fluid. Our experience confirms that neurological complications might be a likely event in COVID-19. Although uncommon, the possible occurrence of meningoencephalitis should be kept in mind by physicians involved in the management of COVID-19 patients. Early recognition of brain involvement may provide better prognosis, preventing evolution into intracerebral hemorrhagic events.

Introducing Cichorium Pumilum as a potential therapeutical agent against drug-induced benign breast tumor in rats.

Cichorium Pumilum (chicory) is could be a promising cancer treatment in which a photosensitizing drug concentrates in benign tumor cells and activated by quanta at certain wavelength. Such activated extracts could lead to cell death and tumor ablation. Previous studies have shown that Cichorium Pumilum (chicory) contains photosensitive compounds such as cichoriin, anthocyanins, lactucin, and Lactucopicrin. In the present study, the protective effect of sun light-activated Cichorium against the dimethylbenz[a]anthracene (DMBA) induced benign breast tumors to female Sprague-Dawley rats was investigated. Chicory's extract has significantly increase P.carbonyl (PC) and malondialdehyde (MDA) and decreases the hepatic levels of total antioxidant capacity (TAC) and superoxide dismutase (SOD) in benign breast tumors-induced group compared to control. It also significantly decrease the number of estrogen receptors ER-positive cells in tumor masses. These results suggest that chicory extracts could be used as herbal photosensitizing agent in treating benign breast tumor in rats.