Time Series AI Model for Acute Kidney Injury Detection Based on a Multicenter Distributed Research Network: Development and Verification Study.

Background: Acute kidney injury (AKI) is a marker of clinical deterioration and renal toxicity. While there are many studies offering prediction models for the early detection of AKI, those predicting AKI occurrence using distributed research network (DRN)-based time series data are rare. Objective: In this study, we aimed to detect the early occurrence of AKI by applying an interpretable long short-term memory (LSTM)-based model to hospital electronic health record (EHR)-based time series data in patients who took nephrotoxic drugs using a DRN. Methods: We conducted a multi-institutional retrospective cohort study of data from 6 hospitals using a DRN. For each institution, a patient-based data set was constructed using 5 drugs for AKI, and an interpretable multivariable LSTM (IMV-LSTM) model was used for training. This study used propensity score matching to mitigate differences in demographics and clinical characteristics. Additionally, the temporal attention values of the AKI prediction model's contribution variables were demonstrated for each institution and drug, with differences in highly important feature distributions between the case and control data confirmed using 1-way ANOVA. Results: This study analyzed 8643 and 31,012 patients with and without AKI, respectively, across 6 hospitals. When analyzing the distribution of AKI onset, vancomycin showed an earlier onset (median 12, IQR 5-25 days), and acyclovir was the slowest compared to the other drugs (median 23, IQR 10-41 days). Our temporal deep learning model for AKI prediction performed well for most drugs. Acyclovir had the highest average area under the receiver operating characteristic curve score per drug (0.94), followed by acetaminophen (0.93), vancomycin (0.92), naproxen (0.90), and celecoxib (0.89). Based on the temporal attention values of the variables in the AKI prediction model, verified lymphocytes and calcvancomycin ium had the highest attention, whereas lymphocytes, albumin, and hemoglobin tended to decrease over time, and urine pH and prothrombin time tended to increase. Conclusions: Early surveillance of AKI outbreaks can be achieved by applying an IMV-LSTM based on time series data through an EHR-based DRN. This approach can help identify risk factors and enable early detection of adverse drug reactions when prescribing drugs that cause renal toxicity before AKI occurs.

Polypharmacy and Elevated Risk of Severe Adverse Events in Older Adults Based on the Korea Institute of Drug Safety and Risk Management-Korea Adverse Event Reporting System Database.

BACKGROUND: Older adults are at a higher risk of severe adverse drug events (ADEs) because of multimorbidity, polypharmacy, and lower physiological function. This study aimed to determine whether polypharmacy, defined as the use of ≥ 5 active drug ingredients, was associated with severe ADEs in this population. METHODS: We used ADE reports from the Korea Institute of Drug Safety and Risk Management-Korea Adverse Event Reporting System Database, a national spontaneous ADE report system, from 2012 to 2021 to examine and compare the strength of association between polypharmacy and severe ADEs in older adults (≥ 65 years) and younger adults (20-64 years) using disproportionality analysis. RESULTS: We found a significant association between severe ADEs of cardiac and renal/urinary Medical Dictionary for Regulatory Activities System Organ Classes (MedDRA SOC) with polypharmacy in older adults. Regarding individual-level ADEs included in these MedDRA SOCs, acute cardiac arrest and renal failure were more significantly associated with polypharmacy in older adults compared with younger adults. CONCLUSION: The addition of new drugs to the regimens of older adults warrants close monitoring of renal and cardiac symptoms.

MetaLAB-HOI: Template standardization of health outcomes enable massive and accurate detection of adverse drug reactions from electronic health records.

PURPOSE: This study aimed to advance the MetaLAB algorithm and verify its performance with multicenter data to effectively detect major adverse drug reactions (ADRs), including drug-induced liver injury. METHODS: Based on MetaLAB, we created an optimal scenario for detecting ADRs by considering demographic and clinical records. MetaLAB-HOI was developed to identify ADR signals using common model-based multicenter electronic health record (EHR) data from the clinical health outcomes of interest (HOI) template and design for drug-exposed and nonexposed groups. In this study, we calculated the odds ratio of 101 drugs for HOI in Konyang University Hospital, Seoul National University Hospital, Chungbuk National University Hospital, and Seoul National University Bundang Hospital. RESULTS: The overlapping drugs in four medical centers are amlodipine, aspirin, bisoprolol, carvedilol, clopidogrel, clozapine, digoxin, diltiazem, methotrexate, and rosuvastatin. We developed MetaLAB-HOI, an algorithm that can detect ADRs more efficiently using EHR. We compared the detection results of four medical centers, with drug-induced liver injuries as representative ADRs. CONCLUSIONS: MetaLAB-HOI's strength lies in fully utilizing the patient's clinical information, such as prescription, procedure, and laboratory results, to detect ADR signals. Considering changes in the patient's condition over time, we created an algorithm based on a scenario that accounted for each drug exposure and onset period supervised by specialists for HOI. We determined that when a template capable of detecting ADR based on clinical evidence is developed and manualized, it can be applied in medical centers for new drugs with insufficient data.

Effective data quality management for electronic medical record data using SMART DATA.

OBJECTIVES: In the medical field, we face many challenges, including the high cost of data collection and processing, difficult standards issues, and complex preprocessing techniques. It is necessary to establish an objective and systematic data quality management system that ensures data reliability, mitigates risks caused by incorrect data, reduces data management costs, and increases data utilization. We introduce the concept of SMART data in a data quality management system and conducted a case study using real-world data on colorectal cancer. METHODS: We defined the data quality management system from three aspects (Construction - Operation - Utilization) based on the life cycle of medical data. Based on this, we proposed the "SMART DATA" concept and tested it on colorectal cancer data, which is actual real-world data. RESULTS: We define "SMART DATA" as systematized, high-quality data collected based on the life cycle of data construction, operation, and utilization through quality control activities for medical data. In this study, we selected a scenario using data on colorectal cancer patients from a single medical institution provided by the Clinical Oncology Network (CONNECT). As SMART DATA, we curated 1,724 learning data and 27 Clinically Critical Set (CCS) data for colorectal cancer prediction. These datasets contributed to the development and fine-tuning of the colorectal cancer prediction model, and it was determined that CCS cases had unique characteristics and patterns that warranted additional clinical review and consideration in the context of colorectal cancer prediction. CONCLUSIONS: In this study, we conducted primary research to develop a medical data quality management system. This will standardize medical data extraction and quality control methods and increase the utilization of medical data. Ultimately, we aim to provide an opportunity to develop a medical data quality management methodology and contribute to the establishment of a medical data quality management system.

Development and Verification of Time-Series Deep Learning for Drug-Induced Liver Injury Detection in Patients Taking Angiotensin II Receptor Blockers: A Multicenter Distributed Research Network Approach.

OBJECTIVES: The objective of this study was to develop and validate a multicenter-based, multi-model, time-series deep learning model for predicting drug-induced liver injury (DILI) in patients taking angiotensin receptor blockers (ARBs). The study leveraged a national-level multicenter approach, utilizing electronic health records (EHRs) from six hospitals in Korea. METHODS: A retrospective cohort analysis was conducted using EHRs from six hospitals in Korea, comprising a total of 10,852 patients whose data were converted to the Common Data Model. The study assessed the incidence rate of DILI among patients taking ARBs and compared it to a control group. Temporal patterns of important variables were analyzed using an interpretable timeseries model. RESULTS: The overall incidence rate of DILI among patients taking ARBs was found to be 1.09%. The incidence rates varied for each specific ARB drug and institution, with valsartan having the highest rate (1.24%) and olmesartan having the lowest rate (0.83%). The DILI prediction models showed varying performance, measured by the average area under the receiver operating characteristic curve, with telmisartan (0.93), losartan (0.92), and irbesartan (0.90) exhibiting higher classification performance. The aggregated attention scores from the models highlighted the importance of variables such as hematocrit, albumin, prothrombin time, and lymphocytes in predicting DILI. CONCLUSIONS: Implementing a multicenter-based timeseries classification model provided evidence that could be valuable to clinicians regarding temporal patterns associated with DILI in ARB users. This information supports informed decisions regarding appropriate drug use and treatment strategies.

Pneumatic tactile stimulus delivery system for studying brain responses evoked by active finger touch with fMRI.

BACKGROUND: Primates use their hands to actively touch objects and collect information. To study tactile information processing, it is important for participants to experience tactile stimuli through active touch while monitoring brain activities. NEW METHOD: Here, we developed a pneumatic tactile stimulus delivery system (pTDS) that delivers various tactile stimuli on a programmed schedule and allows voluntary finger touches during MRI scanning. The pTDS uses a pneumatic actuator to move tactile stimuli and place them in a finger hole. A photosensor detects the time when an index finger touches a tactile stimulus, enabling the analysis of the touch-elicited brain responses. RESULTS: We examined brain responses while the participants actively touched braille objects presented by the pTDS. BOLD responses during tactile perception were significantly stronger in a finger touch area of the contralateral somatosensory cortex compared with that of visual perception. CONCLUSION: The pTDS enables MR studies of brain mechanisms for tactile processes through natural finger touch.

Hippocampal integration and separation processes with different temporal and spatial dynamics during learning for associative memory.

The hippocampus is known to be critically involved in associative memory formation. However, the role of the hippocampus during the learning of associative memory is still controversial; while the hippocampus is considered to play a critical role in the integration of related stimuli, numerous studies also suggest a role of the hippocampus in the separation of different memory traces for rapid learning. Here, we employed an associative learning paradigm consisting of repeated learning cycles. By tracking the changes in the hippocampal representations of associated stimuli on a cycle-by-cycle basis as learning progressed, we show that both integration and separation processes occur in the hippocampus with different temporal dynamics. We found that the degree of shared representations for associated stimuli decreased significantly during the early phase of learning, whereas it increased during the later phase of learning. Remarkably, these dynamic temporal changes were observed only for stimulus pairs remembered 1 day or 4 weeks after learning, but not for forgotten pairs. Further, the integration process during learning was prominent in the anterior hippocampus, while the separation process was obvious in the posterior hippocampus. These results demonstrate temporally and spatially dynamic hippocampal processing during learning that can lead to the maintenance of associative memory.

Comparison of cardiocerebrovascular disease incidence between angiotensin converting enzyme inhibitor and angiotensin receptor blocker users in a real-world cohort.

BACKGROUND: Both angiotensin-converting enzyme inhibitors (ACEIs) and angiotensin II receptor blockers (ARBs) are known to be effective in managing cardiovascular diseases, but more evidence supports the use of an ACEI. This study investigated the difference in cardiovascular disease incidence between relatively low-compliance ACEIs and high-compliance ARBs in the clinical setting. METHODS: Patients who were first prescribed ACEIs or ARBs at two tertiary university hospitals in Korea were observed in this retrospective cohort study for the incidence of heart failure, angina, acute myocardial infarction, cerebrovascular disease, ischemic heart disease, and major adverse cardiovascular events for 5 years after the first prescription. Additionally, 5-year Kaplan-Meier survival curves were used based on the presence or absence of statins. RESULTS: Overall, 2,945 and 9,189 patients were prescribed ACEIs and ARBs, respectively. When compared to ACEIs, the incidence of heart failure decreased by 52% in those taking ARBs (HR [95% CI] = 0.48 [0.39-0.60], P < 0.001), and the incidence of cerebrovascular disease increased by 62% (HR [95% CI] = 1.62 [1.26-2.07], P < 0.001). The incidence of ischemic heart disease (P = 0.223) and major adverse cardiovascular events (P = 0.374) did not differ significantly between the two groups. CONCLUSIONS: ARBs were not inferior to ACEIs in relation to reducing the incidence of cardiocerebrovascular disease in the clinical setting; however, there were slight differences for each disease. The greatest strength of real-world evidence is that it allows the follow-up of specific drug use, including drug compliance. Large-scale studies on the effects of relatively low-compliance ACEIs and high-compliance ARBs on cardiocerebrovascular disease are warranted in the future.

Drug_SNSMiner: standard pharmacovigilance pipeline for detection of adverse drug reaction using SNS data.

As society continues to age, it is becoming increasingly important to monitor drug use in the elderly. Social media data have been used for monitoring adverse drug reactions. The aim of this study was to determine whether social network studies (SNS) are useful sources of drug side effects information. We propose a method for utilizing SNS data to plot the known side effects of geriatric drugs in a dosing map. We developed a lexicon of drug terms associated with side effects and mapped patterns from social media data. We confirmed that well-known side effects may be obtained by utilizing SNS data. Based on these results, we propose a pharmacovigilance pipeline that can be extended to unknown side effects. We propose the standard analysis pipeline Drug_SNSMiner for monitoring side effects using SNS data and evaluated it as a drug prescription platform for the elderly. We confirmed that side effects may be monitored from the consumer's perspective based on SNS data using only drug information. SNS data were deemed good sources of information to determine ADRs and obtain other complementary data. We established that these learning data are invaluable for AI requiring the acquisition of ADR posts on efficacious drugs.

Genital tract infection and pelvic surgery contribute to the development of endometriosis.

Endometriosis is a multifactorial disease, and inflammation is considered a core pathology. Inflammation related to genital tract infection (GTI) and surgical injury may cause endometriosis. Therefore, we investigated the incidence of endometriosis in women with a recent history of GTI, pelvic surgery, or both. Using the Korean National Health Insurance Service-National Sample Cohort, 20- to 49-year-old women diagnosed with GTI or who underwent pelvic surgeries between 2002 and 2008 were collected and followed up for five years. After excluding women who had already been diagnosed with endometriosis or diseases that may affect endometriosis, a total of 30,336 women were diagnosed with GTI (Study 1), 2894 women who underwent pelvic surgery (Study 2), and 788 women who underwent GTI and pelvic surgery, both (Study 3) were enrolled for each study. The comparison groups in which sociodemographic factors matched for each group were collected. The incidence of endometriosis per 1000 person-year was 5.37, 5.17, and 20.81 in each case group and was significantly higher than each comparison group. A recent history of GTI increased an adjusted hazard ratio (aHR) of 2.29 (1.99-2.63, 95% confidence interval) for the development of endometriosis. The aHRs of pelvic surgery history and the history of both GTI and pelvic surgery were 2.10 and 7.82, respectively. In conclusion, the pelvic inflammation resulting from genital infection and pelvic surgical injury may play a role in developing endometriosis. Active treatment of genital infections and careful surgical procedures to minimize tissue injury may reduce the incidence of pelvic endometriosis.

Time to surgery and survival in breast cancer.

BACKGROUND: This study aimed to investigate the effect of the time from diagnosis to breast cancer surgery on breast cancer patients' prognosis. METHODS: Of the 1900 patients diagnosed with invasive (stage 1-3) breast cancer who underwent surgery in KUH between 2012 and 2019, 279 patients were enrolled in this study. All patients, including those who received neoadjuvant chemotherapy, were classified as Model 1 subjects, and those who received immediate surgical treatment were classified as Model 2 subjects. We conducted a Cox regression analysis to identify prognostic factors of breast cancer associated with the time from diagnosis to surgery. RESULTS: The univariate results indicated a sharp drop in both groups' survival rates when the time to surgery was delayed for more than 8 weeks (Model 1 p = 0.000; Model 2 p = 0.001). In the multivariate analysis, the hazard ratio (HR) of Model 1increased (HR = 6.84, 95% CI 1.06-44.25) in response to a delay in surgery of more than 8 weeks. Smoking and the American Joint Committee on Cancer (AJCC) staging system had a negative effect on breast cancer prognosis, while hormone therapy had a positive effect. CONCLUSION: For all patients, a delay in breast cancer surgery of more than 8 weeks was inversely associated with survival.

A Data-Driven Reference Standard for Adverse Drug Reaction (RS-ADR) Signal Assessment: Development and Validation.

BACKGROUND: Pharmacovigilance using real-world data (RWD), such as multicenter electronic health records (EHRs), yields massively parallel adverse drug reaction (ADR) signals. However, proper validation of computationally detected ADR signals is not possible due to the lack of a reference standard for positive and negative associations. OBJECTIVE: This study aimed to develop a reference standard for ADR (RS-ADR) to streamline the systematic detection, assessment, and understanding of almost all drug-ADR associations suggested by RWD analyses. METHODS: We integrated well-known reference sets for drug-ADR pairs, including Side Effect Resource, Observational Medical Outcomes Partnership, and EU-ADR. We created a pharmacovigilance dictionary using controlled vocabularies and systematically annotated EHR data. Drug-ADR associations computed from MetaLAB and MetaNurse analyses of multicenter EHRs and extracted from the Food and Drug Administration Adverse Event Reporting System were integrated as "empirically determined" positive and negative reference sets by means of cross-validation between institutions. RESULTS: The RS-ADR consisted of 1344 drugs, 4485 ADRs, and 6,027,840 drug-ADR pairs with positive and negative consensus votes as pharmacovigilance reference sets. After the curation of the initial version of RS-ADR, novel ADR signals such as "famotidine-hepatic function abnormal" were detected and reasonably validated by RS-ADR. Although the validation of the entire reference standard is challenging, especially with this initial version, the reference standard will improve as more RWD participate in the consensus voting with advanced pharmacovigilance dictionaries and analytic algorithms. One can check if a drug-ADR pair has been reported by our web-based search interface for RS-ADRs. CONCLUSIONS: RS-ADRs enriched with the pharmacovigilance dictionary, ADR knowledge, and real-world evidence from EHRs may streamline the systematic detection, evaluation, and causality assessment of computationally detected ADR signals.

False memory confidence depends on the prefrontal reinstatement of true memory.

For confidence of memory, a neural basis such as traces of stored memories should be required. However, because false memories have never been stored, the neural basis for false memory confidence remains unclear. Here we monitored the brain activity in participants while they viewed learned or novel objects, subsequently decided whether each presented object was learned and assessed their confidence levels. We found that when novel objects are presented, false memory confidence significantly depends on the shared representations with learned objects in the prefrontal cortex. However, such a tendency was not found in posterior regions including the visual cortex, which may be involved in the processing of perceptual gist. Furthermore, the confidence-dependent shared representations were not observed when participants correctly answered novel objects as non-learned objects. These results demonstrate that false memory confidence is critically based on the reinstatement of high-level semantic gist of stored memories in the prefrontal cortex.

Stronger memory representation after memory reinstatement during retrieval in the human hippocampus.

Memory retrieval allows us to reinstate previously encoded information but is also considered to contribute to memory enhancement. Retrieval-induced enhancement may involve processing to strengthen memory traces, but neural processing beyond reinstatement during retrieval remains elusive. Here, we show that hippocampal processing, different from memory reinstatement, exists during retrieval in the human brain. By tracking changes in the response patterns in the selected hippocampal and cortical regions over time during retrieval based on functional MRI, we found that the representation of associative memory in CA3/DG became stronger even after cortical memory reinstatement, while CA1 showed significant memory representation at retrieval onset with the cortical reinstatement, but not afterwards. This tendency was not observed in the condition without active retrieval. Moreover, subsequent long-term memory performance depended on the delayed CA3/DG representation during retrieval. These findings suggest that CA3/DG contributes to neural processing beyond memory reinstatement during retrieval, which may lead to memory enhancement.

The Common Effects of Sleep Deprivation on Human Long-Term Memory and Cognitive Control Processes.

Sleep deprivation is known to have adverse effects on various cognitive abilities. In particular, a lack of sleep has been reported to disrupt memory consolidation and cognitive control functions. Here, focusing on long-term memory and cognitive control processes, we review the consistency and reliability of the results of previous studies of sleep deprivation effects on behavioral performance with variations in the types of stimuli and tasks. Moreover, we examine neural response changes related to these behavioral changes induced by sleep deprivation based on human fMRI studies to determine the brain regions in which neural responses increase or decrease as a consequence of sleep deprivation. Additionally, we discuss about the possibility that light as an environmentally influential factor affects our sleep cycles and related cognitive processes.

Analyzing adverse drug reaction using statistical and machine learning methods: A systematic review.

BACKGROUND: Adverse drug reactions (ADRs) are unintended negative drug-induced responses. Determining the association between drugs and ADRs is crucial, and several methods have been proposed to demonstrate this association. This systematic review aimed to examine the analytical tools by considering original articles that utilized statistical and machine learning methods for detecting ADRs. METHODS: A systematic literature review was conducted based on articles published between 2015 and 2020. The keywords used were statistical, machine learning, and deep learning methods for detecting ADR signals. The study was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses statement (PRISMA) guidelines. RESULTS: We reviewed 72 articles, of which 51 and 21 addressed statistical and machine learning methods, respectively. Electronic medical record (EMR) data were exclusively analyzed using the regression method. For FDA Adverse Event Reporting System (FAERS) data, components of the disproportionality method were preferable. DrugBank was the most used database for machine learning. Other methods accounted for the highest and supervised methods accounted for the second highest. CONCLUSIONS: Using the 72 main articles, this review provides guidelines on which databases are frequently utilized and which analysis methods can be connected. For statistical analysis, >90% of the cases were analyzed by disproportionate or regression analysis with each spontaneous reporting system (SRS) data or electronic medical record (EMR) data; for machine learning research, however, there was a strong tendency to analyze various data combinations. Only half of the DrugBank database was occupied, and the k-nearest neighbor method accounted for the greatest proportion.

A Study on Methodologies of Drug Repositioning Using Biomedical Big Data: A Focus on Diabetes Mellitus.

Drug repositioning is a strategy for identifying new applications of an existing drug that has been previously proven to be safe. Based on several examples of drug repositioning, we aimed to determine the methodologies and relevant steps associated with drug repositioning that should be pursued in the future. Reports on drug repositioning, retrieved from PubMed from January 2011 to December 2020, were classified based on an analysis of the methodology and reviewed by experts. Among various drug repositioning methods, the network-based approach was the most common (38.0%, 186/490 cases), followed by machine learning/deep learningbased (34.3%, 168/490 cases), text mining-based (7.1%, 35/490 cases), semantic-based (5.3%, 26/490 cases), and others (15.3%, 75/490 cases). Although drug repositioning offers several advantages, its implementation is curtailed by the need for prior, conclusive clinical proof. This approach requires the construction of various databases, and a deep understanding of the process underlying repositioning is quintessential. An in-depth understanding of drug repositioning could reduce the time, cost, and risks inherent to early drug development, providing reliable scientific evidence. Furthermore, regarding patient safety, drug repurposing might allow the discovery of new relationships between drugs and diseases.

Hybrid Method Incorporating a Rule-Based Approach and Deep Learning for Prescription Error Prediction.

INTRODUCTION: Recently, automated detection has been a new approach to address the risks posed by prescribing errors. This study focused on prescription errors and utilized real medical data to supplement the Drug Utilization Review (DUR)-based rules, the current prescription error detection method. We developed a new hybrid method through artificial intelligence for prescription error prediction by utilizing actual detection accuracy improvement to reduce 'warning fatigue' for doctors and improve medical care quality. OBJECT: This study was conducted in the Department of Pediatrics, targeting children sensitive to drugs to develop a prescription error detection system. Based on the DUR prescription history, 15,281 patient-level observations of children from Konyang University Hospital (KYUH)'s common data model (CDM) and DUR were collected and analyzed retrospectively. METHOD: Among the CDM data, inspection information was interlocked with DUR and reflected as standard information for model development; this included outpatient prescriptions from January 1 to December 31, 2018. Through consultation with pediatric clinicians, rule definitions and model development were conducted for 35 drugs, with 137,802 normal and 1609 prescription errors. RESULTS: We developed a novel hybrid method of error detection in the form of an advanced rule-based deep neural network (ARDNN), which showed the expected performance (precision: 72.86, recall: 81.01, F1 score: 76.72) and reduced alarm pop-up alert fatigue to below 10%. We also created an ARDNN-based comprehensive dashboard that allows doctors to monitor prescription errors with alarm pop-ups when prescribing medications. CONCLUSION: These results can advance the existing rule-based model by developing a prescription error detection model using deep learning. This method can improve overall medical efficiency and service quality by reducing doctors' fatigue.