A framework for inferring and analyzing pharmacotherapy treatment patterns.

BACKGROUND: To discover pharmacotherapy prescription patterns and their statistical associations with outcomes through a clinical pathway inference framework applied to real-world data. METHODS: We apply machine learning steps in our framework using a 2006 to 2020 cohort of veterans with major depressive disorder (MDD). Outpatient antidepressant pharmacy fills, dispensed inpatient antidepressant medications, emergency department visits, self-harm, and all-cause mortality data were extracted from the Department of Veterans Affairs Corporate Data Warehouse. RESULTS: Our MDD cohort consisted of 252,179 individuals. During the study period there were 98,417 emergency department visits, 1,016 cases of self-harm, and 1,507 deaths from all causes. The top ten prescription patterns accounted for 69.3% of the data for individuals starting antidepressants at the fluoxetine equivalent of 20-39 mg. Additionally, we found associations between outcomes and dosage change. CONCLUSIONS: For 252,179 Veterans who served in Iraq and Afghanistan with subsequent MDD noted in their electronic medical records, we documented and described the major pharmacotherapy prescription patterns implemented by Veterans Health Administration providers. Ten patterns accounted for almost 70% of the data. Associations between antidepressant usage and outcomes in observational data may be confounded. The low numbers of adverse events, especially those associated with all-cause mortality, make our calculations imprecise. Furthermore, our outcomes are also indications for both disease and treatment. Despite these limitations, we demonstrate the usefulness of our framework in providing operational insight into clinical practice, and our results underscore the need for increased monitoring during critical points of treatment.

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.

Prevention of microbial colonization of feeding tubes in the intensive care unit.

BACKGROUND: Various microorganisms which increase the mortality rate in the intensive care unit (ICU) cause microbial colonization of the nasogastric tube (NGT) and use the NGT as a reservoir. AIM: To detect the colonization on the NGT and to determine the effect that training regarding hand hygiene, NGT management, and enteral feeding (EF) provided to ICU nurses and auxiliary service staff (ASS) has on the level of NGT colonization. STUDY DESIGN: A quasi-experimental pre-test and post-test control design was used in this study. Microbial samples were taken from the outer and inner parts of NGT. The microorganisms were categorized as: group 1, no risk; group 2, low risk pathogenic; group 3, high-risk pathogenic group. The training was given to nurses (n = 15) and ASS (n = 7). Hand hygiene, NGT, and EF care training are provided to nurses and ASS by researchers. A total of three training sessions were scheduled to be held in 3 weeks so that all health care staff members were trained. Each session lasted 2 h in total. Patients were assigned to a group if one of the microorganisms presented on the outer surface of the patient's feeding tube and/or on the hub. The hand hygiene compliance was evaluated by direct observation according to the World Health Organization hand hygiene indications. RESULTS: The study was conducted with 46 patients. Evaluating the patients for the presence of microorganisms before education revealed that 4.3% were in group 1, 21.8% were in group 2, and 73.9% were in group 3. After the education, evaluating the samples for the presence of microorganisms revealed that 39.1% were in group 1, 13% were in group 2, and 47.8% were in group 3. A statistically significant difference was found between the number of samples included in the groups after the participants had received training (H = 8.186; p = .017). CONCLUSIONS: An NGT could act as a reservoir of microbial colonization and high-risk microorganisms could be on the tube. Providing training not only to nurses but also to ASS will help reduce the risk of colonization. RELEVANCE TO CLINICAL PRACTICE: Eliminating such colonization with effective hand hygiene during NGT feeding is a cost-effective method. Providing training not only to nurses but also to ASS will help obtain the optimum benefit from patient care.

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.

A new methodological framework for hazard detection models in health information technology systems.

The adoption of health information technology (HIT) has facilitated efforts to increase the quality and efficiency of health care services and decrease health care overhead while simultaneously generating massive amounts of digital information stored in electronic health records (EHRs). However, due to patient safety issues resulting from the use of HIT systems, there is an emerging need to develop and implement hazard detection tools to identify and mitigate risks to patients. This paper presents a new methodological framework to develop hazard detection models and to demonstrate its capability by using the US Department of Veterans Affairs' (VA) Corporate Data Warehouse, the data repository for the VA's EHR. The overall purpose of the framework is to provide structure for research and communication about research results. One objective is to decrease the communication barriers between interdisciplinary research stakeholders and to provide structure for detecting hazards and risks to patient safety introduced by HIT systems through errors in the collection, transmission, use, and processing of data in the EHR, as well as potential programming or configuration errors in these HIT systems. A nine-stage framework was created, which comprises programs about feature extraction, detector development, and detector optimization, as well as a support environment for evaluating detector models. The framework forms the foundation for developing hazard detection tools and the foundation for adapting methods to particular HIT systems.

What is the optimal dose of intrathecal meperidine in open prostate surgery? A prospective double-blind randomized study.

OBJECTIVES: This study was an analysis of the effect of different dosages of intrathecal meperidine (40 mg, 50 mg, 60 mg, and 70 mg) on hemodynamic parameters, the duration of neural blockade, and the incidence of meperidine-related side effects in patients who underwent an open prostatectomy. METHODS: Sixty patients who underwent an open prostatectomy with combined spinal-epidural anesthesia were included. The patients were allocated to receive 1 of 4 different dosages of intrathecal meperidine (n=15 for each group): Group I: 40 mg, Group II: 50 mg, Group III: 60 mg, and Group IV: 70 mg. The duration of the block procedure, surgery duration, highest sensory block level, and anesthetic complications were recorded and analyzed. RESULTS: At 20 minutes after the spinal injection, the maximum sensory block level was T6 in Group I and II, and it was T5 in Group III and IV. The mean motor block scores at 20 minutes after the spinal injection were lower in Group I compared with the other groups (p<0.001 for all). The motor block duration was significantly shorter in Group I and II than in Group III and IV (p<0.001 for all). Surgeon satisfaction was greater in Group II, III, and IV compared with Group I (p<0.001 for all). Patient satisfaction was better in Group III and IV compared with Groups I and II (p<0.001 for all). CONCLUSION: Intrathecal meperidine at a dose of 60 mg exerted a sufficient analgesic effect with minimum side effects in patients undergoing open prostatectomy.

Granisetron or ondansentron to prevent hypotension after spinal anesthesia for elective cesarean delivery: A randomized placebo-controlled trial.

STUDY OBJECTIVE: This study aimed to compare the effects of high doses of ondansetron and granisetron before spinal anesthesia on hemodynamic parameters in patients undergoing elective cesarean section. DESIGN: A double-blinded randomized placebo-controlled trial. SETTING: Operating room. PATIENTS: A total of 120 parturients with term pregnancy undergoing elective cesarean section with combined spinal-epidural anesthesia were included. INTERVENTIONS: Three groups (n = 40 for each group) were formed by randomization. Five minutes before the anesthesia procedure, Group I received 8 mg intravenous (IV) ondansetron diluted in 10 ml normal saline, Group II received IV 3 mg granisetron diluted in 10 ml normal saline, and Group III received IV 10 ml normal saline. MEASUREMENTS: Following intrathecal drug administration, intraoperative hemodynamic changes were recorded every 2 min for 20 min and then every 5 min until the end of the operation. MAIN RESULTS: Twenty patients (50%) in Group I, 12 patients (30%) in Group II, and 29 patients (72.5%) in Group III had hypotension requiring treatment with IV ephedrine (P = 0.001). The ephedrine requirement in Group III was significantly higher than in Groups I (P = 0.033) and II (P < 0.001). Also, the ephedrine requirement in Group II was lower than in Group I, but the difference was not statistically significant (P = 0.055). The mean arterial pressure for the three groups differed in the 10th, 18th, and 60th minutes. The number of patients with nausea or vomiting was lower in Groups I and II than in Group III (P < 0.001). At 5 min, the Apgar scores were higher than 8 for all neonates. Postoperative scores for the visual analogue scale were similar for all groups. CONCLUSIONS: It was concluded that prophylactic IV administration of 3 mg of granisetron or 8 mg of ondansetron before spinal anesthesia results in a significantly lower ephedrine requirement compared to placebo.

Combined spinal epidural anesthesia in obese parturients undergoing cesarean surgery : A single-blinded randomized comparison of lateral decubitus and sitting positions.

BACKGROUND: There is a significant increase in number of obese pregnant women worldwide. Obese parturients undergoing cesarean section have a higher risk for hypotension and require higher doses of vasopressors following spinal anesthesia compared to nonobese parturients. OBJECTIVE: This study aimed to compare the maternal hemodynamic changes when combined spinal-epidural anesthesia (CSEA) is induced in the left lateral decubitus and sitting positions in obese pregnant women undergoing elective cesarean section. MATERIAL AND METHODS: In this study, pregnant women with full-term gestation diagnosed as obese undergoing elective cesarean section were included. Two groups were formed: the CSEA was performed in left lateral position in group I (n = 50) and in sitting position in group II (n = 50). At the end of the CSEA procedure, patients were placed in the supine position. When the sensory block reached at the upper level of T6 dermatome, surgery was initiated. Hemodynamic, anesthetic and neonatal parameters were recorded. RESULTS: In all patients, CSEA was successful and sufficient anesthesia was provided for surgery. Time to reach T6 dermatome sensory level in group II was found to be longer than group I (P = 0.011). At 20 min after spinal injection, the maximum sensory block level was similar in both groups. There were no significant differences between groups in terms of sensory block time and the time to requiring postoperative supplemental analgesics. There were no significant differences in terms of the volume of intravenous fluid administered, ephedrine and atropine requirements between groups. Both groups had similar systolic blood pressure, heart rate and oxygen saturation values during surgery and postoperatively. While both groups had similar diastolic blood pressure (DBP) values during surgery and at the 1st postoperative hour, group II had lower DBP values at the 2nd postoperative hour compared with group I (P = 0.04). CONCLUSION: Left lateral decubitus and sitting positions during performance of CSEA lead to similar maternal hemodynamic changes in obese pregnant women undergoing cesarean section.

Does local anesthetic temperature affect the onset and duration of ultrasound-guided infraclavicular brachial plexus nerve block?: a randomized clinical trial.

BACKGROUND: Infraclavicular brachial plexus nerve block is a commonly performed anesthesiology technique in the upper extremity. Local anesthetics may be administered at different temperatures for both neuraxial and peripheral nerve blocks. We aimed to evaluate the effects of the temperature of the local anesthetic at the time of administration on the onset and duration of sensory and motor blocks in infraclavicular brachial plexus nerve block. METHODS: A total of 80 patients undergoing elective upper extremity surgery were randomly assigned to one of the following groups using a computer-based randomization software; low temperature (4 °C) (Group L, n = 26), room temperature (25 °C) (Group R, n = 27) and warmed (37 °C) (Group W, n = 27). A 1:1 mixture of 2% lidocaine and 0.5% bupivacaine was used as local anesthetic. Infraclavicular brachial plexus nerve block was performed under ultrasound guidance in all patients preoperatively. The onset and duration of sensory and motor blocks were recorded. RESULTS: Each group had different onset of motor (p < 0.001) and sensory (p < 0.001) blocks. The duration of motor block was similar between groups (p = 221). However, a significant difference was found in the duration of sensory block between group L (399.1 ± 40.8 min) and group R (379.6 ± 27.6 min) (p = 0.043). There was no complication related to nerve block procedure. CONCLUSIONS: The administration of the local anesthetic at lower temperatures may prolong the onset of both motor and sensory blocks in infraclavicular brachial plexus nerve block.

[Rare reflex in regional anesthesia which have a high-risk in case of forgotten: Bezold-Jarisch reflex]. / Rejyonel anestezide nadir görülen unutulmasi durumunda yüksek risk tasiyan bir refleks: Bezold-Jarisch refleksi.

Bezold-Jarisch reflex is a reflex that may occur during regional anesthesia, upper-extremity blocks and sometimes in general anesthesia, resulting in hypotension, bradycardia, apnea or cardiac arrest elicited by chemical or mechanical receptor stimulations. This reflex mostly occurs in the sitting position during upper-extremity nerve blocks can be forgotten in other complications. The complications that occurred after this reflex can be overcome by taking necessary precautions and providing sufficient cardiac monitorization. In our cases to be presented, we want to remind you of Bezold-Jarisch reflex, which may cause severe complications when forgotten.

Feature Engineering and Process Mining to Enable Hazard Detection in Health Information Technology.

In this work, we aim to enhance the reliability of health information technology (HIT) systems by detection of plausible HIT hazards in clinical order transactions. In the absence of well-defined event logs in corporate data warehouses, our proposed approach identifies relevant timestamped data fields that could indicate transactions in the clinical order life cycle generating raw event sequences. Subsequently, we adopt state transitions of the OASIS Human Task standard to map the raw event sequences and simplify the complex process that clinical radiology orders go through. We describe how the current approach provides the potential to investigate areas of improvement and potential hazards in HIT systems using process mining. The discussion concludes with a use case and opportunities for future applications.

Comparing the Clinical Features and Trauma Scores of Trauma Patients Aged Under 65 Years with Those of Patients Aged over 65 Years in the Intensive Care Unit: A Retrospective Study for Last Ten Years.

OBJECTIVE: This retrospective study aimed to compare the clinical characteristics and trauma scores of Intensive Care Unit (ICU) trauma patients 65 years and older with the patients under 65 years old. MATERIALS AND METHODS: Trauma patients (n=161) who stayed at least 24 hours in ICU were included. Patients younger than 65 years were included into Group 1 (n=109) and patients aged ≥65 years (n=52) were included into Group 2. Patient characteristics and trauma index scores (GCS; APACHE II score, ISS; TRISS and RTS) at ICU admission were calculated. RESULTS: The patients in Group 2 had more comorbid disease compared with Group 1 (61.5%, 6.4%) (p=0.001). The Trauma-related Injury Severity Score score were higher in Group 1 (49.76±33.75) compared with Group 2 (35.38±34.93) (p=0.006). The APACHE II score were higher in Group 2 (20.08±7.60) compared with Group 1 (17.00±6.90) (p=0.007). The need for invasive mechanical ventilation and tracheostomy were more frequent in Group 2 trauma patients compared with those of patients in Group 1 (92.3%, 73.4%; p=0.003; 26.9%, 8.3%; p=0.002; respectively). The need for transfusion of packed red blood cell suspension (PRBC) was more frequent in Group 2 compared with Group 1 (92.3%, 55.0%; respectively) (p=0.001). The mortality rate was found to be higher in Group 2 compared with Group 1 (48.1%, 19.3%; respectively) (p=0.001). CONCLUSION: The elderly trauma patients have more comorbid disease, higher scores for APACHE II and lower scores for TRISS, more mechanical ventilation and tracheostomy requirements and higher mortality rate compared with young trauma patients.

Real-Time Automated Hazard Detection Framework for Health Information Technology Systems.

An increase in the reliability of Health Information Technology (HIT) will facilitate institutional trust and credibility of the systems. In this paper, we present an end-to-end framework for improving the reliability and performance of HIT systems. Specifically, we describe the system model, present some of the methods that drive the model, and discuss an initial implementation of two of the proposed methods using data from the Veterans Affairs HIT and Corporate Data Warehouse systems. The contributions of this paper, thus, include (1) the design of a system model for monitoring and detecting hazards in HIT systems, (2) a data-driven approach for analysing the health care data warehouse, (3) analytical methods for characterising and analysing failures in HIT systems, and (4) a tool architecture for generating and reporting hazards in HIT systems. Our goal is to work towards an automated system that will help identify opportunities for improvements in HIT systems.

Evaluation of pain scoring and free cortisol levels of postoperative analgesic methods in cardiac surgery: A new perspective.

BACKGROUND: This study aims to evaluate the most appropriate analgesic method of minimizing postoperative pain to prevent complications in patients scheduled for cardiac surgery. METHODS: Between January 2016 and June 2016, a total of 60 patients with the American Society of Anesthesiologists Physical Status Class III (27 males, 33 females; mean age 63 years; range, 49 to 77 years) with an ejection fraction of above 50% who underwent elective coronary artery bypass grafting were included. The patients were divided into two groups following admission to the intensive care unit. Group 1 (n=30) was administered intravenous fentanyl citrate with patient-controlled analgesia protocol, while Group 2 (n=30) was administered 0.1% bupivacaine hydrochloride analgesia protocol with catheter placed between the sternum and subcutaneous tissue. RESULTS: In Group 1, pain intensity scores at two h and visual analog scale scores except at 24, 36, and 48 h were higher than Group 2 (p<0.05). The length of intensive care unit stay and urine cortisol levels were higher in Group 1 than Group 2 (78±12 h and 631±505 ?g at 24 h vs. 66±13 h and 401±297 ?g at 24 h, respectively p<0.05). Partial pressure of oxygen levels at 10 and 16 h during the postoperative intensive care unit stay were lower, while partial pressure of carbon dioxide levels at 24 h was higher in Group 1 than Group 2 (p<0.05). CONCLUSION: The bupivacaine protocol is a relatively more useful analgesic method which produces improved results in blood gas analysis by reducing the effects of pain and shortens the length of intensive care unit stay. Low levels of free cortisol also confirm this finding.

The Effect of the Modified Thoracolumbar Interfacial Nerve Plane Block on Postoperative Analgesia and Healing Quality in Patients Undergoing Lumbar Disk Surgery: A Prospective, Randomized Study.

OBJECTIVE: The purpose of this study was to investigate the effect of the modified thoracolumbar interfascial plane block (TLIP) on postoperative analgesia and quality of recovery in patients undergoing lumbar disk surgery. METHOD: Ninety patients scheduled for lumbar disk surgery were divided into a control group (Group C) and a modified TLIP block group (Group T). Controlled analgesia was administered to both groups. Pain evaluation was performed at 30 min and at 1., 2., 4., 8.,12., and 24. hrs using a VAS scale, with patients at rest and duringand patients completed the QoR-40 quality of recovery inventory. RESULTS: Fentanyl used during postoperative 24 hours was 742.5±220.3 mcg in Group C and 446.0±241.98 in Group T. Postoperative fentanyl consumption was statistically significantly lower in Group T (p<0.001) with a statistically significant intergroup difference. The patient's pain, physical independence, physical comfort, psychological support, and emotional support were compared using the QoR-40 questionnaire survey. Significant differences in favor of Group T were observed (p<0.001, p=0.017, p=0.002, p=0.001 and p<0.001, respectively). Static and dynamic pain scores in Group C and Group T were recorded at 30 min and at 1, 2, 4, 8, 12, and 24h. Mean static scores were statistically significantly different in favor of Group T with the exception of 8th and 12h assessments (p<0.05). Dynamic scores were statistically significantly different in favor of Group T at all time points (p<0.05). CONCLUSION: Pain scores, opioid consumption and QoR-40 values after lumbar disk surgery were superior in the group undergoing TLIP. We think that the modified TLIP block may be an important method in terms of postoperative analgesia and patient recovery for lumbar spinal disk surgery.

Erector Spinae Plane Block Catheter Insertion under Ultrasound Guidance for Thoracic Surgery: Case Series of Three Patients.

The erector spinae plane (ESP) block is a novel plane block first reported for thoracic analgesia. It affects the dorsal and ventral rami of the thoracic nerves. Owing to the ease of the technique and decreased risk of complication of the ESP block under ultrasound guidance, it can be a preferable procedure compared with other invasive techniques, such as neuraxial and nerve blocks. In this case report, we presented three patients who had thoracic surgery under general anesthesia. The ESP block and catheter placement was applied to the patients before operation. The catheter was inserted deep into the erector spinae muscle and was used successfully for postoperative pain management.