Real-time Alerts Research Articles

Implementing real-time sepsis alerts using middleware and smartphone technology

Implementing real-time sepsis alerts using middleware and smartphone technology

Iot Enabled Pipeline Leakage Detection and Real Time Alert System in Oil and Gas Industry

Automation and control systems are necessary throughout oil & gas industries, to production and processing plants, and distribution and retailing of petroleum products. Pipelines are the efficient mode of transportations of fuels for processing plants over long distances. At present Automation is achieved by using PLC’s that are communicated through SCADA. But it is complex and remote operation is not possible. With the introduction of IoT, the pipeline leak detection system is improved through real-time monitoring of the pipelines. Our Proposed system is designed to detect even small leakage that occurs within the pipeline. The implementation of IoT in oil and gas industries prevents accidents and to make quick decisions based on real-time data.

A Mobile Phone-Based Telemonitoring Program for Heart Failure Patients After an Incidence of Acute Decompensation (Medly-AID): Protocol for a Randomized Controlled Trial.

BackgroundPatients with heart failure (HF) are at the highest risk for hospital readmissions during the first few weeks after discharge when patients are transitioning from hospital to home. Telemonitoring (TM) for HF management has been found to reduce mortality risk and hospital readmissions if implemented appropriately; however, the impact of TM targeted for patients recently discharged from hospital, for whom TM might have the biggest benefit, is still unknown. Medly, a mobile phone–based TM system that is currently being used as a standard of care for HF at a large Canadian hospital, may be an effective tool for the management of HF in patients recently discharged from hospital.ObjectiveThe objective of the Medly-After an Incidence of acute Decompensation (Medly-AID) trial is to determine the effect of Medly on the self-care and quality of life of patients with HF who have been recently discharged from hospital after an HF-related decompensation.MethodsA multisite multimethod randomized controlled trial (RCT) will be conducted at 2 academic hospitals and at least one community hospital to evaluate the impact of Medly-enabled HF management on the outcomes of patients with HF who had been hospitalized for HF-related decompensation and discharged during the 2 weeks before recruitment. The trial will include 144 participants with HF (74 in each control and intervention groups). Control patients will receive standard of care, whereas patients in the intervention group will receive standard of care and Medly. Specifically, patients in the intervention group will record daily weight, blood pressure, and heart rate and answer symptom-related questions via the Medly app. Medly will generate automated patient self-care messages such as to adjust diuretic medications, based on the rules-based algorithm personalized to the individual patient, and send real-time alerts to their health care providers as necessary. All patients will be followed for 3 months. Primary outcome measures are self-care and quality of life as measured through the validated questionnaires Self-Care of Heart Failure Index, EQ-5D-5L, and the Kansas City Cardiomyopathy Questionnaire-12. Secondary outcome measures for this study include cost of health care services used and health outcomes.ResultsPatient recruitment began in November 2018 at the Sunnybrook Health Sciences Centre, with a total of 35 participants recruited by July 30, 2019 (17 in the intervention group and 18 in the control group). The final analysis is expected to occur in the fall of 2020.ConclusionsThis RCT will be the first to assess the effectiveness of the Medly TM system for use following discharge from hospital after a HF-related decompensation.Trial RegistrationClinicalTrials.gov NCT03358303; https://clinicaltrials.gov/ct2/show/NCT03358303International Registered Report Identifier (IRRID)DERR1-10.2196/15753

Threat Alert Prioritization Using Isolation Forest and Stacked Auto Encoder With Day-Forward-Chaining Analysis

Security Incident and Event Manager (SIEM) is a security management approach designed to identify possible threats within a real-time enterprise environment. The main challenge for SIEM is to find critical security incidents among a huge number of less critical alerts coming from separate security products. The continuously growing number of internet-connected devices has led to the alert fatigue problem, which is defined as the inability of security operators to investigate each incoming alert from intrusion detection systems. This fatigue can lead to human errors and leave many alerts being not investigated. Aiming at reducing the number of less important threat alerts presented to security operators, this paper presents a new method for highlighting critical alerts with a minimal number of false negatives. The proposed method employs isolation forest to ensure unsupervised performance and adaptability to different types of networks. Furthermore, it takes the advantage of day-forward-chaining analysis to ensure the detection of highly important alerts in real time. The number of false positive cases is reduced by employing an autoencoder. The proposed method achieved a recall score of 95.89% and a false positive rate of 5.86% on a dataset comprising more than half a million alerts collected in a real-world enterprise environment over ten months. This study highlights the importance of addressing the alert fatigue problem and validates the effectiveness of unsupervised learning in filtering out less important threat alerts.

An efficient approach for Paroxysmal Atrial Fibrillation events prediction using Extreme Learning Machine

Paroxysmal Atrial Fibrillation (PAF) is a special class of Atrial Fibrillation. Predicting PAF events from electrocardiogram (ECG) signal streams plays a vital role in generating real-time alerts for cardiac disorders. These alerts are extremely important to cardiologists in taking precautions to prevent their patients from having a stroke. In this study, an effective predictive approach to PAF events using the Extreme Learning Machine classification technique is proposed. Besides, we propose a feature extraction method that integrates new ECG signal features to its time-domain ones. The new features are based on the construction of sparse vectors for peaks in ECG signals that provide high overlap between similar ECGs. The proposed prediction approach with the new ECG features representation were evaluated on a real PAF dataset using the five-fold cross-validation method. Experiments show promising results for predicting PAF in terms of accuracy and execution time compared to other existing studies. The proposed approach achieved classification accuracy of 97% for non-streaming ECG signals mode and 94.4% for streaming mode.

Discussion

Discussion

Implementation of a Clinical Decision Support Tool to Improve Antibiotic IV-to-Oral Conversion Rates at a Community Academic Hospital

Antibiotic IV-to-oral (IV-PO) conversion is a key initiative of antimicrobial stewardship programs. Guidelines and education are commonly described interventions to promote IV-PO conversion; however, technological interventions may be more effective in changing practice. To determine the impact of a clinical decision support (CDS) tool on the adoption and sustainability of an antibiotic IV-PO conversion program at a community academic hospital. A quasi-experimental study consisting of 3 phases was conducted. During phase 1, the pre-intervention antibiotic IV-PO conversion rate was determined. During phase 2, the IV-PO conversion policy was updated, education was provided to pharmacists and physicians, and a post-intervention evaluation was conducted. During phase 3, a CDS tool was developed to generate real-time electronic alerts prompting pharmacists to assess antibiotic therapy, and post-intervention audits were performed 1 month, 3 months, and 15 months after implementation of the tool. Pantoprazole IV-PO conversion was assessed during each phase as a non-equivalent dependent variable. The primary outcome was the proportion of patients eligible for IV-PO conversion who were switched to oral therapy. Of 332 patients receiving targeted IV antibiotic therapy during the overall study period, 122 (37%) met the criteria for IV-PO conversion. The phase 2 IV-PO conversion rate of 35% (9/26) was comparable to the pre-intervention rate of 29% (10/35) (p = 0.61). Implementation of the CDS tool significantly increased the conversion rate to 78% (14/18), an increase that was sustained at 3 months (71% [17/24]) and 15 months (74% [14/19]) after implementation (p < 0.05 for all comparisons with phases 1 and 2). Pantoprazole conversion rates were similar across all phases. Implementation of the CDS tool was effective in improving and sustaining antibiotic IV-PO conversion rates and enhancing policy compliance beyond the effects of policy revision and education. Refinement of both the policy and the tool is warranted to maximize adoption of the IV-PO conversion program.

A real-time alert correlation method based on code-books for intrusion detection systems

Alert Correlation is the process of analyzing alerts to reduce their number, eliminate false positives, detect the scenarios behind them and generate a higher perspective of the incidents. Making this process online will upgrade the classic role of alert correlation from being a post-process step to a key part of intrusion detection systems. In this article, we propose a novel two-phase model called a Real-time Alert Correlation method based on Code-books (RACC) for intrusion detection systems. First, in the offline phase, RACC pre-processes a knowledge base to propose some matrices as the main data structure of the method that we call them code-books. Instead of keeping alerts in the memory, those matrices just hold keys to the corresponding meta-alerts. An index that is based upon red-black trees is used to access matrix elements. Generating the matrices and mentioned index are independent from the alerts, so utilizing them can facilitate the alert correlation process in an online manner in phase two of the proposed model. The experiments show that compared to similar methods, RACC can significantly reduce the alert correlation time and can enable real-time alert correlation.

Real-Time Alerting for Medical Science and Healthcare

Particular in medical communication is can say as an underappreciated skill. By using ever-growing number of new infrastructure, apps are devices our reality has turned out to be progressively interconnected, numerous connections among specialists and patients are still amazingly dated. A great deal of delicate data is passed along face to face, however most different collaborations are done by means of telephone. Without the need to revive or physically demand data the Real-time applications receive and send data instantaneously. It could be devices that screens vitals and immediately streams those readings to a database or different devices or for connecting the patient with doctors it could be a simple application of chat.

Impact of Beta-lactam Allergy on Treatment of Outpatient Infections

PurposeThe most commonly reported medication allergies in the United States involve beta-lactam antibiotics, creating an important consideration for prescribers when choosing optimal treatment of infections. Currently, few data exist on outpatient prescribing patterns in response to patients with a beta-lactam allergy. This study sought to evaluate the appropriateness of outpatient antibiotic therapy in patients with documented beta-lactam allergies within a Veterans Affairs health care system to evaluate areas of improvement in prescribing practices. MethodsPatients receiving outpatient oral antibiotics were prospectively identified through real-time electronic alerts from June 2017 through February 2018. Prescriptions were then reviewed retrospectively to identify appropriateness of antibiotic, drug choice, dose, and duration based on current guideline recommendations. Data were compared between patients with a listed beta-lactam allergy and patients without a beta-lactam allergy to determine the impact on prescribing patterns and outcomes. Baseline characteristics were compared by using descriptive statistics. Significant risk factors for inappropriate prescribing were identified through a multivariable analysis. FindingsThe cohort included 1844 antibiotic prescriptions (documented beta-lactam allergy, 221; no beta-lactam allergy, 1623). Appropriate drug, dose, and duration for antibiotics prescribed in patients reporting a beta-lactam allergy versus nonallergic patients were 44.3% versus 53.0% (P = 0.02), 91.4% versus 86.2% (P = 0.03), and 75.1% versus 76.2% (P = 0.83), respectively. Patients with a reported beta-lactam allergy were 31% less likely to receive the correct drug for indication empirically (95% CI, 0.52–0.92) in the multivariable regression model when adjusted for fluoroquinolone use. In addition, patients reporting a beta-lactam allergy were 2.2 times (95% CI, 1.6–3.0) more likely to receive a fluoroquinolone antibiotic. Antibiotics were considered overall inappropriate based on at least one aspect of therapy in 79.6% of patients reporting a beta-lactam allergy and in 71% of nonallergic patients. ImplicationsAntibiotic therapy in patients with a documented beta-lactam allergy was less likely to be appropriate overall, suggesting an area of improvement for prescribing habits. Future interventions should focus on prescriber education regarding first-line and alternative treatments for patients with beta-lactam allergies to ensure that optimal treatment is being provided.

1025. Inappropriate Aztreonam Usage – Antimicrobial Stewardship Strikes Back

BackgroundSeveral studies have demonstrated that patients with reportedly β-lactam allergies (BLA) receive less efficacious and more toxic alternative antibiotics. A previous study at our institution utilizing aztreonam as a surrogate marker for BLA demonstrated nearly 50% of patients receiving aztreonam had previously tolerated an alternative β-lactam (BL). In response to those results, our Antimicrobial Stewardship Program (ASP) provided dedicated hospitalist, medical resident and pharmacist education on appropriate utilization of aztreonam and BLA. Additionally, members of the ASP team began receiving real-time clinical surveillance alerts for all aztreonam orders.MethodsA retrospective chart review of inpatients >18 years old who received at least one dose of aztreonam between July 1, 2018 – December 31, 2018. Patients were excluded if they did not have a documented BLA or if they received aztreonam as de-escalation therapy. Cost of aztreonam therapy was compared with the cost of alternative BL agents based on prior and subsequently tolerated classes of BLs. Comparator agents included: piperacillin/tazobactam (penicillin), cefepime (cephalosporin) and meropenem (carbapenem). Comparisons of total number of aztreonam patients and doses, cost of aztreonam, and cost of alternative therapy were compared with the index population from 2017ResultsSimilar to our prior study, 43.7% (48.5% in 2017) had prior BL tolerance with an additional 31.3% (19.4% in 2017) demonstrated subsequent BL tolerance following aztreonam administration. Following the ASP interventions, orders, doses and cost of aztreonam was reduced. Forty-eight patients during the 6-month period received aztreonam, a 26.7% reduction. There was a 38.5% reduction in the number of aztreonam doses (P = 0.001), which yielded a cost savings of $14,067.67 (extrapolated to 1 year). Median aztreonam cost in 2017 $382.40 vs. $191.20 in 2018 (P = 0.004). In 2018, 41.7% of patient’s allergy profiles were appropriately updated compared with 3.3% in 2017.ConclusionOur study demonstrates that ASP interventions including increased education, allergy documentation and clinical surveillance alerts targeted at reducing aztreonam utilization can reduce pharmaceutical expenditures. Disclosures All authors: No reported disclosures.

1056. Evaluation of Clinical Outcomes Following Implementation of Real-Time Stewardship Team Interventions for Multi-Drug-Resistant Organisms

BackgroundInfections due to multidrug-resistant organisms (MDRO) are associated with an increased risk of mortality. Accurate assessment of culture results and prompt initiation of effective antibiotic therapy have the potential to improve patient outcomes. The purpose of this study was to assess the time to effective therapy and associated clinical outcomes following the implementation of real-time stewardship alerts for infections due to MDRO.MethodsThis pre–post quasi-experimental study identified patients admitted to Michigan Medicine with a positive culture for one of 14 pre-defined MDRO. An alerting system was implemented within the institution’s electronic health record (EHR) in October 2018, which notifies the antimicrobial stewardship (ASP) pharmacist upon detection of an MDRO, regardless of source. The ASP pager is monitored 24/7 by a clinical pharmacy specialist who reviews the patient’s chart and recommends antibiotic modifications if necessary. In the pre-intervention period, no structured alerting or assessment was performed. Inclusion: ≥18 years old and trigger of an alert. Exclusions: pediatric service, cystic fibrosis, discharged or deceased prior to alert sensitivities, outside hospital (OSH) transfer growing identical organism upon admission, culture contamination or colonization. The primary outcome of time to effective therapy is determined from time of alert for MDRO to the order time of the effective antimicrobial agent. Secondary outcome measures include: length of stay, 30-day all-cause mortality, and 30-day readmission.Results152 alerts were included in the study (post, n = 75 and pre, n = 77). Outcomes were assessed in patients not on effective therapy at the time of alert (68.0% vs. 70.1%). Time to effective therapy was significantly improved in the intervention group (2.08hours vs. 3.72hours, P = 0.0010). Length of stay (18 days vs. 15.5 days, P = 0.1662) and 30-day all-cause mortality (17.6% vs. 18.5%, P = 0.9088) were not different between groups. However, 30-day readmission rates were significantly reduced with the intervention (21.4% vs. 43.2%, P = 0.0316).ConclusionReal-time stewardship team interventions for infections due to MDRO improve time to effective therapy and are associated with a decrease in hospital readmissions.Disclosures All authors: No reported disclosures.

Outcomes of Mobile Reporting to Enhance Disease Surveillance in 632 Districts of 29 States in Nigeria

Background Optimal disease surveillance provides opportunities for identifying outbreaks early and intervening to reduce their spread and impact. The availability of mobile phone technologies have improved communication across the world and now serves as an effective system for frontline healthcare workers to gather and disseminate data that can inform actions at country and program levels. In Nigeria, with an estimated population of over 200 million people spread across a wide land mass area of 923,763 km2, surveillance for diseases will require innovative strategies with penetrative abilities to the lowest levels of healthcare to achieve desired outcomes. Objective The objective was to describe the outcomes of reporting using mobile technology to enhance surveillance. Methods An SMS-based reporting tool was developed which conforms to the nationally approved weekly reporting format for IDSR 002 diseases. A total of nine diseases and public health events are reported weekly by 774 Disease Surveillance and Notification Officers (DSNOs) at the Districts. On reporting days (Tuesdays), the DSNOs receive a reminder via SMS to send in their reports, which is shortly followed by the reporting template. The DSNOs enter the weekly data for their respective data and send via SMS. The data is received nationally at the Nigeria Centre for Disease Control (NCDC) where staff provide oversight function on reports coming in by states. The team monitor reporting through visualization monitoring boards and respond to wrongly sent reports by calling up the DSNO. Collated reports by states are shared with the State Supervisory Teams on nationally approved Excel sheets which bypasses the cumbersome nature of direct data entry on the Excel sheets. Reports are validated by the state before the final version of the Excel sheets are shared with the NCDC. Completeness, timeliness of data, and alert threshold of reported cases were used to monitor the reporting process for 52 weeks in 2018. Results A total of 32,864 reports were expected in 2018 with 1 report sent weekly from each of the 632 districts of 29 states. The benchmark for timely reports is 80% and completeness of reports is 90% as indicated in the Integrated Disease Surveillance and Response (IDSR) Technical Guidelines. Average completeness was 90% with 97% noted in February and 57% in November. An average of 93% of reports were sent in a timely manner with timeliness of 89% observed in in June and July and 96% observed in January, February, and December. All 29 states reported in a timely manner and 2 states sent in complete reports consistently for 52 weeks. This system provided real-time alerts for priority diseases that were above established thresholds highlighting the start of various outbreaks reported in the year. Conclusions During the year, there was a marked improvement in disease surveillance and notification despite periods of low completeness of reports observed. Instituting into mobile systems, processing for feedback, and improvement will further support the system among healthcare workers. Leveraging on the ease of how mobile phones have become part of everyday human life, disease surveillance methods can be enhanced and used on mobile phones

Enabling real-time multi-messenger astrophysics discoveries with deep learning

Multi-messenger astrophysics is a fast-growing, interdisciplinary field that combines data, which vary in volume and speed of data processing, from many different instruments that probe the Universe using different cosmic messengers: electromagnetic waves, cosmic rays, gravitational waves and neutrinos. In this Expert Recommendation, we review the key challenges of real-time observations of gravitational wave sources and their electromagnetic and astroparticle counterparts, and make a number of recommendations to maximize their potential for scientific discovery. These recommendations refer to the design of scalable and computationally efficient machine learning algorithms; the cyber-infrastructure to numerically simulate astrophysical sources, and to process and interpret multi-messenger astrophysics data; the management of gravitational wave detections to trigger real-time alerts for electromagnetic and astroparticle follow-ups; a vision to harness future developments of machine learning and cyber-infrastructure resources to cope with the big-data requirements; and the need to build a community of experts to realize the goals of multi-messenger astrophysics.

REAL-TIME WILDFIRE DETECTION FROM SPACE – A TRADE-OFF BETWEEN SENSOR QUALITY, PHYSICAL LIMITATIONS AND PAYLOAD SIZE

Abstract. Wildfires cause large scale devastation to human settlements and forests every year and their frequency and severity is on the rise. A major reason for this devastation is the significant delay in their detection due to their remote locations in forests. To mitigate this, a constellation of nanosatellites in Low Earth Orbit (LEO) equipped with multi-spectral visible to Infrared (IR) cameras is proposed leveraging the modular and affordable architecture of CubeSats. Coupled with the payload design, meticulously planned constellation and a ground support system, all surface points on the planet will be revisited at least once in an hour. Capturing a surface location with a high resolution in MidWavelength Infrared (MWIR) and LongWavelength Infrared (LWIR) allows a precise estimation of thermal output of the surface. Simulations indicate that a fire of about four hundred square meters can be easily detected from this satellite payload. Through onboard data processing, wildfires can be already detected in space, minimizing bandwidth requirements for real-time alerts. This enables an early wildfire warning within 30 min by utilizing existing satellite internet networks. Additionally, compressed raw images will be transmitted on fixed ground station passes to provide a global thermal data updated every 90 min. The near real-time multi-spectral data provides opportunity for several other applications like weather forecasting besides wildfire detection.

95. IMPROVING RESIDENT NOTE COMPLETION IN A GENERAL PEDIATRICS CLINIC

Background Timely note completion is an important part of patient care. Our hospital has standard expectations for note completion; however, pediatric residents in our program were often delinquent in their documentation, resulting in incomplete patient data in the electronic health record during return visits, elevated resident stress, and threat of suspension of clinical duties from the professional board. The vast majority of these delinquencies were from our general pediatric clinic, where residents see patients for both acute and well child care. Aim Statement Decrease number of delinquent resident notes by 80% over a 9 month period. Interventions We used problem solving methodology and serial tests of change to improve note timeliness. The primary outcome measure was the number of overall delinquent charts according to a weekly graduate medical education deficiency notification system. Tests of change included: 1-Program Director emails and pages to residents with delinquent notes (defined by the institution as >14 days for ambulatory charts) 2-General Pediatric attending consensus on note completion timeliness (same day for acute care visits, next day for well child visits) 3-Intermittent auditing and real time alerts by administrative staff for residents who failed to comply with the same day/next day clinic note completion timeline. Measures Number of delinquent charts by pediatric residents according to the weekly graduate medical education deficiency notification system. Results Timely note completion improved significantly over the 13 months of the project. Program Director emails/pages to residents with deficient charts resulted in a reduction of a median 26 deficient charts/week to 12 deficient charts/week. Intermittent real time alerts to residents who failed to close charts within 24 hours of an acute care visit or 48 hours of a well child visit further reduced the median from 12 charts per week to 2 charts per week. Conclusions and Next Steps Standard expectations for resident note completion in a general pediatric clinic coupled with real time feedback improved resident adherence to institutional expectations around timely note completion. While program director contact with residents who have delinquent charts demonstrated some improvement, this intervention alone was insufficient.

Implementation of a Digitally Enabled Care Pathway (Part 2): Qualitative Analysis of Experiences of Health Care Professionals.

BackgroundOne reason for the introduction of digital technologies into health care has been to try to improve safety and patient outcomes by providing real-time access to patient data and enhancing communication among health care professionals. However, the adoption of such technologies into clinical pathways has been less examined, and the impacts on users and the broader health system are poorly understood. We sought to address this by studying the impacts of introducing a digitally enabled care pathway for patients with acute kidney injury (AKI) at a tertiary referral hospital in the United Kingdom. A dedicated clinical response team—comprising existing nephrology and patient-at-risk and resuscitation teams—received AKI alerts in real time via Streams, a mobile app. Here, we present a qualitative evaluation of the experiences of users and other health care professionals whose work was affected by the implementation of the care pathway.ObjectiveThe aim of this study was to qualitatively evaluate the impact of mobile results viewing and automated alerting as part of a digitally enabled care pathway on the working practices of users and their interprofessional relationships.MethodsA total of 19 semistructured interviews were conducted with members of the AKI response team and clinicians with whom they interacted across the hospital. Interviews were analyzed using inductive and deductive thematic analysis.ResultsThe digitally enabled care pathway improved access to patient information and expedited early specialist care. Opportunities were identified for more constructive planning of end-of-life care due to the earlier detection and alerting of deterioration. However, the shift toward early detection also highlighted resource constraints and some clinical uncertainty about the value of intervening at this stage. The real-time availability of information altered communication flows within and between clinical teams and across professional groups.ConclusionsDigital technologies allow early detection of adverse events and of patients at risk of deterioration, with the potential to improve outcomes. They may also increase the efficiency of health care professionals’ working practices. However, when planning and implementing digital information innovations in health care, the following factors should also be considered: the provision of clinical training to effectively manage early detection, resources to cope with additional workload, support to manage perceived information overload, and the optimization of algorithms to minimize unnecessary alerts.

On building a smarter ecosystem using the internet of intelligent things: progress and future challenges

With a growing interest in the Internet of Things (IoT), the businesses are undergoing a revolution in the way they monitor and control. In the recent past, many applications were developed using the IoT system architectures in various business verticals such as industrial, healthcare, farming, transportation, etc. However, with the development of low-complex artificial intelligence frameworks which are capable of operating on the edge devices, the IoT architectures have taken a major leap leading to the Internet of Intelligent Things (IoIT). In this paper, we discuss our focused research and applications of IoIT across the following verticals: (1) healthcare, (2) smart buildings, (3) farming, along with the recent state of the art methodologies and future challenges. Under the healthcare, we laid our main focus on the development of AI enabled computer-aided diagnosis framework, which acquires the scanning information from a wireless ultrasound transducer and automatically identifies the abnormalities present. Also, we developed a low-complex brain-controlled IoT environments framework which automatically classifies the motor imagery task performed by the user using 22 channel electroencephalography. Using IoIT, we developed a novel non-invasive technology capable of monitoring various electrical parameters without any need for cutting the wires. This developed non-invasive power monitor is capable of generating real-time alerts in the case of system malfunctions and will be a key enabler for smart buildings. Also, we developed mathematical, simulation, and experimental models for analyzing the performance of channel access mechanisms of dense traffic IoT networks.

Real-time monitoring of drug-laboratory test interactions with an automated decision support application

Background-aim: The lack of knowledge of the presence of Drug-Laboratory Test Interactions (DLTIs) can cause misinterpretation of laboratory test results and delayed or erroneous diagnosis with extra healthcare costs and even harm to patients. There are over 50.000 physiological and/or analytical drug-test interactions described. In this pilot study, an automated decision support application was used to detect drug laboratory test interactions in real-time. Methods: In this multicentre study, 34 clinical rules about DLTI were programmed and validated in an automated decision support application (Gaston, Medecs B.V.). The DLTIs were described in a validated database from the Dutch Society for Clinical Chemistry. The application is able to generate a DLTI-based advisory text based on predefined aberrant laboratory test results and medication data from individual patients and present this alert text to the laboratory specialist in the laboratory information system. The software application was successfully connected and installed in one hospital laboratory in 2018 with two other hospitals to follow in 2019. Generated real-time DLTI alerts were collected and monitored during 4 weeks. Results: A mean of 45 DLTI alerts were generated per day. Twenty-one out of 34 clinical rules were generated at least once in this period. The most frequently reported interactions were magnesium - proton pump inhibitors (14%), creatine kinase – statins (13%) and potassium - ACE-inhibitors (13%). Most DLTI alerts were from the internal medicine department (43%), cardiology department (22%) and the emergency department (10%). Conclusions: In this study, an automated decision support application was implemented to facilitate signalling the presence of drug laboratory test interactions. A mean of 45 DLTI alerts per day were generated in this study. The clinical relevance of the alerts for laboratory specialists and physicians will be examined.

Heat Illness Related Meteorology over Chiangmai Using Automatic Weather Station Observed Data

This research is a part of study of heat illness vulnerability. Understanding heat characteristic, especially in tropical area, would decrease loss from heat deceases and also support tourism in tropical countries. The aim of this research is to apply the meteorological sensor dataset in Chiangmai (a famous city in northern Thailand), which is under the control of Thai Meteorological Department, from 2015-2017 to investigate heat index characteristic. Two elements, temperature and relative humidity, were used to calculate heat index following Steadman’s equation. Analyzed heat index would be arranged by its intensity and then applied on heat illness warning. The study demonstrated that heat index warning from Automatic Weather Station data analysis could get along with the maximum temperature historical statistics data which observed by weather stations. Local people and visitors in Chiangmai mostly suffer from heat in between March and June. The greatest vulnerability to heat illness in Chiangmai was in April and May. This extreme-heat period is consistent with the report from Department of Decease Control Thailand, an amount of heat illness patients is very high in April and May. Moreover, the results show that even if the air temperature is getting low in after summer season but heat index is still high through the year. So, people still need to be aware of heat deceases and always concern about environmental heat when doing outdoor activities. In the future, AWS data from every station over Thailand would be used to develop a real-time Heat Illness Alert System.