scholarly journals Patient-Specific Sedation Management via Deep Reinforcement Learning

2021 ◽  
Vol 3 ◽  
Author(s):  
Niloufar Eghbali ◽  
Tuka Alhanai ◽  
Mohammad M. Ghassemi
Keyword(s):  
Intensive Care Unit ◽  
Intensive Care ◽  
Reinforcement Learning ◽  
Primary Objective ◽  
Target Range ◽  
Patient Specific ◽  
Performance Improvements ◽  
Unseen Data ◽  
Experience Replay ◽  
Sedative Hypnotics

Introduction: Developing reliable medication dosing guidelines is challenging because individual dose–response relationships are mitigated by both static (e. g., demographic) and dynamic factors (e.g., kidney function). In recent years, several data-driven medication dosing models have been proposed for sedatives, but these approaches have been limited in their ability to assess interindividual differences and compute individualized doses.Objective: The primary objective of this study is to develop an individualized framework for sedative–hypnotics dosing.Method: Using publicly available data (1,757 patients) from the MIMIC IV intensive care unit database, we developed a sedation management agent using deep reinforcement learning. More specifically, we modeled the sedative dosing problem as a Markov Decision Process and developed an RL agent based on a deep deterministic policy gradient approach with a prioritized experience replay buffer to find the optimal policy. We assessed our method's ability to jointly learn an optimal personalized policy for propofol and fentanyl, which are among commonly prescribed sedative–hypnotics for intensive care unit sedation. We compared our model's medication performance against the recorded behavior of clinicians on unseen data.Results: Experimental results demonstrate that our proposed model would assist clinicians in making the right decision based on patients' evolving clinical phenotype. The RL agent was 8% better at managing sedation and 26% better at managing mean arterial compared to the clinicians' policy; a two-sample t-test validated that these performance improvements were statistically significant (p < 0.05).Conclusion: The results validate that our model had better performance in maintaining control variables within their target range, thereby jointly maintaining patients' health conditions and managing their sedation.

Frequency and Severity of Chlorothiazide-Induced Hyponatremia in the Neonatal Intensive Care Unit

2021 ◽  
Author(s):  
Maura Harkin ◽  
Peter N. Johnson ◽  
Stephen B. Neely ◽  
Lauren White ◽  
Jamie L. Miller
Keyword(s):  
Intensive Care Unit ◽  
Intensive Care ◽  
Neonatal Intensive Care Unit ◽  
Serum Sodium ◽  
Neonatal Intensive Care ◽  
Primary Objective ◽  
Severe Hyponatremia ◽  
Days Of Therapy ◽  
Neonates And Infants ◽  
Sodium Supplementation

Objective Although thiazide diuretics are commonly used in the neonatal intensive care unit (NICU), the risk of thiazide-induced hyponatremia in infants has not been well documented. The primary objective of this study was to determine the frequency and severity of hyponatremia in neonates and infants receiving enteral chlorothiazide. Secondary objectives included identifying: (1) percent change in serum sodium from before chlorothiazide initiation to nadir, (2) time to reach nadir serum sodium concentration, and (3) percentage of patients on chlorothiazide receiving sodium supplementation. Study Design This was a retrospective cohort study of NICU patients admitted between July 1, 2014 and July 31, 2019 who received ≥1 dose of enteral chlorothiazide. Mild, moderate, and severe hyponatremia were defined as serum sodium of 130 to 134 mEq/L, 120 to 129 mEq/L, and less than 120 mEq/L, respectively. Data including serum electrolytes, chlorothiazide dosing, and sodium supplementation were collected for the first 2 weeks of therapy. Descriptive and inferential statistics were performed in SAS software, Version 9.4. Results One hundred and seven patients, receiving 127 chlorothiazide courses, were included. The median gestational age at birth and postmenstrual age at initiation were 26.0 and 35.9 weeks, respectively. The overall frequency of hyponatremia was 35.4% (45/127 courses). Mild, moderate, and severe hyponatremia were reported in 27 (21.3%), 16 (12.6%), and 2 (1.6%) courses. The median percent decrease in serum sodium from baseline to nadir was 2.9%, and the median time to nadir sodium was 5 days. Enteral sodium supplements were administered in 52 (40.9%) courses. Sixteen courses (12.6%) were discontinued within the first 14 days of therapy due to hyponatremia. Conclusion Hyponatremia occurred in over 35% of courses of enteral chlorothiazide in neonates and infants. Given the high frequency of hyponatremia, serum sodium should be monitored closely in infants receiving chlorothiazide. Providers should consider early initiation of sodium supplements if warranted. Key Points

scholarly journals The effect of rectal progesterone on latency period as well as maternal and prenatal outcome between 24 to 33 weeks

2015 ◽  
Vol 2 (4) ◽  
pp. 97
Author(s):  
Fadwah Tahir ◽  
Mohammed Badawi ◽  
Abdulelah Nuqali ◽  
Yasir Katib ◽  
Irfanallah Muhammad Siddiqui ◽  
...  
Keyword(s):  
Intensive Care Unit ◽  
Intensive Care ◽  
Neonatal Intensive Care ◽  
Randomized Clinical Trials ◽  
Post Partum ◽  
Controlled Trial ◽  
Latency Period ◽  
Neonatal Morbidity ◽  
Primary Objective ◽  
Intrauterine Fetal Death

Preterm Premature Rupture Of Membranes (PPROM) is directly linked to prematurity associated with severe neonatal morbidity and mortality. Randomized clinical trials have shown that weekly injections of 17-alpha-hydroxyprogesterone (17P) or daily vaginal progesterone application decreases the number of preterm deliveries, particularly for women with a history of preterm delivery or those with a shortened cervix. However, no studies have yet been conducted to prove or disprove the effect of rectal progesterone on latency period. To address this issue,<strong> </strong>we will conduct a multicenter randomized triple-blind controlled trial of 216 participants (108 in each group) from January 1, 2016 to August 31, 2016. Inclusion criteria, exclusion criteria, data collection procedure, data analysis, and assessment of safety procedures are explained in the study protocol.<strong> </strong>The primary objective will be to determine the effect of rectal progesterone on the latency period in PPROM. The secondary objective will be to study the effect of rectal progesterone on maternal outcomes of hospitalization, intensive care unit admission, chorioamnionitis, post-partum hemorrhage, post-partum pyrexia, endometritis, and maternal death. In addition, we will evaluate prenatal birth weight, Apgar score, neonatal morbidity, duration of neonatal intensive care unit stay, intrauterine fetal death, and neonatal death associated with PPROM.

Prescribing Practices of Valproic Acid for Agitation and Delirium in the Intensive Care Unit

2020 ◽  
pp. 106002802094717
Author(s):  
Nicholas J. Quinn ◽  
Benjamin Hohlfelder ◽  
Matthew R. Wanek ◽  
Abhijit Duggal ◽  
Heather Torbic
Keyword(s):  
Intensive Care Unit ◽  
Valproic Acid ◽  
Intensive Care ◽  
Primary Objective ◽  
Assessment Tools ◽  
Prescribing Practices ◽  
Dose Frequency ◽  
Institutional Review ◽  
Alternative Treatment Option ◽  
Icu Delirium

Background: Analgesics, sedatives, and antipsychotics are commonly prescribed for agitation and delirium in the intensive care unit (ICU), but their use is limited by adverse effects and lack of efficacy. Valproic acid is an alternative treatment option. Objective: The primary objective of this study was to describe valproic acid prescribing in our institution’s ICUs when used for agitation or delirium. Measures of effectiveness and safety were also assessed. Methods: This was a single-center, retrospective, institutional review board–approved cohort study of adult inpatients admitted to the ICU between January 2018 and August 2018. Patients who received valproic acid for the treatment of agitation or delirium for ≥24 hours were included. Prescribing practices were evaluated for dose, frequency, and route of administration. Effectiveness was assessed via agitation and delirium assessment tools and quantity of adjunctive agents used. Results: A total of 80 patients were included, with 35 receiving valproic acid alone and 45 in conjunction with antipsychotics. The most common valproic acid regimen was 250 mg orally 3 times daily. Delirium resolution occurred in 55% of patients: 24 in the valproic acid monotherapy group and 20 in the valproic acid plus antipsychotic group (69% vs 44%; P = 0.03). The incidence of delirium decreased from valproic acid day 0 to day 3 (93% vs 68%; P < 0.01), with no change in agitation (64% vs 63%; P = 0.28). Conclusion and Relevance: Valproic acid is frequently prescribed in agitated, delirious patients at our institution and may have a role in the management of ICU delirium.

scholarly journals Glucose Control in the Intensive Care Unit by Use of Continuous Glucose Monitoring: What Level of Measurement Error Is Acceptable?

2014 ◽  
Vol 60 (12) ◽  
pp. 1500-1509 ◽  
Author(s):  
Malgorzata E Wilinska ◽  
Roman Hovorka
Keyword(s):  
Intensive Care Unit ◽  
Intensive Care ◽  
Measurement Error ◽  
Continuous Glucose Monitoring ◽  
Glucose Control ◽  
Glucose Monitoring ◽  
Glucose Variability ◽  
Glucose Measurement ◽  
Target Range ◽  
Mean Glucose

Abstract BACKGROUND Accuracy and frequency of glucose measurement is essential to achieve safe and efficacious glucose control in the intensive care unit. Emerging continuous glucose monitors provide frequent measurements, trending information, and alarms. The objective of this study was to establish the level of accuracy of continuous glucose monitoring (CGM) associated with safe and efficacious glucose control in the intensive care unit. METHODS We evaluated 3 established glucose control protocols [Yale, University of Washington, and Normoglycemia in Intensive Care Evaluation and Surviving Using Glucose Algorithm Regulation (NICE-SUGAR)] by use of computer simulations. Insulin delivery was informed by intermittent blood glucose (BG) measurements or CGM levels with an increasing level of measurement error. Measures of glucose control included mean glucose, glucose variability, proportion of time glucose was in target range, and hypoglycemia episodes. RESULTS Apart from the Washington protocol, CGM with mean absolute relative deviation (MARD) ≤15% resulted in similar mean glucose as with the use of intermittent BG measurements. Glucose variability was also similar between CGM and BG-informed protocols. Frequency and duration of hypoglycemia were not worse by use of CGM with MARD ≤10%. Measures of glucose control varied more between protocols than at different levels of the CGM error. CONCLUSIONS The efficacy of CGM-informed and BG-informed commonly used glucose protocols is similar, but the risk of hypoglycemia may be reduced by use of CGM with MARD ≤10%. Protocol choice has greater influence on glucose control measures than the glucose measurement method.

scholarly journals Staphylococcus aureusNasal Colonization and Subsequent Infection in Intensive Care Unit Patients: Does Methicillin Resistance Matter?

2010 ◽  
Vol 31 (6) ◽  
pp. 584-591 ◽  
Author(s):  
Hitoshi Honda ◽  
Melissa J. Krauss ◽  
Craig M. Coopersmith ◽  
Marin H. Kollef ◽  
Amy M. Richmond ◽  
...  
Keyword(s):  
Risk Factors ◽  
Intensive Care Unit ◽  
Intensive Care ◽  
Confidence Interval ◽  
Methicillin Resistance ◽  
Hazard Ratio ◽  
Adjusted Hazard Ratio ◽  
Patient Specific ◽  
Icu Patients ◽  
Icu Admission

Background.Staphylococcus aureusis an important cause of infection in intensive care unit (ICU) patients. Colonization with methicillin-resistantS. aureus(MRSA) is a risk factor for subsequentS. aureusinfection. However, MRSA-colonized patients may have more comorbidities than methicillin-susceptibleS. aureus(MSSA)-colonized or noncolonized patients and therefore may be more susceptible to infection on that basis.Objective.To determine whether MRSA-colonized patients who are admitted to medical and surgical ICUs are more likely to develop anyS. aureusinfection in the ICU, compared with patients colonized with MSSA or not colonized withS. aureus,independent of predisposing patient risk factors.Design.Prospective cohort study.Setting.A 24-bed surgical ICU and a 19-bed medical ICU of a 1,252-bed, academic hospital.Patients.A total of 9,523 patients for whom nasal swab samples were cultured forS. aureusat ICU admission during the period from December 2002 through August 2007.Methods.Patients in the ICU for more than 48 hours were examined for an ICU-acquired S.aureusinfection, defined as development ofS. aureusinfection more than 48 hours after ICU admission.Results.S. aureuscolonization was present at admission for 1,433 (27.8%) of 5,161 patients (674 [47.0%] with MRSA and 759 [53.0%] with MSSA). An ICU-acquiredS. aureusinfection developed in 113 (2.19%) patients, of whom 75 (66.4%) had an infection due to MRSA. Risk factors associated with an ICU-acquiredS. aureusinfection included MRSA colonization at admission (adjusted hazard ratio, 4.70 [95% confidence interval, 3.07-7.21]) and MSSA colonization at admission (adjusted hazard ratio, 2.47 [95% confidence interval, 1.52-4.01]).Conclusion.ICU patients colonized with S.aureuswere at greater risk of developing aS. aureusinfection in the ICU. Even after adjusting for patient-specific risk factors, MRSA-colonized patients were more likely to developS. aureusinfection, compared with MSSA-colonized or noncolonized patients.

scholarly journals Predictors of mortality and validation of burn mortality prognostic scores in a Malaysian burns intensive care unit

2019 ◽  
Vol 19 (1) ◽  
Author(s):  
Henry Tan Chor Lip ◽  
Mohamad Azim Md. Idris ◽  
Farrah-Hani Imran ◽  
Tuan Nur’ Azmah ◽  
Tan Jih Huei ◽  
...  
Keyword(s):  
Risk Factors ◽  
Intensive Care Unit ◽  
Mechanical Ventilation ◽  
Intensive Care ◽  
Burn Injury ◽  
Total Body Surface Area ◽  
Primary Objective ◽  
Prognostic Scores ◽  
Secondary Objective ◽  
Total Body

Abstract Background Majority burn mortality prognostic scores were developed and validated in western populations. The primary objective of this study was to evaluate and identify possible risk factors which may be used to predict burns mortality in a local Malaysian burns intensive care unit. The secondary objective was to validate the five well known burn prognostic scores (Baux score, Abbreviated Burn Severity Index (ABSI) score, Ryan score, Belgium Outcome Burn Injury (BOBI) score and revised Baux score) to predict burn mortality prediction. Methods Patients that were treated at the Hospital Sultan Ismail’s Burns Intensive Care (BICU) unit for acute burn injuries between 1 January 2010 to 31 December 2017 were included. Risk factors to predict in-patient burn mortality were gender, age, mechanism of injury, total body surface area burn (TBSA), inhalational injury, mechanical ventilation, presence of tracheotomy, time from of burn injury to BICU admission and initial centre of first emergency treatment was administered. These variables were analysed using univariate and multivariate analysis for the outcomes of death. All patients were scored retrospectively using the five-burn mortality prognostic scores. Predictive ability for burn mortality was analysed using the area under receiver operating curve (AUROC). Results A total of 525 patients (372 males and 153 females) with mean age of 34.5 ± 14.6 years were included. There were 463 survivors and 62 deaths (11.8% mortality rate). The outcome of the primary objective showed that amongst the burn mortality risk factors that remained after multivariate analysis were older age (p = 0.004), wider TBSA burn (p < 0.001) and presence of mechanical ventilation (p < 0.001). Outcome of secondary objective showed good AUROC value for the prediction of burn death for all five burn prediction scores (Baux score; AUROC:0.9, ABSI score; AUROC:0.92, Ryan score; AUROC:0.87, BOBI score; AUROC:0.91 and revised Baux score; AUROC:0.94). The revised Baux score had the best AUROC value of 0.94 to predict burns mortality. Conclusion Current study evaluated and identified older age, total body surface area burns, and mechanical ventilation as significant predictors of burn mortality. In addition, the revised Baux score was the most accurate burn mortality risk score to predict mortality in a Malaysian burn’s population.

scholarly journals A study of clinical characteristics and outcome of obstetric patients in intensive care and high dependency unit of a tertiary centre of Jharkhand, India

2019 ◽  
Vol 9 (1) ◽  
pp. 394
Author(s):  
Samarina Kamal ◽  
Vandita Singh ◽  
Shashibala Singh
Keyword(s):  
Intensive Care Unit ◽  
Intensive Care ◽  
Antenatal Care ◽  
Arterial Embolization ◽  
Postnatal Period ◽  
Primary Objective ◽  
Blood Product Transfusion ◽  
Tertiary Centre ◽  
High Dependency ◽  
A Prospective Study

Background: Few women during their pregnancy, labour and postnatal period require critical care related to the pregnancy itself, aggravation of a pre-existing illness and complications of the delivery. Pregnant patients account for a small number of ICU admission - 2-10% two main indications for admission are hypertensive disorders (17.2%-46%) and massive haemorrhage (10%-32.8%). The primary objective of the present study was to review the characteristics of the obstetric patients admitted to our ICU over a 2-year period.Methods: It was a prospective study conducted over 50 patients in high dependency and intensive care unit at Alam hospital over a period of 2 years (October 2014 to October 2016).Results: During the study period a total of 50 obstetric patients were transferred to the intensive care unit (ICU). Antenatal care played significant role in the obstetric outcome. 84% of patients transferred to the ICU during the study period had inadequate or no antenatal care, while 8% were booked in their pregnancy and had adequate antenatal care. ICU interventions included mechanical ventilation used in 20(40%) patients, blood and blood product transfusion in 35(70%) patients’ inotropes in 20 patients (40%) antihypertensive therapy in 20 patients (40%), arterial embolization in 2(4%) patients. Maternal mortality was seen in 10 patients (20%).Conclusions: There is a need for training in emergency obstetrics so that the complication can be managed right at the time of occurrence.

scholarly journals Selection and Receipt of Kidney Replacement in Critically Ill Older Patients with AKI

2019 ◽  
Vol 14 (4) ◽  
pp. 496-505 ◽  
Author(s):  
Sean M. Bagshaw ◽  
Neill K.J. Adhikari ◽  
Karen E.A. Burns ◽  
Jan O. Friedrich ◽  
Josée Bouchard ◽  
...  
Keyword(s):  
Intensive Care Unit ◽  
Intensive Care ◽  
Replacement Therapy ◽  
Critically Ill ◽  
Older Patients ◽  
Patient Specific ◽  
Clinical Frailty Scale ◽  
Related Quality ◽  
Kidney Replacement Therapy ◽  
Charlson Comorbidity Score

Background and objectivesOlder patients in the intensive care unit are at greater risk of AKI; however, use of kidney replacement therapy in this population is poorly characterized. We describe the triggers and outcomes associated with kidney replacement therapy in older patients with AKI in the intensive care unit.Design, setting, participants, & measurementsOur study was a prospective cohort study in 16 Canadian hospitals from September 2013 to November 2015. Patients were ≥65 years old, were critically ill, and had severe AKI; exclusion criteria were urgent kidney replacement therapy for a toxin and ESKD. We recorded triggers for kidney replacement therapy (primary exposure), reasons for not receiving kidney replacement therapy, 90-day mortality (primary outcome), and kidney recovery.ResultsOf 499 patients, mean (SD) age was 75 (7) years old, Charlson comorbidity score was 3.0 (2.3), and median (interquartile range) Clinical Frailty Scale score was 4 (3–5). Most were receiving mechanical ventilation (64%; n=319) and vasoactive support (63%; n=314). Clinicians were willing to offer kidney replacement therapy to 361 (72%) patients, and 229 (46%) received kidney replacement therapy. Main triggers for kidney replacement therapy were oligoanuria, fluid overload, and acidemia, whereas main reasons for not receiving therapy were anticipated recovery (67%; n=181) and therapy not consistent with patient preferences for care (24%; n=66). Ninety-day mortality was similar in patients who did and did not receive kidney replacement therapy (50% versus 51%; adjusted hazard ratio, 0.78; 95% confidence interval, 0.58 to 1.06); however, decisions to offer kidney replacement therapy varied significantly by patient mix, acuity, and perceived benefit. There were no differences in health-related quality of life or rehospitalization among survivors.ConclusionsMost older, critically ill patients with severe AKI were perceived as candidates for kidney replacement therapy, and approximately one half received therapy. Both willingness to offer kidney replacement therapy and reasons for not starting showed heterogeneity due to a range in patient-specific factors and clinician perceptions of benefit.

Sign in / Sign up

Export Citation Format

Share Document