Utilization of a computerized program to identify nutritionally at risk patients in real time

2001 ◽  
Vol 101 (9) ◽  
pp. A-9
Author(s):  
P.A. Pullen ◽  
A.T. DeFrancesco ◽  
M.M. Wrana ◽  
J. Moen ◽  
D. Korchnak ◽  
...  
Keyword(s):  
At Risk ◽  
Real Time ◽  
Risk Patients

scholarly journals Physiomarkers in Real-Time Physiological Data Streams Predict Adult Sepsis Onset Earlier Than Clinical Practice

2018 ◽  
Author(s):  
Franco van Wyk ◽  
Anahita Khojandi ◽  
Robert L. Davis ◽  
Rishikesan Kamaleswaran
Keyword(s):  
Machine Learning ◽  
At Risk ◽  
Real Time ◽  
Early Stage ◽  
Time Windows ◽  
Machine Learning Algorithms ◽  
Physiological Data ◽  
Threatening Condition ◽  
Risk Patients ◽  
Life Threatening

AbstractRationale: Sepsis is a life-threatening condition with high mortality rates and expensive treatment costs. To improve short- and long-term outcomes, it is critical to detect at-risk sepsis patients at an early stage.Objective: Our primary goal was to develop machine learning models capable of predicting sepsis using streaming physiological data in real-time.Methods: A dataset consisting of high-frequency physiological data from 1,161 critically ill patients admitted to the intensive care unit (ICU) was analyzed in this IRB-approved retrospective observational cohort study. Of that total, 634 patients were identified to have developed sepsis. In this paper, we define sepsis as meeting the Systemic Inflammatory Response Syndrome (SIRS) criteria in the presence of the suspicion of infection. In addition to the physiological data, we include white blood cell count (WBC) to develop a model that can signal the future occurrence of sepsis. A random forest classifier was trained to discriminate between sepsis and non-sepsis patients using a total of 108 features extracted from 2-hour moving time-windows. The models were trained on 80% of the patients and were tested on the remaining 20% of the patients, for two observational periods of lengths 3 and 6 hours.Results: The models, respectively, resulted in F1 scores of 75% and 69% half-hour before sepsis onset and 79% and 76% ten minutes before sepsis onset. On average, the models were able to predict sepsis 210 minutes (3.5 hours) before the onset.Conclusions: The use of robust machine learning algorithms, continuous streams of physiological data, and WBC, allows for early identification of at-risk patients in real-time with high accuracy.

Exploring the Validity and Operational Impact of Using Allied Health Assistants to Conduct Dysphagia Screening for Low-Risk Patients Within the Acute Hospital Setting

2020 ◽  
Vol 29 (4) ◽  
pp. 1944-1955 ◽  
Author(s):  
Maria Schwarz ◽  
Elizabeth C. Ward ◽  
Petrea Cornwell ◽  
Anne Coccetti ◽  
Pamela D'Netto ◽  
...  
Keyword(s):  
At Risk ◽  
Allied Health ◽  
Assessment Tool ◽  
Hospital Setting ◽  
Low Risk ◽  
False Negatives ◽  
Exact Agreement ◽  
Risk Patients ◽  
Impact Phase ◽  
Operational Impact

Purpose The purpose of this study was to examine (a) the agreement between allied health assistants (AHAs) and speech-language pathologists (SLPs) when completing dysphagia screening for low-risk referrals and at-risk patients under a delegation model and (b) the operational impact of this delegation model. Method All AHAs worked in the adult acute inpatient settings across three hospitals and completed training and competency evaluation prior to conducting independent screening. Screening (pass/fail) was based on results from pre-screening exclusionary questions in combination with a water swallow test and the Eating Assessment Tool. To examine the agreement of AHAs' decision making with SLPs, AHAs ( n = 7) and SLPs ( n = 8) conducted an independent, simultaneous dysphagia screening on 51 adult inpatients classified as low-risk/at-risk referrals. To examine operational impact, AHAs independently completed screening on 48 low-risk/at-risk patients, with subsequent clinical swallow evaluation conducted by an SLP with patients who failed screening. Results Exact agreement between AHAs and SLPs on overall pass/fail screening criteria for the first 51 patients was 100%. Exact agreement for the two tools was 100% for the Eating Assessment Tool and 96% for the water swallow test. In the operational impact phase ( n = 48), 58% of patients failed AHA screening, with only 10% false positives on subjective SLP assessment and nil identified false negatives. Conclusion AHAs demonstrated the ability to reliably conduct dysphagia screening on a cohort of low-risk patients, with a low rate of false negatives. Data support high level of agreement and positive operational impact of using trained AHAs to perform dysphagia screening in low-risk patients.

scholarly journals The APAC Score: A Novel and Highly Performant Serological Tool for Early Diagnosis of Hepatocellular Carcinoma in Patients with Liver Cirrhosis

2021 ◽  
Vol 10 (15) ◽  
pp. 3392
Author(s):  
Joeri Lambrecht ◽  
Mustafa Porsch-Özçürümez ◽  
Jan Best ◽  
Fabian Jost-Brinkmann ◽  
Christoph Roderburg ◽  
...  
Keyword(s):  
Hepatocellular Carcinoma ◽  
At Risk ◽  
Liver Cirrhosis ◽  
Early Stage ◽  
Treatment Options ◽  
Growth Factor Receptor ◽  
Serum Samples ◽  
Disease Etiology ◽  
Risk Patients ◽  
Scoring Tool

(1) Background: Surveillance of at-risk patients for hepatocellular carcinoma (HCC) is highly necessary, as curative treatment options are only feasible in early disease stages. However, to date, screening of patients with liver cirrhosis for HCC mostly relies on suboptimal ultrasound-mediated evaluation and α-fetoprotein (AFP) measurement. Therefore, we sought to develop a novel and blood-based scoring tool for the identification of early-stage HCC. (2) Methods: Serum samples from 267 patients with liver cirrhosis, including 122 patients with HCC and 145 without, were collected. Expression levels of soluble platelet-derived growth factor receptor beta (sPDGFRβ) and routine clinical parameters were evaluated, and then utilized in logistic regression analysis. (3) Results: We developed a novel serological scoring tool, the APAC score, consisting of the parameters age, sPDGFRβ, AFP, and creatinine, which identified patients with HCC in a cirrhotic population with an AUC of 0.9503, which was significantly better than the GALAD score (AUC: 0.9000, p = 0.0031). Moreover, the diagnostic accuracy of the APAC score was independent of disease etiology, including alcohol (AUC: 0.9317), viral infection (AUC: 0.9561), and NAFLD (AUC: 0.9545). For the detection of patients with (very) early (BCLC 0/A) HCC stage or within Milan criteria, the APAC score achieved an AUC of 0.9317 (sensitivity: 85.2%, specificity: 89.2%) and 0.9488 (sensitivity: 91.1%, specificity 85.3%), respectively. (4) Conclusions: The APAC score is a novel and highly accurate serological tool for the identification of HCC, especially for early stages. It is superior to the currently proposed blood-based algorithms, and has the potential to improve surveillance of the at-risk population.

scholarly journals Seroprevalence of Antibodies against Diphtheria, Tetanus and Pertussis in Adult At-Risk Patients

Vaccines ◽  
2021 ◽  
Vol 9 (1) ◽  
pp. 18
Author(s):  
Lise Boey ◽  
Eline Bosmans ◽  
Liane Braz Ferreira ◽  
Nathalie Heyvaert ◽  
Melissa Nelen ◽  
...  
Keyword(s):  
At Risk ◽  
Chronic Diseases ◽  
Age Groups ◽  
Chronic Obstructive ◽  
Solid Organ ◽  
Recent Infection ◽  
Vaccination Programs ◽  
Vaccine Preventable Diseases ◽  
Increased Risk ◽  
Risk Patients

Patients with chronic diseases are at increased risk of complications following infection. It remains, however, unknown to what extend they are protected against vaccine-preventable diseases. We assessed seroprevalence of antibodies against diphtheria, tetanus and pertussis to evaluate whether current vaccination programs in Belgium are adequate. Antibody titers were assessed with a bead-based multiplex assay in serum of 1052 adults with chronic diseases. We included patients with diabetes mellitus type 1 (DM1) (n = 172), DM2 (n = 77), chronic kidney disease (n = 130), chronic obstructive pulmonary disease (COPD) (n = 170), heart failure (n = 77), HIV (n = 196) and solid organ transplant (SOT) recipients (n = 230). Factors associated with seroprevalence were analysed with multiple logistic regression. We found seroprotective titers in 29% for diphtheria (≥0.1 IU/mL), in 83% for tetanus (≥0.1 IU/mL) and 22% had antibodies against pertussis (≥5 IU/mL). Seroprotection rates were higher (p < 0.001) when vaccinated within the last ten years. Furthermore, diphtheria seroprotection decreased with age (p < 0.001). Tetanus seroprotection was less reached in women (p < 0.001) and older age groups (p < 0.001). For pertussis, women had more often a titer suggestive of a recent infection or vaccination (≥100 IU/mL, p < 0.01). We conclude that except for tetanus, the vast majority of at-risk patients remains susceptible to vaccine-preventable diseases such as diphtheria and pertussis.

Sign in / Sign up

Export Citation Format

Share Document