scholarly journals Artificial Intelligence May Predict Early Sepsis After Liver Transplantation

2021 ◽  
Vol 12 ◽  
Author(s):  
Rishikesan Kamaleswaran ◽  
Sanjaya K. Sataphaty ◽  
Valeria R. Mas ◽  
James D. Eason ◽  
Daniel G. Maluf

Background: Sepsis, post-liver transplantation, is a frequent challenge that impacts patient outcomes. We aimed to develop an artificial intelligence method to predict the onset of post-operative sepsis earlier.Methods: This pilot study aimed to identify “physiomarkers” in continuous minute-by-minute physiologic data streams, such as heart rate, respiratory rate, oxygen saturation (SpO2), and blood pressure, to predict the onset of sepsis. The model was derived from a cohort of 5,748 transplant and non-transplant patients across intensive care units (ICUs) over 36 months, with 92 post-liver transplant patients who developed sepsis.Results: Using an alert timestamp generated with the Third International Consensus Definition of Sepsis (Sepsis-3) definition as a reference point, we studied up to 24 h of continuous physiologic data prior to the event, totaling to 8.35 million data points. One hundred fifty-five features were generated using signal processing and statistical methods. Feature selection identified 52 highly ranked features, many of which included blood pressures. An eXtreme Gradient Boost (XGB) classifier was then trained on the ranked features by 5-fold cross validation on all patients (n = 5,748). We identified that the average sensitivity, specificity, positive predictive value (PPV), and area under the receiver-operator curve (AUC) of the model after 100 iterations was 0.94 ± 0.02, 0.9 ± 0.02, 0.89 ± 0.01, respectively, and 0.97 ± 0.01 for predicting sepsis 12 h before meeting criteria.Conclusion: The data suggest that machine learning/deep learning can be applied to continuous streaming data in the transplant ICU to monitor patients and possibly predict sepsis.

2020 ◽  
Vol 27 (1) ◽  
pp. 158-168
Author(s):  
Maximilian Schönung ◽  
Julia Meyer ◽  
Peter Nöllke ◽  
Adam B. Olshen ◽  
Mark Hartmann ◽  
...  

BMJ Open ◽  
2021 ◽  
Vol 11 (12) ◽  
pp. e049777
Author(s):  
Lies ter Beek ◽  
Mathieu S Bolhuis ◽  
Harriët Jager-Wittenaar ◽  
René X D Brijan ◽  
Marieke G G Sturkenboom ◽  
...  

ObjectivesMalnutrition is associated with a twofold higher risk of dying in patients with tuberculosis (TB) and considered an important potentially reversible risk factor for failure of TB treatment. The construct of malnutrition has three domains: intake or uptake of nutrition; body composition and physical and cognitive function. The objectives of this systematic review are to identify malnutrition assessment methods, and to quantify how malnutrition assessment methods capture the international consensus definition for malnutrition, in patients with TB.DesignDifferent assessment methods were identified. We determined the extent of capturing of the three domains of malnutrition, that is, intake or uptake of nutrition, body composition and physical and cognitive function.ResultsSeventeen malnutrition assessment methods were identified in 69 included studies. In 53/69 (77%) of studies, body mass index was used as the only malnutrition assessment method. Three out of 69 studies (4%) used a method that captured all three domains of malnutrition.ConclusionsOur study focused on published articles. Implementation of new criteria takes time, which may take longer than the period covered by this review. Most patients with TB are assessed for only one aspect of the conceptual definition of malnutrition. The use of international consensus criteria is recommended to establish uniform diagnostics and treatment of malnutrition.PROSPERO registration numberCRD42019122832.


Neurosurgery ◽  
2020 ◽  
Author(s):  
Andrew J Gardner

Abstract BACKGROUND Consensus on the definition of extant video signs of concussion have recently been proposed by representatives of international sporting codes for global consistency across professional leagues. OBJECTIVE To review the reliability of the proposed international consensus video signs of concussion in National Rugby League (NRL) head impact events (HIEs). METHODS The video signs of concussion were coded for every HIE during the 2019 NRL season. Coding was conducted blinded to the concussion status. Frequency, sensitivity, specificity, and a receiver operating characteristic curve were calculated. RESULTS There were 943 HIEs identified over the 2019 NRL season, of which 106 resulted in a diagnosed concussion. The most frequently observed video sign in concussed athletes was blank/vacant look (54%), which was also the most sensitive video sign (0.54, CI: 0.44-0.63), while the most specific was tonic posturing (0.99, CI: 0.99-1.00). In 43.4% of diagnosed concussions none of the 6 video signs were present. The 6 video signs demonstrated a “fair” ability to discriminate between concussion and nonconcussion HIEs (area under the curve = 0.76). CONCLUSION International consensus agreement between collision sports for extant video signs of concussion and the definition of those extant video signs are clinically important. The selection of signs requires rigorous assessment to examine their predictive value across all sports and within individual sports, and to determine further video signs to compliment and improve the identification of possible concussion events within various sports. The current study demonstrated that, for NRL-related HIEs, the diagnostic accuracy of video signs varies.


PLoS ONE ◽  
2018 ◽  
Vol 13 (4) ◽  
pp. e0196754
Author(s):  
Albert Balaguer ◽  
Cristina Monforte-Royo ◽  
Josep Porta-Sales ◽  
Alberto Alonso-Babarro ◽  
Rogelio Altisent ◽  
...  

Neurology ◽  
2019 ◽  
Vol 93 (14) ◽  
pp. 630-639 ◽  
Author(s):  
Pietro Cortelli ◽  
Giovanna Calandra-Buonaura ◽  
Eduardo E. Benarroch ◽  
Giulia Giannini ◽  
Alex Iranzo ◽  
...  

Multiple system atrophy (MSA) is a neurodegenerative disorder characterized by a combination of autonomic failure, cerebellar ataxia, and parkinsonism. Laryngeal stridor is an additional feature for MSA diagnosis, showing a high diagnostic positive predictive value, and its early occurrence might contribute to shorten survival. A consensus definition of stridor in MSA is lacking, and disagreement persists about its diagnosis, prognosis, and treatment. An International Consensus Conference among experts with methodological support was convened in Bologna in 2017 to define stridor in MSA and to reach consensus statements for the diagnosis, prognosis, and treatment. Stridor was defined as a strained, high-pitched, harsh respiratory sound, mainly inspiratory, occurring only during sleep or during both sleep and wakefulness, and caused by laryngeal dysfunction leading to narrowing of the rima glottidis. According to the consensus, stridor may be recognized clinically by the physician if present at the time of examination, with the help of a witness, or by listening to an audio recording. Laryngoscopy is suggested to exclude mechanical lesions or functional vocal cord abnormalities related to different neurologic conditions. If the suspicion of stridor needs confirmation, drug-induced sleep endoscopy or video polysomnography may be useful. The impact of stridor on survival and quality of life remains uncertain. Continuous positive airway pressure and tracheostomy are both suggested as symptomatic treatment of stridor, but whether they improve survival is uncertain. Several research gaps emerged involving diagnosis, prognosis, and treatment. Unmet needs for research were identified.


2020 ◽  
Vol 90 (3) ◽  
pp. 300-307 ◽  
Author(s):  
Celia Keane ◽  
Nicola S. Fearnhead ◽  
Liliana G. Bordeianou ◽  
Peter Christensen ◽  
Eloy Espin Basany ◽  
...  

2021 ◽  
pp. 002076402110322
Author(s):  
Gemma Simons ◽  
David S Baldwin

Background: There is no international consensus definition of ‘wellbeing’. This has led to wellbeing being captured in many different ways. Aims: To construct an inclusive, global operational definition of wellbeing. Methods: The differences between wellbeing components and determinants and the terms used interchangeably with wellbeing, such as health, are considered from the perspective of a doctor. The philosophies underpinning wellbeing and modern wellbeing research theories are discussed in terms of their appropriateness in an inclusive definition. Results: An operational definition is proposed that is not limited to doctors, but universal, and inclusive: ‘Wellbeing is a state of positive feelings and meeting full potential in the world. It can be measured subjectively and objectively, using a salutogenic approach’. Conclusions: This operational definition allows the differentiation of wellbeing from terms such as quality of life and emphasises that in the face of global challenges people should still consider wellbeing as more than the absence of pathology.


2020 ◽  
Vol 63 (3) ◽  
pp. 274-284 ◽  
Author(s):  
Celia Keane ◽  
Nicola S. Fearnhead ◽  
Liliana G. Bordeianou ◽  
Peter Christensen ◽  
Eloy Espin Basany ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document