scholarly journals Machine Learning Evaluation of Biliary Atresia Patients to Predict Long-Term Outcome after the Kasai Procedure

2021 ◽  
Vol 8 (11) ◽  
pp. 152
Author(s):  
Martina Caruso ◽  
Carlo Ricciardi ◽  
Gregorio Delli Paoli ◽  
Fabiola Di Dato ◽  
Leandro Donisi ◽  
...  

Kasai portoenterostomy (KP) represents the first-line treatment for biliary atresia (BA). The purpose was to compare the accuracy of quantitative parameters extracted from laboratory tests, US imaging, and MR imaging studies using machine learning (ML) algorithms to predict the long-term medical outcome in native liver survivor BA patients after KP. Twenty-four patients were evaluated according to clinical and laboratory data at initial evaluation (median follow-up = 9.7 years) after KP as having ideal (n = 15) or non-ideal (n = 9) medical outcomes. Patients were re-evaluated after an additional 4 years and classified in group 1 (n = 12) as stable and group 2 (n = 12) as non-stable in the disease course. Laboratory and quantitative imaging parameters were merged to test ML algorithms. Total and direct bilirubin (TB and DB), as laboratory parameters, and US stiffness, as an imaging parameter, were the only statistically significant parameters between the groups. The best algorithm in terms of accuracy, sensitivity, specificity, and AUCROC was naive Bayes algorithm, selecting only laboratory parameters (TB and DB). This preliminary ML analysis confirms the fundamental role of TB and DB values in predicting the long-term medical outcome for BA patients after KP, even though their values may be within the normal range. Physicians should be alert when TB and DB values change slightly.

Cytokine ◽  
2018 ◽  
Vol 111 ◽  
pp. 382-388 ◽  
Author(s):  
Omid Madadi-Sanjani ◽  
Joachim F. Kuebler ◽  
Stephanie Dippel ◽  
Anna Gigina ◽  
Christine S. Falk ◽  
...  

2018 ◽  
Vol 25 (5) ◽  
pp. 275-280
Author(s):  
Takeshi Saito ◽  
Keita Terui ◽  
Tetsuya Mitsunaga ◽  
Mitsuyuki Nakata ◽  
Shugo Komatsu ◽  
...  

2018 ◽  
Vol 44 (suppl_1) ◽  
pp. S101-S102 ◽  
Author(s):  
Jessica De Nijs ◽  
Daniel P J van Opstal ◽  
Ronald J Janssen ◽  
Wiepke Cahn ◽  
Hugo Schnack ◽  
...  

2009 ◽  
Vol 48 (4) ◽  
pp. 443-450 ◽  
Author(s):  
Masato Shinkai ◽  
Youkatsu Ohhama ◽  
Hiroshi Take ◽  
Norihiko Kitagawa ◽  
Hironori Kudo ◽  
...  

Author(s):  
Shahram Paydar ◽  
Elahe Bordbar ◽  
Mehdi Taghipour ◽  
Hosseinali Khalili ◽  
Mehran Jafari

Background: To evaluate the relationship between presenting Glasgow Coma Scale (GCS) or laboratory data of patients with TBI and Extended Glasgow Outcome Scale (GOSE) and final outcome (deceased, survived) at one year.Methods: 74 patients (59 males and 15 females; mean age ±SD of 40±19years) who presented with TBI were entered into the study, and their GCS and laboratory data were recorded. After one year, GOSE level and final outcome were evaluated with 11 yes/no questions obtained from the patients or their first-degree relatives.Results: The patients with lower GCS on admission or day six, significantly had lower GOSE. Moreover, the lower the GCS in the first week of admission, the poorer the final outcome. Among laboratory data, the base deficit (BD) level of -6 or worse on admission was an indicator of mortality at one year. Hypernatremia was the only laboratory factor which predicted poor GOSE after a year. Furthermore, patients with serum hypernatremia, hyperkalemia, or high PTT levels on the first week of admission had poor final outcome.Conclusions: Presenting GCS and metabolic derangements are reliable indicators of long-term outcome and GOSE at one year. 


2021 ◽  
Vol Publish Ahead of Print ◽  
Author(s):  
Daan B.E. van Wessel ◽  
M. Nomden ◽  
J.L.M. Bruggink ◽  
R.H.J. de Kleine ◽  
A. Kurilshikov ◽  
...  

Stroke ◽  
2012 ◽  
Vol 43 (suppl_1) ◽  
Author(s):  
Shadi Yaghi ◽  
Salah G Keyrouz ◽  
Archana Hinduja

Objective: to determine the outcome of patients with minor strokes who receive intravenous thrombolysis in a telestroke network. Background: The Arkansas SAVES (Stroke Assistance through Virtual Emergency Support) telestroke network provided emergency evaluation and therapy for acute stroke to 22 spoke sites statewide between November 2008 and May 2011. While there is little question regarding safety of IV thrombolysis in minor strokes, its impact on long-term outcome is equivocal. Few studies, yet with methodological problems attempted to answer this question. Methods: Institutional IRB approval was obtained to review the prospective database of the Arkansas SAVES program. We included patients with admission NIHSS ≤ 4. They were divided into two groups based on whether or not they received IV thrombolysis. Baseline characteristics, risk factors, laboratory data and outcomes were compared between the two groups. Good outcome was defined as mRS < 2 and excellent outcome as mRS < 1, at 90 days. For statistical analysis, we used independent T, and fisher’s exact tests. Results: The cohort included 562 patients receiving a teleconsultation between November 2008 and May 2011, of whom 116 underwent IV thrombolysis. Sixty patients with admission NIHSS ≤ 4 were included in this analysis. Patients who received IV thrombolysis had a trend towards a higher mean admission NIHSS (3.5 ± 0.7 vs. 3.9 ± 1.0, p = 0.085). There was no statistically significant difference in the percentage of good (76.7% vs. 73.3%, p = NS) or excellent outcome (60.0% vs. 56.7%, p = NS) between the two groups. The mean admission NIHSS was similar in patients with mRS<1 and mRS>1 (3.6 ± 0.9 vs. 3.7 ± 0.9, p = NS), possibly indicating a disconnect between stroke severity, when mild, and overall outcome. Conclusion: Intravenous thrombolysis did not improve outcomes in patients with minimal deficits. The use of IV thrombolytics in patients with minor strokes should be individualized depending on the type of deficits and potential disability. A larger randomized trial is needed to confirm those results.


1996 ◽  
Vol 31 (6) ◽  
pp. 774-778 ◽  
Author(s):  
Natalie L. Yanchar ◽  
Andrew M.J. Shapiro ◽  
David L. Sigalet

Sign in / Sign up

Export Citation Format

Share Document