On predictions in critical care: The individual prognostication fallacy in elderly patients

被引：21

作者：

Beil, Michael ^{[1
]}

Sviri, Sigal ^{[1
]}

Flaatten, Hans ^{[2
]}

De Lange, Dylan W. ^{[3
]}

Jung, Christian ^{[4
]}

Szczeklik, Wojciech ^{[5
]}

Leaver, Susannah ^{[6
]}

Rhodes, Andrew ^{[6
]}

Guidet, Bertrand ^{[7
]}

van Heerden, P. Vernon ^{[8
]}

机构：

[1] Hadassah Univ Hosp, Med Intens Care Unit, POB 12000, IL-9112001 Jerusalem, Israel

[2] Haukeland Univ Sjukehus, Intens Care & Dept Clin Med, Bergen, Norway

[3] Univ Utrecht, Univ Med Ctr, Dept Intens Care Med, Utrecht, Netherlands

[4] Heinrich Heine Univ, Univ Hosp, Div Cardiol, Dusseldorf, Germany

[5] Jagiellonian Univ Med Coll, Dept Intens Care, Krakow, Poland

[6] St Georges Univ Hosp NHS Fdn Trust, Intens Care, London, England

[7] Hop St Antoine, Assistance Publ Hop Paris, Serv Reanimat Med, Paris, France

[8] Hadassah Univ Hosp, Gen Intens Care Unit, Jerusalem, Israel

来源：

JOURNAL OF CRITICAL CARE | 2021年 / 61卷

关键词：

Critical care; individual prognostication; predictive modeling; time-limited trial; DECISION-MAKING; RECOMMENDATIONS; PROGNOSIS; ADMISSION; MEDICINE; DOCTORS; MODELS; TRIAGE; RISK; TIME;

D O I：

10.1016/j.jcrc.2020.10.006

中图分类号：

R4 [临床医学];

学科分类号：

1002 ; 100602 ;

摘要：

Predicting the future course of critical conditions involves personal experience, heuristics and statistical models. Although these methods may perform well for some cases and population averages, they suffer from substantial shortcomings when applied to individual patients. The reasons include methodological problems of statistical modeling as well as limitations of cross-sectional data sampling. Accurate predictions for individual patients become crucial when they have to guide irreversible decision-making. This notably applies to triage situations in response to a lack of healthcare resources. We will discuss these issues and argue that analysing longitudinal data obtained from time-limited trials in intensive care can provide a more robust approach to individual prognostication. (C) 2020 Elsevier Inc. All rights reserved.

引用

页码：34 / 38

页数：5

共 52 条

[1] Clinical reasoning of junior doctors in emergency medicine: a grounded theory study [J].

Adams, E. ;

Goyder, C. ;

Heneghan, C. ;

Brand, L. ;

Ajjawi, R. .

EMERGENCY MEDICINE JOURNAL, 2017, 34 (02) :70-75

[2] Ergodicity is sufficient but not necessary for group-to-individual generalizability [J].

Adolf, Janne K. ;

Fried, Eiko I. .

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2019, 116 (14) :6540-6541

[3]

Allam A., 2020, ARXIV200506630

[4] Ethical considerations about artificial intelligence for prognostication in intensive care [J].

Beil, Michael ;

Proft, Ingo ;

van Heerden, Daniel ;

Sviri, Sigal ;

van Heerden, Peter Vernon .

INTENSIVE CARE MEDICINE EXPERIMENTAL, 2019, 7 (01)

[5] Trauma in silico: Individual-specific mathematical models and virtual clinical populations [J].

Brown, David ;

Namas, Rami A. ;

Almahmoud, Khalid ;

Zaaqoq, Akram ;

Sarkar, Joydeep ;

Barclay, Derek A. ;

Yin, Jinling ;

Ghuma, Ali ;

Abboud, Andrew ;

Constantine, Gregory ;

Nieman, Gary ;

Zamora, Ruben ;

Chang, Steven C. ;

Billiar, Timothy R. ;

Vodovotz, Yoram .

SCIENCE TRANSLATIONAL MEDICINE, 2015, 7 (285)

[6] Machine Learning and Prediction in Medicine - Beyond the Peak of Inflated Expectations [J].

Chen, Jonathan H. ;

Asch, Steven M. .

NEW ENGLAND JOURNAL OF MEDICINE, 2017, 376 (26) :2507-2509

[7]

Collins GS, 2015, ANN INTERN MED, V162, P55, DOI [10.1186/s12916-014-0241-z, 10.7326/M14-0698, 10.1016/j.jclinepi.2014.11.010, 10.7326/M14-0697, 10.1016/j.eururo.2014.11.025, 10.1002/bjs.9736, 10.1038/bjc.2014.639, 10.1136/bmj.g7594, 10.1111/eci.12376]

[8]

Domowitz L, 2001, J ECONOMETRICS, V102, P365

[9]

Donaldson, 2000, ERR IS HUMAN

[10]

Dusenberry Michael W., 2020, CHIL '20: Proceedings of the Conference on Health, Inference, and Learning, P204, DOI 10.1145/3368555.3384457

← 1 2 3 4 5 6 →