Machine Learning to Develop and Internally Validate a Predictive Model for Post-operative Delirium in a Prospective, Observational Clinical Cohort Study of Older Surgical Patients

Racine, Annie M.; Tommet, Douglas; D'Aquila, Madeline L; Fong, Tamara G.; Gou, Yun; Tabloski, Patricia A.; Metzger, Eran D.; Hshieh, Tammy T.; Schmitt, Eva M.; Vasunilashorn, Sarinnapha; Kunze, Lisa; Vlassakov, Kamen; Abdeen, Ayesha; Lange, Jeffrey; Earp, Brandon E.; Dickerson, Bradford C.; Marcantonio, Edward R.; Steingrimsson, Jon A.; Travison, Thomas G.; Inouye, Sharon K.; Jones, Richard N.

doi:10.1007/s11606-020-06238-7

Cited by 37 publications

(52 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…With the full data of 71 items, the AUCs in this study were 0.62 up to 0.71. Thus, all prediction models in SAGES were numerically less accurate (Racine et al, 2020) than the shorter models.…”

Section: Discussionmentioning

confidence: 93%

“…In the Successful Aging after Elective Surgery (SAGES) cohort (Racine et al, 2020), a stepwise logistic regression and machine learning algorithms were used to predict POD in elective surgery of 560 older adults. With a limited data set of 18 items in different machine learning methods, they showed AUCs from 0.53 to 0.57, while in another analysis, adding cognitive performance using the modified Mini-Mental-State 3MS (Teng and Chui, 1987) showed intermediate AUCs (0.53-0.68).…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Presurgical Screening Improves Risk Prediction for Delirium in Elective Surgery of Older Patients: The PAWEL RISK Study

Eschweiler

Czornik

Herrmann

et al. 2021

Front. Aging Neurosci.

View full text Add to dashboard Cite

Introduction: The number of elective surgeries for patients who are over 70 years of age is continuously growing. At the same time, postoperative delirium (POD) is common in older patients (5–60%) depending on predisposing risk factors, such as multimorbidity, cognitive impairment, neurodegenerative disorders and other dementing disorders, and precipitating factors, such as duration of surgery. Knowledge of individual risk profiles prior to elective surgery may help to identify patients at increased risk for development of POD. In this study, clinical and cognitive risk factors for POD were investigated in patients undergoing various elective cardiac and non-cardiac surgeries.Methods: The PAWEL study is a prospective, interventional trial on delirium prevention. At baseline, 880 inpatients at five surgical centers were recruited for sub-sample PAWEL-R. Multimodal assessments included clinical renal function, medication, American Society of Anesthesiologists (ASA) Physical Status Classification System, geriatric and cognitive assessments, which comprised the Montreal Cognitive Assessment Scale (MoCA), Trail-making Test, and Digit Span backward. Delirium incidence was monitored postoperatively by the Confusion Assessment Method (CAM) and a chart review for up to a week or until discharge. Multivariate regression models and Chi-square Automatic Interaction Detectors (CHAID) analyses were performed using delirium incidence as the primary outcome.Results: Eighteen risk factors were investigated in elective cardiovascular and orthopedic or general surgery. A total of 208 out of 880 patients (24%) developed POD. A global regression model that included all risk variables predicted delirium incidence with high accuracy (AUC = 0.81; 95% CI 0.77, 0.85). A simpler model (clinical and cognitive variables; model CLIN-COG) of 10 factors that only included surgery type, multimorbidity, renal failure, polypharmacy, ASA, cut-to-suture time, and cognition (MoCA, Digit Span backward, and preexisting dementia), however, exhibited similar predictive accuracy (AUC = 0.80; 95% CI 0.76, 0.84).Conclusion: The risk of developing POD can be estimated by preoperative assessments, such as ASA classification, expected cut-to-suture time, and short cognitive screenings. This rather efficient approach predicted POD risk over all types of surgery. Thus, a basic risk assessment including a cognitive screen can help to stratify patients at low, medium, or high POD risk to provide targeted prevention and/or management strategies for patients at risk.

show abstract

Section: Discussionmentioning

confidence: 93%

Section: Discussionmentioning

confidence: 99%

Presurgical Screening Improves Risk Prediction for Delirium in Elective Surgery of Older Patients: The PAWEL RISK Study

Eschweiler

Czornik

Herrmann

et al. 2021

Front. Aging Neurosci.

View full text Add to dashboard Cite

show abstract

“…All the models presented in these studies show better performance when compared to a clinical tool. Another recent study have developed a predictive model for post-operative delirium in older surgical patients with better performances than chance, but with similar performances when compared with the traditional stepwise logistic regression [ 26 ]. Another recent study has showed the high predictive ability of RF model in detection delirium based on CAM and delirium observation screening scale (DOSS) [ 28 ].…”

Section: Discussionmentioning

confidence: 99%

“…In literature, there are several tools for facilitating delirium detection [ 22 , 23 ], such as the Confusion Assessment Method (CAM) [ 24 ], 4AT test [ 25 ], and the most recent Nursing DElirium SCreening (Nu-DESC) tool [ 19 ]. Both CAM [ 26 , 27 , 28 ] and Nu-DESC scales were used to compare the ability of random forest (RF) models in predicting the risk of delirium episodes. The structure of these tools shows similar domains.…”

Section: Introductionmentioning

confidence: 99%

“…Bellelli [ 25 ], for the first time, used the 4AT score to assess patients at risk for delirium. Machine learning techniques (MLTs) have been widely used in data-driven prediction models, for example in dementia [ 29 ], or delirium as well with performances comparable with traditional logistic regression [ 26 ] and included into clinical workflow [ 30 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Machine Learning Approach for Investigating Delirium as a Multifactorial Syndrome

Ocagli

Bottigliengo

Lorenzoni

et al. 2021

IJERPH

View full text Add to dashboard Cite

Delirium is a psycho-organic syndrome common in hospitalized patients, especially the elderly, and is associated with poor clinical outcomes. This study aims to identify the predictors that are mostly associated with the risk of delirium episodes using a machine learning technique (MLT). A random forest (RF) algorithm was used to evaluate the association between the subject’s characteristics and the 4AT (the 4 A’s test) score screening tool for delirium. RF algorithm was implemented using information based on demographic characteristics, comorbidities, drugs and procedures. Of the 78 patients enrolled in the study, 49 (63%) were at risk for delirium, 32 (41%) had at least one episode of delirium during the hospitalization (38% in orthopedics and 31% both in internal medicine and in the geriatric ward). The model explained 75.8% of the variability of the 4AT score with a root mean squared error of 3.29. Higher age, the presence of dementia, physical restraint, diabetes and a lower degree are the variables associated with an increase of the 4AT score. Random forest is a valid method for investigating the patients’ characteristics associated with delirium onset also in small case-series. The use of this model may allow for early detection of delirium onset to plan the proper adjustment in healthcare assistance.

show abstract

せん妄の予測に対する機械学習の利用状況：スコーピングレビュー(The use of machine learning for the prediction of delirium: a scoping review)

守克

和也

匡

et al. 2022

Nihon Kyukyu Igakukai Zasshi: Japanese Journal of Japanese Asso

View full text Add to dashboard Cite

要旨【目的】せん妄の予測に対して機械学習を利用した研究の動向を概観し，今後の課題を明らかにすることを目的とした。【方法】2021年4月までに発行された論文を対象として，PubMed，CINAHL，医中誌Webの各データベースで検索し，適格基準を満たした論文をレビューの対象とした。【結果】適格基準を満たした論文は23編であった。対象論文は多施設研究が多かったものの，集中治療患者を対象とした研究は単施設研究に限られていた。せん妄の予測には，多くの論文が100以上の変数を使用していた。せん妄のラベルにはICDを使用した論文が多かった。【結語】集中治療患者を対象として，予測に使用する変数を減らし，CAM–ICUやICDSCをせん妄のラベルとする多施設研究を実施することで，せん妄の予測における機械学習の利用可能性を模索する必要がある。

show abstract

Machine Learning to Develop and Internally Validate a Predictive Model for Post-operative Delirium in a Prospective, Observational Clinical Cohort Study of Older Surgical Patients

Cited by 37 publications

References 45 publications

Presurgical Screening Improves Risk Prediction for Delirium in Elective Surgery of Older Patients: The PAWEL RISK Study

Presurgical Screening Improves Risk Prediction for Delirium in Elective Surgery of Older Patients: The PAWEL RISK Study

A Machine Learning Approach for Investigating Delirium as a Multifactorial Syndrome

せん妄の予測に対する機械学習の利用状況：スコーピングレビュー(The use of machine learning for the prediction of delirium: a scoping review)

Contact Info

Product

Resources

About