1
|
Sheng W, Tang X, Hu X, Liu P, Liu L, Miao H, Wang D, Li T. Random forest algorithm for predicting postoperative delirium in older patients. Front Neurol 2024; 14:1325941. [PMID: 38274882 PMCID: PMC10808713 DOI: 10.3389/fneur.2023.1325941] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/22/2023] [Accepted: 12/29/2023] [Indexed: 01/27/2024] Open
Abstract
Objective In this study, we were aimed to identify important variables via machine learning algorithms and predict postoperative delirium (POD) occurrence in older patients. Methods This study was to make the secondary analysis of data from a randomized controlled trial. The Boruta function was used to screen relevant basic characteristic variables. Four models including Logistic Regression (LR), K-Nearest Neighbor (KNN), the Classification and Regression Tree (CART), and Random Forest (RF) were established from the data set using repeated cross validation, hyper-parameter optimization, and Smote technique (Synthetic minority over-sampling technique, Smote), with the calculation of confusion matrix parameters and the plotting of Receiver operating characteristic curve (ROC), Precision recall curve (PRC), and partial dependence graph for further analysis and evaluation. Results The basic characteristic variables resulting from Boruta screening included grouping, preoperative Mini-Mental State Examination(MMSE), CHARLSON score, preoperative HCT, preoperative serum creatinine, intraoperative bleeding volume, intraoperative urine volume, anesthesia duration, operation duration, postoperative morphine dosage, intensive care unit (ICU) duration, tracheal intubation duration, and 7-day postoperative rest and move pain score (median and max; VAS-Rest-M, VAS-Move-M, VAS-Rest-Max, and VAS-Move-Max). And Random Forest (RF) showed the best performance in the testing set among the 4 models with Accuracy: 0.9878; Matthews correlation coefficient (MCC): 0.8763; Area under ROC curve (AUC-ROC): 1.0; Area under the PRC Curve (AUC-PRC): 1.0. Conclusion A high-performance algorithm was established and verified in this study demonstrating the degree of POD risk changes in perioperative elderly patients. And the major risk factors for the development of POD were CREA and VAS-Move-Max.
Collapse
Affiliation(s)
- Weixuan Sheng
- Department of Anesthesiology, Beijing Shijitan Hospital, Capital Medical University, Beijing, China
| | - Xianshi Tang
- Key Laboratory of National Health Commission on Parasitic Disease Control and Prevention, Key Laboratory of Jiangsu Province on Parasite and Vector Control Technology, Jiangsu Institute of Parasitic Diseases, Wuxi, China
| | - Xiaoyun Hu
- Department of Anesthesiology, Beijing Shijitan Hospital, Capital Medical University, Beijing, China
| | - Pengfei Liu
- Department of Anesthesiology, Beijing Shijitan Hospital, Capital Medical University, Beijing, China
| | - Lei Liu
- Department of Science and Technology, Beijing Shijitan Hospital, Capital Medical University, Beijing, China
| | - Huihui Miao
- Department of Anesthesiology, Beijing Shijitan Hospital, Capital Medical University, Beijing, China
| | - Dongxin Wang
- Department of Anesthesiology, Peking University First Hospital, Beijing, China
| | - Tianzuo Li
- Department of Anesthesiology, Beijing Shijitan Hospital, Capital Medical University, Beijing, China
| |
Collapse
|
2
|
Shorofi SA, Dadashian P, Arbon P, Moosazadeh M. The efficacy of earplugs and eye masks for delirium severity and sleep quality in patients undergoing coronary artery bypass grafting in cardiac intensive care units: A single-blind, randomised controlled trial. Aust Crit Care 2024; 37:74-83. [PMID: 37802695 DOI: 10.1016/j.aucc.2023.08.003] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/16/2023] [Revised: 07/31/2023] [Accepted: 08/26/2023] [Indexed: 10/08/2023] Open
Abstract
BACKGROUND AND PURPOSE Delirium is a neuropsychiatric syndrome with a wide range of possible causes and multiple complications in patients admitted to intensive care units. It is, therefore, necessary to seek appropriate and safe strategies to prevent and manage delirium. This study is intended to examine the efficacy of eye masks and earplugs for delirium severity and sleep quality in patients with coronary artery bypass grafting in a cardiac intensive care unit. MATERIALS AND METHODS This single-blind, randomised controlled trial was conducted on 114 patients who were consecutively enrolled and randomly assigned to either the experimental group or the control group. The experimental group received routine care plus eye masks and earplugs, and the control group received only routine care. The delirium severity and sleep quality were measured with the Neelon and Champagne confusion scale and the Verran and Snyder-Halpern sleep scale. RESULTS The mean delirium severity score differed significantly between the two groups on the second, third, and fourth postoperative days (p < 0.001). Although the trend of changes in the mean delirium severity score from the first postoperative day (before the intervention) to the second, third, and fourth postoperative days was downward in the two groups (trending towards higher delirium severity), the control group experienced greater changes than the experimental group. An intragroup analysis of delirium severity detected a statistically significant difference in both the experimental and control groups (p < 0.001). The sleep quality domains (sleep disturbance, sleep effectiveness, sleep supplementation) showed a statistically significant difference between the two groups across the three intervention days (p < 0.001). CONCLUSION The overnight use of eye masks and earplugs were found to have positive effects on sleep quality domains (sleep disturbance, sleep effectiveness, sleep supplementation) and delirium severity in coronary artery bypass grafting patients admitted to the cardiac intensive care unit for several days. It was also found that a significant interaction effect between the sleep disturbance subscale and delirium severity exists. CLINICAL TRIAL REGISTRATION NUMBER (https://en.irct.ir): IRCT20210523051370N2.
Collapse
Affiliation(s)
- Seyed Afshin Shorofi
- Traditional and Complementary Medicine Research Center, Addiction Institute, Mazandaran University of Medical Sciences, Sari, Iran; Adjunct Research Fellow, Flinders University, Adelaide, Australia.
| | - Pooneh Dadashian
- Student Research Committee, School of Nursing and Midwifery, Mazandaran University of Medical Sciences, Sari, Iran
| | - Paul Arbon
- Torrens Resilience Institute, Flinders University, Adelaide, Australia
| | - Mahmood Moosazadeh
- Health Sciences Research Center, Addiction Institute, Mazandaran University of Medical Sciences, Sari, Iran
| |
Collapse
|
3
|
Harrison JD, Rathfon M, Binford S, Miranda J, Oreper S, Holt B, Rogers SE. Development and evaluation of a concise nurse-driven non-pharmacological delirium reduction workflow for hospitalized patients: An interrupted time series study. Geriatr Nurs 2024; 55:6-13. [PMID: 37956601 PMCID: PMC10955602 DOI: 10.1016/j.gerinurse.2023.10.007] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/08/2023] [Revised: 10/09/2023] [Accepted: 10/11/2023] [Indexed: 11/15/2023]
Abstract
We created a concise nurse-driven delirium reduction workflow with the aim of reducing delirium rates and length of stay for hospitalized adults. Our nurse-driven workflow included five evidence-based daytime "sunrise" interventions (patient room lights on, blinds up, mobilization/out-of-bed, water within patient's reach and patient awake) and five nighttime "turndown" interventions (patient room lights off, blinds down, television off, noise reduction and pre-set bedtime). Interventions were also chosen because fidelity could be quickly monitored twice daily without patient interruption from outside the room. To evaluate the workflow, we used an interrupted time series study design between 06/01/17 and 05/30/22 to determine if the workflow significantly reduced the unit's delirium rate and average length of stay. Our workflow is feasible to implement and monitor and initially significantly reduced delirium rates but not length of stay. However, the reduction in delirium rates were not sustained following the emergence of the COVID-19 pandemic.
Collapse
Affiliation(s)
- James D Harrison
- Division of Hospital Medicine, University of California San Francisco, San Francisco, CA, USA.
| | - Megan Rathfon
- Division of Geriatrics, University of California San Francisco, San Francisco, CA, USA
| | - Sasha Binford
- Center for Nursing Excellence and Innovation, University of California San Francisco Medical Center, San Francisco, CA, USA; School of Nursing, University of California San Francisco, San Francisco, CA, USA
| | | | - Sandra Oreper
- Division of Hospital Medicine, University of California San Francisco, San Francisco, CA, USA
| | - Brian Holt
- Continuous Improvement Department, University of California Medical Center, San Francisco, CA, USA
| | - Stephanie E Rogers
- Division of Geriatrics, University of California San Francisco, San Francisco, CA, USA
| |
Collapse
|
4
|
Trabert J, Schenk A, Golbach R, Püllen R, Schütze S. Family-centered delirium prevention and treatment using video calls: the FACE Delirium trial. Eur Geriatr Med 2023; 14:1353-1357. [PMID: 37647011 PMCID: PMC10754740 DOI: 10.1007/s41999-023-00854-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/09/2022] [Accepted: 08/14/2023] [Indexed: 09/01/2023]
Abstract
PURPOSE In the FACE Delirium trial, we investigated the feasibility of a structured FAmily-CEntered delirium prevention and treatment during the corona pandemic. METHODS Patients hospitalized in a German geriatric medicine department were included in this single-center, prospective, single-arm feasibility study. Their relatives received a short training on delirium and volunteers or paid staff members facilitated video calls. The primary endpoint was reached when contact between patients and their relatives occurred on ≥ 80% of treatment days, either via video call or visit. RESULTS 38 patients were included (age 83.0 ± 5.9 years; 73.7% women). 76.3% reached the primary endpoint. Due to the pandemic, 99.3% of the contacts were video calls with a duration of 24.8 ± 16.3 min. CONCLUSION Family-centered delirium prevention and treatment using video calls is feasible among hospitalized geriatric patients. Daily implementation in clinical practice poses challenges and requires motivated and qualified staff.
Collapse
Affiliation(s)
- Johannes Trabert
- Department of Geriatric Medicine, AGAPLESION Markus Hospital, Wilhelm-Epstein-Strasse 4, 60431, Frankfurt, Germany.
| | - Andreas Schenk
- Department of Geriatric Medicine, AGAPLESION Markus Hospital, Wilhelm-Epstein-Strasse 4, 60431, Frankfurt, Germany
| | - Rejane Golbach
- Institute for Biostatistics and Mathematic Modelling, Faculty of Medicine, Goethe-University, Frankfurt, Germany
| | - Rupert Püllen
- Department of Geriatric Medicine, AGAPLESION Markus Hospital, Wilhelm-Epstein-Strasse 4, 60431, Frankfurt, Germany
| | - Sandra Schütze
- Department of Geriatric Medicine, AGAPLESION Markus Hospital, Wilhelm-Epstein-Strasse 4, 60431, Frankfurt, Germany
| |
Collapse
|
5
|
Zhao Q, Liu S, Zhao H, Dong L, Zhu X, Liu J. Non-pharmacological interventions to prevent and treat delirium in older people: An overview of systematic reviews. Int J Nurs Stud 2023; 148:104584. [PMID: 37826889 DOI: 10.1016/j.ijnurstu.2023.104584] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/11/2023] [Revised: 07/30/2023] [Accepted: 08/02/2023] [Indexed: 10/14/2023]
Abstract
BACKGROUND As advanced age is a major risk factor for confusion status, delirium has become prevalent in the older population, contributing to longer hospital stays, cognitive impairment, and higher risks of complications and mortality. Compared with pharmacological methods, non-pharmacological interventions are preferred and are recommended by the National Institute for Health and Care Excellence for the prevention of delirium. Numerous systematic reviews and meta-analyses have been carried out to investigate the effects of non-pharmacological interventions. However, the outcomes were diverse and the quality varied widely, making it challenging to draw firm conclusions from the evidence. OBJECTIVE To summarize the contents and evaluate the effects of non-pharmacological interventions to prevent and treat delirium among older people. DESIGN Overview of systematic reviews. METHODS A comprehensive literature search was conducted in Medline, Cochrane Library, EMBASE, CINAHL, PsycINFO, JBI EBP Database, China's SinoMed, CNKI, and Wangfang databases from inception to 2nd December 2022. Two reviewers performed the study selection, quality appraisal, and data extraction independently. The AMSTAR 2 tool was used to appraise the methodological quality of eligible reviews. The results were presented in narrative synthesis based on types of intervention, including multicomponent and single-component interventions. RESULTS Twenty-four systematic reviews were included in this overview, of which four reviews were of high quality. Multicomponent interventions were the most widely disseminated non-pharmacological strategy, which were effective in preventing delirium with 27 %-54 % reduction in delirium incidence. Additionally, the multicomponent strategy also reduced the incidence of falls and pressure ulcers, and showed trends toward shortening the length of stay and improving cognitive function. Among single-component interventions, physical training, geriatric risk assessment, and reorientation protocol revealed positive effects in delirium prevention. However, the effectiveness of non-pharmacological interventions for treating delirium was limited, and while multicomponent methods had inconsistent impacts on the duration and severity of delirium, single-component methods showed no significant impact. CONCLUSION Non-pharmacological interventions are effective in reducing the incidence of delirium and improving other health outcomes among older patients. However, the effects on the duration and severity of delirium need more evidence to confirm. REGISTRATION NUMBER CRD42022376651 in PROSPERO.
Collapse
Affiliation(s)
- Qin Zhao
- Nursing Department, The Third Xiangya Hospital of Central South University, Changsha, China; Xiangya Nursing School, Central South University, Changsha, China
| | - Shan Liu
- College of Nursing and Public Health, Adelphi University 1 South Ave., Garden City, NY, USA
| | - Hongyu Zhao
- Xiangya Nursing School, Central South University, Changsha, China
| | - Lei Dong
- Xiangya Nursing School, Central South University, Changsha, China
| | - Xiao Zhu
- Nursing Department, The Third Xiangya Hospital of Central South University, Changsha, China; Xiangya Nursing School, Central South University, Changsha, China; Research Center of Chinese Health Ministry on Transplantation Medicine Engineering and Technology, Changsha, China
| | - Jia Liu
- Nursing Department, The Third Xiangya Hospital of Central South University, Changsha, China; Xiangya Nursing School, Central South University, Changsha, China; Research Center of Chinese Health Ministry on Transplantation Medicine Engineering and Technology, Changsha, China.
| |
Collapse
|
6
|
Hata M, Miyazaki Y, Nagata C, Masuda H, Wada T, Takahashi S, Ishii R, Miyagawa S, Ikeda M, Ueno T. Predicting postoperative delirium after cardiovascular surgeries from preoperative portable electroencephalography oscillations. Front Psychiatry 2023; 14:1287607. [PMID: 38034919 PMCID: PMC10682064 DOI: 10.3389/fpsyt.2023.1287607] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/04/2023] [Accepted: 10/23/2023] [Indexed: 12/02/2023] Open
Abstract
Introduction Postoperative delirium (POD) is common and life-threatening, however, with intensive interventions, a potentially preventable clinical syndrome. Although electroencephalography (EEG) is a promising biomarker of delirium, standard 20-leads EEG holds difficulties for screening usage in clinical practice. Objective We aimed to develop an accurate algorithm to predict POD using EEG data obtained from portable device. Methods We recruited 128 patients who underwent scheduled cardiovascular surgery. Cognitive function assessments were conducted, and portable EEG recordings were obtained prior to surgery. Results Among the patients, 47 (36.7%) patients with POD were identified and they did not significantly differ from patients without POD in sex ratio, age, cognitive function, or treatment duration of intensive care unit. However, significant differences were observed in the preoperative EEG power spectrum densities at various frequencies, especially gamma activity, between patients with and without POD. POD was successfully predicted using preoperative EEG data with a machine learning algorithm, yielding accuracy of 86% and area under the receiver operating characteristic curve of 0.93. Discussion This study provides new insights into the objective and biological vulnerability to delirium. The developed algorithm can be applied in general hospitals without advanced equipment and expertise, thereby enabling the reduction of POD occurrences with intensive interventions for high-risk patients.
Collapse
Affiliation(s)
- Masahiro Hata
- Department of Psychiatry, Osaka University Graduate School of Medicine, Osaka, Japan
| | - Yuki Miyazaki
- Department of Psychiatry, Osaka University Graduate School of Medicine, Osaka, Japan
| | - Chie Nagata
- Division of Health Sciences, Osaka University Graduate School of Medicine, Osaka, Japan
| | - Hirotada Masuda
- Department of Cardiovascular Surgery, Osaka University Graduate School of Medicine, Osaka, Japan
| | - Tamiki Wada
- Department of Psychiatry, Osaka University Graduate School of Medicine, Osaka, Japan
| | - Shun Takahashi
- Department of Psychiatry, Osaka University Graduate School of Medicine, Osaka, Japan
- Department of Occupational Therapy, Graduate School of Rehabilitation Science, Osaka Metropolitan University, Osaka, Japan
- Clinical Research and Education Center, Asakayama General Hospital, Osaka, Japan
- Department of Neuropsychiatry, Wakayama Medical University, Wakayama, Japan
| | - Ryouhei Ishii
- Department of Psychiatry, Osaka University Graduate School of Medicine, Osaka, Japan
- Department of Occupational Therapy, Graduate School of Rehabilitation Science, Osaka Metropolitan University, Osaka, Japan
| | - Shigeru Miyagawa
- Department of Cardiovascular Surgery, Osaka University Graduate School of Medicine, Osaka, Japan
| | - Manabu Ikeda
- Department of Psychiatry, Osaka University Graduate School of Medicine, Osaka, Japan
| | - Takayoshi Ueno
- Division of Health Sciences, Osaka University Graduate School of Medicine, Osaka, Japan
- Department of Cardiovascular Surgery, Osaka University Graduate School of Medicine, Osaka, Japan
| |
Collapse
|
7
|
Sabbe K, Van Der Mast R, Van Rompaey B. Delirium in Home Care: A Case Report. Cureus 2023; 15:e47094. [PMID: 38021756 PMCID: PMC10646439 DOI: 10.7759/cureus.47094] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 10/15/2023] [Indexed: 12/01/2023] Open
Abstract
Delirium is a challenging medical problem, particularly in the home care setting, and greatly affects both patients and family caregivers. When delirium is not immediately detected and effectively managed, various outcomes are adversely affected. This report describes delirium in an older home-bound man and offers strategies for detecting and managing delirium in a home care setting. The patient is a frail 86-year-old man with multiple medical comorbidities and functional decline after bronchitis that was diagnosed by a general practitioner. Following the diagnosis and subsequent treatment of bronchitis, the patient suffered a major decline in cognitive and physical functioning during normal daily activities. Medical screening revealed confusion, apathy, and extreme fatigue. Using the assessment tool of the Functional Independence Measures and Delirium Observation Screening Scale (DOSS), the presence of functional decline and delirious symptoms were found. Through multidisciplinary collaboration, a treatment plan was initiated. It consisted of hydration following a fixed schedule, adapted nutrition, a temporary adapted medication schedule for pre-diabetes, and an exercise plan. No specific pharmaceuticals were given. The patient made a full recovery over time. All professional and informal caregivers should be aware of the potential presence of delirium when an older patient with a deteriorating physical or mental condition presents itself. Good diagnostics for delirium and possible underlying diseases are necessary. Adequate treatment, with the help of paramedics such as dieticians, physiotherapists, etc. must be provided when necessary.
Collapse
Affiliation(s)
- Kelly Sabbe
- Medicine and Health Sciences, University of Antwerp, Antwerp, BEL
| | - Roos Van Der Mast
- Psychiatry and Behavioral Sciences, University of Leiden, Leiden, NLD
| | - Bart Van Rompaey
- Family Medicine and Population Health, University of Antwerp, Antwerp, BEL
| |
Collapse
|
8
|
Kiliç G, Kav S. Effect of using eye masks and earplugs in preventing delirium in intensive care patients: A single-blinded, randomized, controlled trial. Nurs Crit Care 2023; 28:698-708. [PMID: 37138379 DOI: 10.1111/nicc.12901] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/30/2022] [Revised: 03/05/2023] [Accepted: 03/13/2023] [Indexed: 05/05/2023]
Abstract
BACKGROUND Delirium, which is frequently encountered in intensive care patients, can be prevented with multicomponent nursing interventions, and thus the negative consequences can be reduced. AIM To examine the effect of using eye masks and earplugs in preventing delirium in intensive care units (ICUs). STUDY DESIGN A randomized, controlled, single-blind intervention study. This study was conducted in the medical and surgical ICUs of a tertiary hospital, and nurses were given pre-study training on delirium risks, diagnosis, prevention, and management. Data were collected using the patient information form, the Nursing Delirium Screening Scale, the Richard-Campbell Sleep Scale, and the daily follow-up form. Various environmental modifications were made in the ICUs for all patients, and evidence-based nonpharmacological nursing interventions were applied to the patients in both groups during the day and night shifts for 3 days. In addition, the patients in the intervention group were provided with eye masks and earplugs for three nights. RESULTS The study included a total of 60 patients (30 in the intervention group and 30 in the control group). There was a statistically significant difference in the development of delirium between the intervention and control groups (night of the 2nd day, p = .019; day of the 3rd day p < .001; night of the 3rd day p ≤ .001). The average total sleep quality score of the intervention group was found to be significantly higher than the control group (p ≤ .001 for three nights). Staying in the internal medicine ICU affected (odds ratio [OR], 11.84; 95% confidence interval [CI], 3.00-46.66; p = .017) more on the development of delirium than in coronary ICU, being in the age group of 65 and over, having a hearing impairment, coming to ICU from the operating room, and education level had an effect. CONCLUSIONS The earplugs and eye masks used by the intensive care patients overnight were found to be effective in increasing sleep quality and preventing delirium. RELEVANCE TO CLINICAL PRACTICE The use of eye masks and earplugs is recommended for ICUs in preventing delirium.
Collapse
Affiliation(s)
- Gülşen Kiliç
- Baskent University Ankara Hospital, Internal Medicine Intensive Care Unit, Ankara, Turkey
| | - Sultan Kav
- Baskent University, Faculty of Health Sciences, Department of Nursing, Ankara, Turkey
| |
Collapse
|
9
|
Wueest AS, Berres M, Bettex DA, Steiner LA, Monsch AU, Goettel N. Independent External Validation of a Preoperative Prediction Model for Delirium After Cardiac Surgery: A Prospective Observational Cohort Study. J Cardiothorac Vasc Anesth 2023; 37:415-422. [PMID: 36567220 DOI: 10.1053/j.jvca.2022.11.038] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/19/2022] [Revised: 11/09/2022] [Accepted: 11/30/2022] [Indexed: 12/12/2022]
Abstract
OBJECTIVE This investigation provided independent external validation of an existing preoperative risk prediction model. DESIGN A prospective observational cohort study of patients undergoing cardiac surgery covering the period between April 16, 2018 and January 18, 2022. SETTING Two academic hospitals in Switzerland. PARTICIPANTS Adult patients (≥60 years of age) who underwent elective cardiac surgery, including coronary artery bypass graft, mitral or aortic valve replacement or repair, and combined procedures. INTERVENTIONS None. MEASUREMENTS AND MAIN RESULTS The primary outcome measure was the incidence of postoperative delirium (POD) in the intensive or intermediate care unit, diagnosed using the Intensive Care Delirium Screening Checklist. The prediction model contained 4 preoperative risk factors to which the following points were assigned: Mini-Mental State Examination (MMSE) score ≤23 received 2 points; MMSE 24-27, Geriatric Depression Scale (GDS) >4, prior stroke and/or transient ischemic attack (TIA), and abnormal serum albumin (≤3.5 or ≥4.5 g/dL) received 1 point each. The missing data were handled using multiple imputation. In total, 348 patients were included in the study. Sixty patients (17.4%) developed POD. For point levels in the prediction model of 0, 1, 2, and ≥3, the cumulative incidence of POD was 12.6%, 22.8%, 25.8%, and 35%, respectively. The validation resulted in a pooled area under the receiver operating characteristics curve of 0.60 (median CI, 0.525-0.679). CONCLUSIONS The evaluated predictive model for delirium after cardiac surgery in this patient cohort showed only poor discriminative capacity but fair calibration.
Collapse
Affiliation(s)
- Alexandra S Wueest
- Memory Clinic, University Department of Geriatric Medicine FELIX PLATTER, Basel, Switzerland; Clinic for Anaesthesia, Intermediate Care, Prehospital Emergency Medicine and Pain Therapy, University Hospital Basel, Basel, Switzerland
| | - Manfred Berres
- Department of Mathematics and Technology, University of Applied Sciences Koblenz, Germany
| | - Dominique A Bettex
- Division of Cardiovascular Anaesthesia, Institute of Anaesthesia, University Hospital Zurich, Zurich, Switzerland
| | - Luzius A Steiner
- Clinic for Anaesthesia, Intermediate Care, Prehospital Emergency Medicine and Pain Therapy, University Hospital Basel, Basel, Switzerland; Department of Clinical Research University of Basel, Basel, Switzerland
| | - Andreas U Monsch
- Memory Clinic, University Department of Geriatric Medicine FELIX PLATTER, Basel, Switzerland
| | - Nicolai Goettel
- Department of Clinical Research University of Basel, Basel, Switzerland; Department of Anaesthesiology, University of Florida College of Medicine, Gainesville, FL, USA.
| |
Collapse
|
10
|
Liu Y, Shen W, Tian Z. Using Machine Learning Algorithms to Predict High-Risk Factors for Postoperative Delirium in Elderly Patients. Clin Interv Aging 2023; 18:157-168. [PMID: 36789284 PMCID: PMC9922512 DOI: 10.2147/cia.s398314] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/26/2022] [Accepted: 01/30/2023] [Indexed: 02/10/2023] Open
Abstract
Purpose Postoperative delirium (POD) is a common postoperative complication in elderly patients, and it greatly affects the short-term and long-term prognosis of patients. The purpose of this study was to develop a machine learning model to identify preoperative, intraoperative and postoperative high-risk factors and predict the occurrence of delirium after nonbrain surgery in elderly patients. Patients and Methods A total of 950 elderly patients were included in the study, including 132 patients with POD. We collected 30 characteristic variables, including patient demographic characteristics, basic medical history, preoperative examination characteristics, type of surgery, and intraoperative information. Three machine learning algorithms, multilayer perceptron (MLP), extreme gradient boosting (XGBoost), and k-nearest neighbor algorithm (KNN), were applied to construct the model, and the k-fold cross-validation method, ROC curve, calibration curve, decision curve analysis (DCA) and external validation were used for model evaluation. Results XGBoost showed the best performance among the three prediction models. The ROC curve results showed that XGBoost had a high area under the curve (AUC) value of 0.982 in the training set; the AUC value in the validation set was 0.924, and the prediction model was highly accurate. The k-fold cross-validation method was used for internal validation, and the XGBoost model was stable The calibration curve showed high predictive power of the XGBoost model. The DCA curve showed a higher benefit rate for patients who received interventional treatment under the XGBoost model. The AUC value for the external validation set was 0.88, indicating that the predictive model was extrapolative. Conclusion The prediction model of POD derived from the machine learning algorithm in this study has high prediction accuracy and clinical utility, which is beneficial for clinicians to diagnose and treat patients in a timely manner.
Collapse
Affiliation(s)
- Yuan Liu
- Department of General Surgery, The Affiliated Wuxi People’s Hospital of Nanjing Medical University, Wuxi, People’s Republic of China
| | - Wei Shen
- Department of General Surgery, The Affiliated Wuxi People’s Hospital of Nanjing Medical University, Wuxi, People’s Republic of China,Correspondence: Wei Shen, Department of General Surgery, The Affiliated Wuxi People’s Hospital of Nanjing Medical University, Wuxi, People’s Republic of China, Tel +86 13385110723, Email
| | - Zhiqiang Tian
- Department of General Surgery, The Affiliated Wuxi People’s Hospital of Nanjing Medical University, Wuxi, People’s Republic of China
| |
Collapse
|
11
|
Wong CK, van Munster BC, Hatseras A, Huis In 't Veld E, van Leeuwen BL, de Rooij SE, Pleijhuis RG. Head-to-head comparison of 14 prediction models for postoperative delirium in elderly non-ICU patients: an external validation study. BMJ Open 2022; 12:e054023. [PMID: 35396283 PMCID: PMC8996014 DOI: 10.1136/bmjopen-2021-054023] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/23/2022] Open
Abstract
OBJECTIVES Delirium is associated with increased morbidity, mortality, prolonged hospitalisation and increased healthcare costs. The number of clinical prediction models (CPM) to predict postoperative delirium has increased exponentially. Our goal is to perform a head-to-head comparison of CPMs predicting postoperative delirium in non-intensive care unit (non-ICU) elderly patients to identify the best performing models. SETTING Single-site university hospital. DESIGN Secondary analysis of prospective cohort study. PARTICIPANTS AND INCLUSION CPMs published within the timeframe of 1 January 1990 to 1 May 2020 were checked for eligibility (Preferred Reporting Items for Systematic Reviews and Meta-Analyses). For the time period of 1 January 1990 to 1 January 2017, included CPMs were identified in systematic reviews based on prespecified inclusion and exclusion criteria. An extended literature search for original studies was performed independently by two authors, including CPMs published between 1 January 2017 and 1 May 2020. External validation was performed using a surgical cohort consisting of 292 elderly non-ICU patients. PRIMARY OUTCOME MEASURES Discrimination, calibration and clinical usefulness. RESULTS 14 CPMs were eligible for analysis out of 366 full texts reviewed. External validation was previously published for 8/14 (57%) CPMs. C-indices ranged from 0.52 to 0.74, intercepts from -0.02 to 0.34, slopes from -0.74 to 1.96 and scaled Brier from -1.29 to 0.088. Based on predefined criteria, the two best performing models were those of Dai et al (c-index: 0.739; (95% CI: 0.664 to 0.813); intercept: -0.018; slope: 1.96; scaled Brier: 0.049) and Litaker et al (c-index: 0.706 (95% CI: 0.590 to 0.823); intercept: -0.015; slope: 0.995; scaled Brier: 0.088). For the remaining CPMs, model discrimination was considered poor with corresponding c-indices <0.70. CONCLUSION Our head-to-head analysis identified 2 out of 14 CPMs as best-performing models with a fair discrimination and acceptable calibration. Based on our findings, these models might assist physicians in postoperative delirium risk estimation and patient selection for preventive measures.
Collapse
Affiliation(s)
- Chung Kwan Wong
- Department of Geriatrics, University of Groningen, University Medical Center Groningen, Groningen, The Netherlands
| | - Barbara C van Munster
- Department of Geriatrics, University of Groningen, University Medical Center Groningen, Groningen, The Netherlands
| | - Athanasios Hatseras
- Department of Geriatrics, University of Groningen, University Medical Center Groningen, Groningen, The Netherlands
| | - Else Huis In 't Veld
- Department of Geriatrics, University of Groningen, University Medical Center Groningen, Groningen, The Netherlands
| | - Barbara L van Leeuwen
- Department of Surgery, University of Groningen, University Medical Center Groningen, Groningen, The Netherlands
| | - Sophia E de Rooij
- Department of Geriatrics, University of Groningen, University Medical Center Groningen, Groningen, The Netherlands
| | - Rick G Pleijhuis
- Department of Internal Medicine, University of Groningen, University Medical Center Groningen, Groningen, The Netherlands
| |
Collapse
|
12
|
O'Hanlon S, Baxter M, Hosie A. Postoperative delirium in older patients with cancer: the role of psychological distress and social support. Curr Opin Support Palliat Care 2022; 16:38-47. [PMID: 34939608 DOI: 10.1097/spc.0000000000000588] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
Abstract
PURPOSE OF REVIEW Delirium is a common and important adverse event in the perioperative period. Older people with cancer are at significant risk, and outcomes are poor. There is increasing awareness of the effect of psychological distress and social support on pathogenesis and outcomes of delirium in this setting. This review aimed to describe recent research in this evolving area. RECENT FINDINGS Across six recent studies of postoperative delirium in older people with cancer, delirium incidence ranged from 8 to 19.8%. Poor social support and high levels of distress are implicated in the development of postoperative delirium. Distress can be related to negative emotional reaction to diagnosis, preconception of cancer diagnosis and interactions with the healthcare system. Prevention of delirium is key, and multicomponent interventions show evidence of effectiveness. 'Emotional distress' has been included in a new core outcome set for studies of interventions to prevent and/or treat delirium. SUMMARY Postoperative delirium in older adults with cancer is common and is associated with increased morbidity and mortality. Psychological distress and social support play an important role, but there are many unmet research needs in this area.
Collapse
Affiliation(s)
- Shane O'Hanlon
- Department of Geriatric Medicine, St Vincent's University Hospital
- University College Dublin, Dublin, Ireland
| | - Mark Baxter
- Division of Molecular and Clinical Medicine, School of Medicine, University of Dundee
- Tayside Cancer Centre, Ninewells Hospital, NHS Tayside, Dundee, UK
| | - Annmarie Hosie
- School of Nursing and Midwifery, Sydney, The University of Notre Dame Australia
- St Vincent's Health Network Sydney, Darlinghurst
- IMPACCT - Improving Palliative, Aged and Chronic Care through Research and Translation, University of Technology Sydney, Ultimo, New South Wales, Australia
| |
Collapse
|
13
|
Abstract
PURPOSE OF REVIEW Postoperative delirium (POD) is one of the most severe complications after surgery.The consequences are dramatic: longer hospitalization, a doubling of mortality and almost all cases develop permanent, yet subtle, cognitive deficits specific to everyday life. Actually, no global guideline with standardized concepts of management exists. Advances in prevention, diagnosis and treatment can improve recognition and risk stratification of delirium and its consequences. RECENT FINDINGS Management of POD is a multiprofessional approach and consists of different parts: First, the detection of high-risk patients with a validated tool, preventive nonpharmacological concepts and an intraoperative anesthetic management plan that is individualized to the older patient (e.g. avoiding large swings in blood pressure, vigilance in maintaining normothermia, ensuring adequate analgesia and monitoring of anesthetic depth). In addition to preventive standards, treatment and diagnostic concepts must also be available, both pharmaceutical and nonpharmacological. SUMMARY Not every POD can be prevented. It is important to detect patients with high risk for POD and have standardized concepts of management. The most important predisposing risk factors are a higher age, preexisting cognitive deficits, multimorbidity and an associated prodelirious polypharmacy. In view of demographic change, the implementation of multidisciplinary approaches to pharmacological and nonpharmacological POD management is highly recommended.
Collapse
|
14
|
Friedman JI, Li L, Kirpalani S, Zhong X, Freeman R, Cheng YT, Alfonso FL, McAlpine G, Vakil A, Macon B, Francaviglia P, Cassara M, LoPachin V, Reina K, Davis K, Reich D, Craven CK, Mazumdar M, Siu AL. A Multi-Phase Quality Improvement Initiative for the Treatment of Active Delirium in Older Persons. J Am Geriatr Soc 2020; 69:216-224. [PMID: 33150615 DOI: 10.1111/jgs.16897] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/07/2020] [Revised: 09/22/2020] [Accepted: 09/26/2020] [Indexed: 12/01/2022]
Abstract
BACKGROUND/OBJECTIVES The Hospital Elder Life Program emerged 20 years ago as the reference model for delirium prevention in hospitalized older patients. However, implementation has been achieved at only 200 hospitals worldwide over the last 20 years. Among the barriers to implementation for some institutions is an unwillingness of hospital administration to assume the costs associated with implementing programs that service all hospitalized older patients at risk for delirium. Facing such a situation, we implemented a unique and self-evolving model of care of older hospitalized patients who had already developed delirium. DESIGN Hypothesis testing was carried out using a pretest-posttest design on program administrative data. SETTING Mount Sinai Hospital, New York, NY, a tertiary-care teaching facility. PARTICIPANTS A total of 9,214 consecutively admitted older patients to non-intensive care (ICU) inpatient units over a 5.5-year period, regardless of the suspected presence of delirium or risk status for developing delirium. INTERVENTION A delirium intervention program targeting patients in whom delirium has already developed, with a modified delirium team supported by extensive workflow automation with custom tools in our electronic medical records system. MEASUREMENTS Length of stay (LOS) for delirious and non-delirious patients on units where this program was piloted. Benzodiazepine, opiate, and antipsychotic use on the same units. RESULTS There was a significant drop in LOS by 1.98 days (95% confidence interval = .24-3.71), a decrease in the average morphine dose equivalents administered from .38 mg to .21 mg per patient hospital day, diazepam dose equivalents from .22 mg to .15 mg per patient hospital day, and quetiapine administered from .17 mg to .14 mg per patient hospital day for delirious patients on the program pilot units. CONCLUSION Elements of our unique active delirium treatment program may provide some direction to other program developers working on improving the care of older hospitalized delirious patients. However, the supporting evidence presented is limited, and a more rigorous prospective study is needed.
Collapse
Affiliation(s)
- Joseph I Friedman
- Department of Psychiatry, Icahn School of Medicine at Mount Sinai, New York, New York.,Department of Neuroscience, Icahn School of Medicine at Mount Sinai, New York, New York
| | - Lihua Li
- Population Health Science and Policy, Icahn School of Medicine at Mount Sinai, New York, New York.,Institute for Health Care Delivery Science, Icahn School of Medicine at Mount Sinai, New York, New York, 10029
| | | | - Xiaobo Zhong
- Population Health Science and Policy, Icahn School of Medicine at Mount Sinai, New York, New York.,Institute for Health Care Delivery Science, Icahn School of Medicine at Mount Sinai, New York, New York, 10029
| | - Robert Freeman
- Clinical Operations, Mount Sinai Hospital, New York, New York
| | - Yim Tan Cheng
- EPIC Clinical Transformation Group, Mount Sinai Health System, New York, New York
| | - Francis L Alfonso
- EPIC Clinical Transformation Group, Mount Sinai Health System, New York, New York
| | - George McAlpine
- EPIC Clinical Transformation Group, Mount Sinai Health System, New York, New York
| | - Aditi Vakil
- EPIC Clinical Transformation Group, Mount Sinai Health System, New York, New York
| | - Bernard Macon
- EPIC Clinical Transformation Group, Mount Sinai Health System, New York, New York
| | - Paul Francaviglia
- EPIC Clinical Transformation Group, Mount Sinai Health System, New York, New York
| | - Margherita Cassara
- EPIC Clinical Transformation Group, Mount Sinai Health System, New York, New York
| | - Vicki LoPachin
- Division of General Internal Medicine, Icahn School of Medicine at Mount Sinai, New York, New York
| | - Katherine Reina
- Department of Nursing, Mount Sinai Hospital, New York, New York
| | - Kenneth Davis
- Department of Psychiatry, Icahn School of Medicine at Mount Sinai, New York, New York.,President's Office, Mount Sinai Health System, New York, New York
| | - David Reich
- Department of Anesthesiology, Icahn School of Medicine at Mount Sinai, New York, New York
| | - Catherine K Craven
- Population Health Science and Policy, Icahn School of Medicine at Mount Sinai, New York, New York
| | - Madhu Mazumdar
- Population Health Science and Policy, Icahn School of Medicine at Mount Sinai, New York, New York.,Institute for Health Care Delivery Science, Icahn School of Medicine at Mount Sinai, New York, New York, 10029
| | - Albert L Siu
- Population Health Science and Policy, Icahn School of Medicine at Mount Sinai, New York, New York.,Geriatrics and Palliative Medicine, Icahn School of Medicine at Mount Sinai, New York, New York.,Department of Medicine, Icahn School of Medicine at Mount Sinai, New York, New York
| |
Collapse
|
15
|
Liang CK, Chu CS, Hsu YH, Chou MY, Wang YC, Lin YT, Renn JH, Liu TY, Yang CC. Effects of modified version of the Hospital Elder Life Program on post-discharge cognitive function and activities of daily living among older adults undergoing total knee arthroplasty. Arch Gerontol Geriatr 2020; 93:104284. [PMID: 33157357 DOI: 10.1016/j.archger.2020.104284] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/08/2020] [Revised: 10/13/2020] [Accepted: 10/15/2020] [Indexed: 12/14/2022]
Abstract
OBJECTIVES This study aimed to investigate the effects of a modified Hospital Elder Life Program (mHELP) on post-discharge cognition and physical function among older adults undergoing total knee arthroplasty (TKA), and to evaluate the incidence of postoperative delirium. DESIGN Non-randomized intervention trial. SETTING AND PARTICIPANTS A total of 140 patients aged 60 years and older scheduled for elective orthopedic surgery at our institution between August 2017 and December 2018 were included. METHODS Ward-level stratification was used with one surgical ward receiving mHELP (intervention group), including orientation communication, early mobilization, vision/hearing impairment equipment, and dehydration prevention, and another ward providing usual care (control group). All participants were assigned to two surgical wards. Outcome measures were collected using MMSE telephone version (tMMSE), activities of daily living (ADL) and instrumental activities of daily living (IADL) instruments at 1, 6, and 12 months after discharge. Multiple linear regression analysis was used to measure effects of mHELP intervention on mean differences in tMMSE, ADL and IADL scores from baseline to 1-, 6- and 12-months. RESULTS Effects of mHELP intervention significantly preserved cognitive function at 1 and 12 months, but not at 6 months, compared with controls, regardless of adjustments for confounders. However, no intervention effects were noted in ADL and IADL scores. Postoperative delirium in the whole cohort was 3.6 % (2.5 % in intervention group, 5.1 % in control group, P = 0.41). CONCLUSIONS mHELP intervention preserves post-discharge cognitive function, but has no notable effect on ADL and IADL function in older adults undergoing elective TKA surgery.
Collapse
Affiliation(s)
- Chih-Kuang Liang
- Center for Geriatrics and Gerontology, Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan; Institute of Environmental and Occupational Health Sciences, School of Medicine, National Yang Ming University, Taipei, Taiwan; Aging and Health Research Center, National Yang Ming University, Taipei, Taiwan; Division of Neurology, Department of Internal Medicine, Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan
| | - Che-Sheng Chu
- Center for Geriatrics and Gerontology, Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan; Department of Psychiatry, Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan
| | - Ying-Hsin Hsu
- Center for Geriatrics and Gerontology, Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan; Division of Neurology, Department of Internal Medicine, Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan; Chia Nan University of Pharmacy and Science, Tainan, Taiwan
| | - Ming-Yueh Chou
- Center for Geriatrics and Gerontology, Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan; Aging and Health Research Center, National Yang Ming University, Taipei, Taiwan
| | - Yu-Chun Wang
- Center for Geriatrics and Gerontology, Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan; Chia Nan University of Pharmacy and Science, Tainan, Taiwan
| | - Yu-Te Lin
- Center for Geriatrics and Gerontology, Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan; Division of Neurology, Department of Internal Medicine, Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan
| | - Jenn-Huei Renn
- Department of Orthopaedics, Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan; Department of Medical Affair Administration, Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan
| | - Tsung-Yun Liu
- Institute of Environmental and Occupational Health Sciences, School of Medicine, National Yang Ming University, Taipei, Taiwan
| | - Chen-Chang Yang
- Institute of Environmental and Occupational Health Sciences, School of Medicine, National Yang Ming University, Taipei, Taiwan; Division of Clinical Toxicology & Occupational Medicine, Department of Medicine, Taipei Veterans General Hospital, Taipei, Taiwan.
| |
Collapse
|