Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
The purpose of this study is to determine the accuracy of an AI-based tool in the prediction of postoperative delirium (POD), in a population at moderately high risk of developing this syndrome (i.e., elderly orthopedic subjects). The population to be studied has already been enrolled in a parallel study regarding the likelihood of developing delirium, its relationship to the type of anesthetic, and the relationship between anesthetic type, development of delirium and risk for post-operative cognitive impairment (including risk for dementia) (Protocol ID#55169 [David Drover-Principal investigator; José Maldonado-Co-investigator]).
Study investigators would like to determine the real-life accuracy of a new tool developed for the prediction of delirium: Pre-Interventional Preventive Risk Assessment (PIPRA) Tool. The importance of assessing the risk for post-operative delirium (POD) includes: providing clinicians and patients with accurate predictive information regarding the patient's risk for developing delirium as part of the risk/benefit calculation for surgical procedures, and thus potential risk of subsequent cognitive impairment; as well as the ability to introduce timely prophylactic techniques that may prevent its onset.
The PIPRA tools consists of nine items commonly found in any presurgical patient's electronic medical record (EMR). The tool has been designed to run in the background of the EMR and automatically calculate the patient's risk for developing delirium upon admission for surgical intervention. For our study, we will be applying the PIPRA tool to the EMR of patients already enrolled in a parallel study as detailed above.
The PIPRA tool predicts the risk of developing POD delirium based on its algorithm that takes into consideration the following nine clinical variables: age, height/weight or body mass index, the American Society of Anesthesiologist physical status Classification system (ASA), past history of delirium, past history of cognitive impairment (including dementia), number of medications, preoperative C-reactive protein levels, surgical risk (as determined by the European Society of Anesthesiology), and type of surgery. The subsequent result predicts the risk (in percentage) of a patient developing POD following surgery.
The PIPRA tool is fully integrated into EMR systems, operating in the background, extracting relevant information, and automatically generating a delirium prediction score. In addition, this software possesses the flexibility to recalibrate the delirium risk based on the availability of the nine clinical variables.
Not provided
Not provided
Not provided
Not provided
Not provided
| Measure | Description | Time Frame |
|---|---|---|
| Number of subjects with postoperative delirium accurately predicted by the PIPRA Tool | Assessment of the accuracy on the prediction of subjects identified as developing delirium by the PIPRA tool, as compared with post-operative standardized delirium assessment tools. We will compare the assessment of the PIPRA prediction tool (performed pre-op) with the actual development of delirium as assessed by a clinical assessment based on DSM; the CAM-ICU & SPTD assessment tools. | Baseline measurement of variables and detection of delirium presenting up to 72 hours post-operatively |
| Development of post-operative Delirium | Number of subjects diagnosed with post-operative delirium | Up to 72 hours post-operatively |
| Determination of Delirium Phenotype | For those who develop delirium, the phenotype of delirium will be determined as per the Liptzin-Levkoff Criteria (based on DSM diagnostic Criteria). As such, all delirium episodes will be categorized as: hyperactive, hypoactive, mixed, or subsyndromal delirium. | Up to 72 hours post-operatively. |
| Impact of delirium on post-operative cognitive impairment | Impact of delirium occurrence and emergence of cognitive impairment post-operatively | Up to 10-year post-operatively. |
| Sensitivity and specificity of the PIPRA tool for detecting postoperative delirium. | Sensitivity and specificity of various cut off points of the PIPRA tool for detecting postoperative delirium. | Baseline measurement of variables and detection of delirium presenting up to 72 hours post-operatively |
| Receiver operating characteristic (ROC) curve analysis of PIPRA tool |
| Measure | Description | Time Frame |
|---|---|---|
| Immediate Postoperative Mortality | Mortality rate immediately after index surgery | From date of post-operative admission up to time of postoperative discharge, an average of 72 hours. |
| Length of Hospital Length of Stay |
Not provided
Inclusion Criteria:
Exclusion Criteria:
Not provided
Not provided
Not provided
Stanford Hospital geriatric patients having surgery
Not provided
| Name | Affiliation | Role |
|---|---|---|
| José R Maldonado, MD | Stanford University | Principal Investigator |
| Facility | Status | City | State | ZIP | Country | Contacts |
|---|---|---|---|---|---|---|
| Stanford Medical Center | Palo Alto | California | 94304 | United States |
| PubMed Identifier | Type | Citation | Retractions |
|---|---|---|---|
| 33189147 | Result | Buchan TA, Sadeghirad B, Schmutz N, Goettel N, Foroutan F, Couban R, Mbuagbaw L, Dodsworth BT. Preoperative prognostic factors associated with postoperative delirium in older people undergoing surgery: protocol for a systematic review and individual patient data meta-analysis. Syst Rev. 2020 Nov 14;9(1):261. doi: 10.1186/s13643-020-01518-z. | |
| 37290122 |
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
| ID | Term |
|---|---|
| D003693 | Delirium |
| D000071257 | Emergence Delirium |
| D060825 | Cognitive Dysfunction |
| ID | Term |
|---|---|
| D003221 | Confusion |
| D019954 | Neurobehavioral Manifestations |
| D009461 | Neurologic Manifestations |
| D009422 | Nervous System Diseases |
Not provided
Not provided
Not provided
Not provided
Not provided
Receiver operating characteristic (ROC) curve analysis of PIPRA tool |
| Baseline measurement of variables and detection of delirium presenting up to 72 hours post-operatively |
Total number of days admitted to the hospital
| From date of post-operative admission up to time of postoperative discharge (assessed up to 1 year after admission). |
| Discharge Site | Site of discharge (e.g., home, rehabilitation, skilled nurse facility, etc) | Type of facility the patient was discharge to from the hospital (assessed up to 6 months from admission) |
| Requirement of Intensive Care Unit Admission | Need for admission to an intensive care unit due to clinical necessity or deterioration | Time to discharge from the hospital (assessed up to 6 months from admission) |
| Need of pharmacological protocol | Need of pharmacological protocol for management of delirium | From post-operative hospital admission up to time of postoperative discharge (assessed up to 6 months from admission) |
| Dodsworth BT, Reeve K, Falco L, Hueting T, Sadeghirad B, Mbuagbaw L, Goettel N, Schmutz Gelsomino N. Development and validation of an international preoperative risk assessment model for postoperative delirium. Age Ageing. 2023 Jun 1;52(6):afad086. doi: 10.1093/ageing/afad086. |
| 37819663 | Result | Sadeghirad B, Dodsworth BT, Schmutz Gelsomino N, Goettel N, Spence J, Buchan TA, Crandon HN, Baneshi MR, Pol RA, Brattinga B, Park UJ, Terashima M, Banning LBD, Van Leeuwen BL, Neerland BE, Chuan A, Martinez FT, Van Vugt JLA, Rampersaud YR, Hatakeyama S, Di Stasio E, Milisen K, Van Grootven B, van der Laan L, Thomson Mangnall L, Goodlin SJ, Lungeanu D, Denhaerynck K, Dhakharia V, Sampson EL, Zywiel MG, Falco L, Nguyen AV, Moss SJ, Krewulak KD, Jaworska N, Plotnikoff K, Kotteduwa-Jayawarden S, Sandarage R, Busse JW, Mbuagbaw L. Perioperative Factors Associated With Postoperative Delirium in Patients Undergoing Noncardiac Surgery: An Individual Patient Data Meta-Analysis. JAMA Netw Open. 2023 Oct 2;6(10):e2337239. doi: 10.1001/jamanetworkopen.2023.37239. |
| 28601132 | Result | Maldonado JR. Acute Brain Failure: Pathophysiology, Diagnosis, Management, and Sequelae of Delirium. Crit Care Clin. 2017 Jul;33(3):461-519. doi: 10.1016/j.ccc.2017.03.013. |
| 18686756 | Result | Robinson TN, Eiseman B. Postoperative delirium in the elderly: diagnosis and management. Clin Interv Aging. 2008;3(2):351-5. doi: 10.2147/cia.s2759. |
| D012816 | Signs and Symptoms |
| D013568 | Pathological Conditions, Signs and Symptoms |
| D019965 | Neurocognitive Disorders |
| D001523 | Mental Disorders |
| D011183 | Postoperative Complications |
| D010335 | Pathologic Processes |
| D003072 | Cognition Disorders |