Postoperative Sleep Disturbance in Patients Undergoing Arthroplasty: Risk Prediction Modeling Based on Logistic Regression

WANG Jing, LI Lingli, ZHAO Chunlin, YANG Xue, YUAN Linyan

Abstract

To construct a risk predictive model for postoperative sleep disturbance (PSD) in patients undergoing arthroplasty by using logistic regression.   Methods  We retrospectively collected the data of 4286 patients who underwent joint replacement surgeries at a tertiary-care hospital in Chengdu, China between January 1, 2017 and September 30, 2021. With 3001 cases in the training set and 1285 cases in the test set, we constructed the model by using a logistic regression algorithm to screen for predictors in Matlab, displaying the predicted risks of postoperative sleep disturbance with nomographs. The performance of the model was assessed by the area under the curve (AUC) of the receiver operating characteristic curve, accuracy, precision, recall, F1 value, and calibration curve.   Results   A total of 9 predictors, including post-admission preoperative sleep disturbance, ward type, body mass index, smoking status, range of diseases, joint mobility (flexion), joint mobility (extension), preoperative last hemoglobin, and type of surgery, were eventually included in the study for predictive modeling . The performance assessment findings of the predictive model were as follows, AUC value, 0.708 (95% confidence interval: 0.677-0.740), accuracy, 75.20%, precision, 65.80%, recall, 43.70%, and F1 value, 0.525. The calibration curve showed good agreement between the predicted probabilities and the actual data.   Conclusion  The model constructed in the study has good predictive efficacy and the nomographs are simple and easy to use. With this model, health workers can make preoperative prediction of the risk of PSD in arthroplasty patients based on the predictors, which facilitates early prevention and reduces the risk of postoperative sleep disturbance in patients.

 

Keywords: Machine learning.  Arthroplasty.  Postoperative sleep disturbance.  Predictive model

 

Full Text:

PDF


References


GONG L， WANG Z， FAN D. Sleep quality effects recovery after total knee arthroplasty (TKA)--a randomized, double-blind, controlled study. J Arthroplasty，2015，30(11): 1897–1901. doi: 10.1016/j.arth.2015.02.020.

AU E H， FRANCIS A， BERNIER-JEAN A， et al. Prediction modeling-part 1: regression modeling. Kidney Int，2020，97(5): 877–884. doi: 10. 1016/j.kint.2020.02.007.

DING J， GUO X， ZHANG M， et al. Development and validation of mathematical nomogram for predicting the risk of poor sleep quality among medical students. Front Neurosci，2022，16: 930617. doi: 10.3389/fnins.2022.930617.

IRISH L A， KLINE C E， GUNN H E， et al. The role of sleep hygiene in promoting public health: a review of empirical evidence. Sleep Med Rev， 2015，22: 23–36. doi: 10.1016/j.smrv.2014.10.001.

SCHOUSBOE J T， KATS A M， STONE K L， et al. Self-reported poor sleep on multiple dimensions is associated with higher total health care costs in older men. Sleep，2020，43(10): zsaa073. doi: 10.1093/sleep/zsaa073.

SIPILÄ R M， KALSO E A. Sleep well and recover faster with less pain--a narrative review on sleep in the perioperative period. J Clin Med，2021， 10(9): 2000. doi: 10.3390/jcm10092000.

MUKARTIHAL R K， ANGADI D S， MANGUKIYA H J， et al. Temporal changes in sleep quality and knee function following primary total knee arthroplasty: a prospective study. Int Orthop，2022，46(2): 223–230. doi: 10.1007/s00264-021-05192-1.

MARTINEZ R， REDDY N， MULLIGAN E P， et al. Sleep quality and nocturnal pain in patients with hip osteoarthritis. Medicine (Baltimore)， 2019，98(41): e17464. doi: 10.1097/MD.0000000000017464. KUGELMAN D N， MAHURE S A， FENG J E， et al. Total knee arthroplasty is associated with greater immediate post-surgical pain and opioid use than total hip arthroplasty. Arch Orthop Trauma Surg，2022， 142(12): 3575–3580. doi: 10.1007/s00402-021-03951-8.

LUO M， SONG B， ZHU J. Sleep disturbances after general anesthesia: current perspectives. Front Neurol，2020，11: 629. doi: 10.3389/fneur. 2020.00629.

CANFIELD M J， CREMINS M S， VELLANKY S S， et al. Evaluating the success of perioperative self-guided meditation in reducing sleep disturbance after total knee arthroplasty. J Arthroplasty，2021，36(7S): S215–S220.e2. doi: 10.1016/j.arth.2021.01.070.

WYLDE V， ROOKER J， HALLIDAY L， et al. Acute postoperative pain at rest after hip and knee arthroplasty: severity, sensory qualities and impact on sleep. Orthop Traumatol Surg Res，2011，97(2): 139–144. doi: 10.1016/j.otsr.2010.12.003.

FINAN P H， GOODIN B R， SMITH M T. The association of sleep and pain: an update and a path forward. J Pain，2013，14(12): 1539–1552. doi: 10.1016/j.jpain.2013.08.007.

YAO Z W， ZHAO B C， YANG X， et al. Relationships of sleep disturbance, intestinal microbiota, and postoperative pain in breast cancer patients: a prospective observational study. Sleep Breath，2021，25(3): 1655–1664. doi: 10.1007/s11325-020-02246-3.

DELANEY L J， CURRIE M J， HUANG H C， et al. "They can rest at home": an observational study of patients' quality of sleep in an Australian hospital. BMC Health Serv Res，2018，18(1): 524. doi: 10.1186/s12913-018-3201-z.

MUKKA S， ROLFSON O， MOHADDES M， et al. The effect of body mass index class on patient-reported health-related quality of life before and after total hip arthroplasty for osteoarthritis: registry-based cohort study of 64, 055 patients. JB JS Open Access，2020，5(4): e20.00100. doi: 10.2106/JBJS.OA.20.00100.

KWON H M， HAN C D， YANG I H， et al. Being underweight is associated with worse surgical outcomes of total knee arthroplasty compared to normal body mass index in elderly patients. Orthop Res Rev，2020，12: 53–60. doi: 10.2147/ORR.S243444.

LIAO Y， XIE L， CHEN X， et al. Sleep quality in cigarette smokers and nonsmokers: findings from the general population in central China. BMC Public Health，2019，19(1): 808. doi: 10.1186/s12889-019-6929-4.

YANG M M H， HARTLEY R L， LEUNG A A， et al. Preoperative predictors of poor acute postoperative pain control: a systematic review and meta-analysis. BMJ Open，2019，9(4): e025091. doi: 10.1136/bmjopen-2018-025091.


Refbacks

  • There are currently no refbacks.