scholarly journals Development and internal validation of an algorithm to predict intraoperative risk of inadvertent hypothermia based on preoperative data

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
C. Wallisch ◽  
S. Zeiner ◽  
P. Scholten ◽  
C. Dibiasi ◽  
O. Kimberger
Keyword(s):  
At Risk ◽  
Minimum Temperature ◽  
Prediction Models ◽  
Predictive Performance ◽  
Moderate Hypothermia ◽  
Probabilistic Prediction ◽  
Forward Selection ◽  
Perioperative Morbidity ◽  
Intraoperative Hypothermia ◽  
Patients At Risk

AbstractIntraoperative hypothermia increases perioperative morbidity and identifying patients at risk preoperatively is challenging. The aim of this study was to develop and internally validate prediction models for intraoperative hypothermia occurring despite active warming and to implement the algorithm in an online risk estimation tool. The final dataset included 36,371 surgery cases between September 2013 and May 2019 at the Vienna General Hospital. The primary outcome was minimum temperature measured during surgery. Preoperative data, initial vital signs measured before induction of anesthesia, and known comorbidities recorded in the preanesthetic clinic (PAC) were available, and the final predictors were selected by forward selection and backward elimination. Three models with different levels of information were developed and their predictive performance for minimum temperature below 36 °C and 35.5 °C was assessed using discrimination and calibration. Moderate hypothermia (below 35.5 °C) was observed in 18.2% of cases. The algorithm to predict inadvertent intraoperative hypothermia performed well with concordance statistics of 0.71 (36 °C) and 0.70 (35.5 °C) for the model including data from the preanesthetic clinic. All models were well-calibrated for 36 °C and 35.5 °C. Finally, a web-based implementation of the algorithm was programmed to facilitate the calculation of the probabilistic prediction of a patient’s core temperature to fall below 35.5 °C during surgery. The results indicate that inadvertent intraoperative hypothermia still occurs frequently despite active warming. Additional thermoregulatory measures may be needed to increase the rate of perioperative normothermia. The developed prediction models can support clinical decision-makers in identifying the patients at risk for intraoperative hypothermia and help optimize allocation of additional thermoregulatory interventions.

scholarly journals Improving drug safety predictions by reducing poor analytical practices

2020 ◽  
Vol 4 ◽  
pp. 239784732097863
Author(s):  
Stanley E Lazic ◽  
Dominic P Williams
Keyword(s):  
At Risk ◽  
Drug Discovery ◽  
Drug Safety ◽  
Prediction Models ◽  
Predictive Modelling ◽  
Equal Weight ◽  
Negative Consequences ◽  
Preclinical Data ◽  
Safety Pharmacology ◽  
Patients At Risk

Predicting the safety of a drug from preclinical data is a major challenge in drug discovery, and progressing an unsafe compound into the clinic puts patients at risk and wastes resources. In drug safety pharmacology and related fields, methods and analytical decisions known to provide poor predictions are common and include creating arbitrary thresholds, binning continuous values, giving all assays equal weight, and multiple reuse of information. In addition, the metrics used to evaluate models often omit important criteria and models’ performance on new data are often not assessed rigorously. Prediction models with these problems are unlikely to perform well, and published models suffer from many of these issues. We describe these problems in detail, demonstrate their negative consequences, and propose simple solutions that are standard in other disciplines where predictive modelling is used.

scholarly journals Predicting Fever in Neutropenia with Safety Relevant Events in Children Undergoing Chemotherapy for Cancer: the Prospective Multicenter SPOG 2015 FN Definition Study

2021 ◽  
Author(s):  
Luana Lavieri ◽  
Christa Koenig ◽  
Nicole Bodmer ◽  
Philipp Agyeman ◽  
Katrin Scheinemann ◽  
...  
Keyword(s):  
At Risk ◽  
Antibiotic Prophylaxis ◽  
Cross Validation ◽  
Pediatric Patients ◽  
Decision Rules ◽  
Predictive Performance ◽  
Clinical Decision ◽  
External Information ◽  
Prospective Multicenter Study ◽  
Patients At Risk

Background Fever in neutropenia (FN) remains a frequent complication in pediatric patients undergoing chemotherapy for cancer. There are only conflicting and weak recommendations for and against antibiotic prophylaxis during chemotherapy. Procedure Pediatric patients were observed in a prospective multicenter study (NCT02324231). A score predicting the risk to develop FN with safety relevant events (SRE; bacteremia, severe sepsis, intensive care unit admission, death) was developed using multivariate mixed Poisson regression. Its predictive performance was assessed by internal cross-validation and compared with the performance of published rules. Results In 238 patients, 318 FN episodes were recorded, including 53 (17%) with bacteremia and 68 (21%) with SRE. The risk prediction score used three variables: chemotherapy intensity, time since diagnosis and type of malignancy. Its cross-validated performance, assessed by the time needed to cover (TNC) one event, exceeded the performance of published rules. Two clinically useful score thresholds were found: a threshold of ≥11 resulted in 2.3% time at risk and 4.1 months TNC; a threshold of ≥8 in 24.9% time at risk and 12.1 months TNC. Using external information on efficacy and timing of intermittent antibiotic prophylaxis, 4.3 months of prophylaxis were needed to prevent one FN with bacteremia, and 5.2 months to prevent one FN with SRE, using a threshold of ≥11. Conclusions This score, based on three routinely accessible characteristics, accurately identifies pediatric patients at risk to develop FN with SRE during chemothearpy. The score can help to design clinical decision rules on targeted primary antibiotic prophylaxis and corresponding efficacy studies.

scholarly journals Improving drug safety predictions by reducing poor analytical practices

2020 ◽  
Author(s):  
Stanley E. Lazic ◽  
Dominic P. Williams
Keyword(s):  
At Risk ◽  
Drug Discovery ◽  
Drug Safety ◽  
Prediction Models ◽  
Predictive Modelling ◽  
Equal Weight ◽  
Negative Consequences ◽  
Preclinical Data ◽  
Safety Pharmacology ◽  
Patients At Risk

AbstractPredicting the safety of a drug from preclinical data is a major challenge in drug discovery, and progressing an unsafe compound into the clinic puts patients at risk and wastes resources. In drug safety pharmacology and related fields, methods and analytical decisions known to provide poor predictions are common and include creating arbitrary thresholds, binning continuous values, giving all assays equal weight, and multiple reuse of information. In addition, the metrics used to evaluate models often omit important criteria and models’ performance on new data are often not assessed rigorously. Prediction models with these problems are unlikely to perform well, and published models suffer from many of these issues. We describe these problems in detail, demonstrate their negative consequences, and propose simple solutions that are standard in other disciplines where predictive modelling is used.

scholarly journals Clinically useful prediction of hospital admissions in an older population

2020 ◽  
Author(s):  
Jan Marcusson ◽  
Magnus Nord ◽  
Huan-Ji Dong ◽  
Johan Lyth
Keyword(s):  
At Risk ◽  
Prediction Model ◽  
Older Persons ◽  
Hospital Admissions ◽  
Model Fitting ◽  
Forward Selection ◽  
Healthcare Data ◽  
Patients At Risk ◽  
Predicted Values ◽  
Unplanned Hospital Admissions

Abstract Background: The healthcare for older adults is insufficient in many countries, not designed to meet their needs and is often described as disorganized and reactive. Prediction of older persons at risk of admission to hospital may be one important way for the future healthcare system to act proactively when meeting increasing needs for care. Therefore, we wanted to develop and test a clinically useful model for predicting hospital admissions of older persons based on routine healthcare data. Methods : We used the healthcare data on 40,728 persons, 75-109 years of age to predict hospital in-ward care in a prospective cohort. Multivariable logistic regression was used to identify significant factors predictive of unplanned hospital admission. Model fitting was accomplished using forward selection. The accuracy of the prediction model was expressed as area under the receiver operating characteristic (ROC) curve, AUC. Results: The prediction model consisting of 38 variables exhibited a good discriminative accuracy for unplanned hospital admissions over the following 12 months (AUC 0·69 [95% confidence interval, CI 0·68–0·70]) and was validated on external datasets. Clinically relevant proportions of predicted cases of 40 or 45% resulted in sensitivities of 62 and 66%, respectively. The corresponding positive predicted values (PPV) was 31% and 29%, respectively. Conclusion : A prediction model based on routine administrative healthcare data from older persons can be used to find patients at risk of admission to hospital. Identifying the risk population can enable proactive intervention for older patients with as-yet unknown needs for healthcare.

scholarly journals Clinically useful prediction of hospital admissions in an older population

2019 ◽  
Author(s):  
Jan Marcusson ◽  
Magnus Nord ◽  
Huan-Ji Dong ◽  
Johan Lyth
Keyword(s):  
Health Care ◽  
At Risk ◽  
Prediction Model ◽  
Older Persons ◽  
Hospital Admissions ◽  
Model Fitting ◽  
Forward Selection ◽  
Future Health ◽  
Health Care Data ◽  
Patients At Risk

Abstract Background The health care for older adults is insufficient in many countries, not designed to meet their needs and is often described as disorganized and reactive. Prediction of older persons at risk of admission to hospital may be one important way for the future health-care system to act proactively when meeting increasing needs for care. Therefore, we wanted to develop and test a clinically useful model for predicting hospital admissions of older persons based on routine health-care data.Methods We used the health-care data on 40,728 persons, 75-109 years of age to predict hospital in-ward care in a prospective cohort. Multivariable logistic regression was used to identify significant factors predictive of unplanned hospital admission. Model fitting was accomplished using forward selection. The accuracy of the prediction model was expressed as area under the receiver operating characteristic (ROC) curve, AUC.Results The prediction model consisting of 38 variables exhibited a good discriminative accuracy for unplanned hospital admissions over the following 12 months (AUC 0·69 [95% confidence interval, CI 0·68–0·70]) and was validated on external datasets. Clinically relevant proportions of predicted cases of 40 or 45% resulted in sensitivities of 62 and 66%, respectively. The corresponding positive predicted values (PPV) was 31% and 29%, respectively.Conclusion A prediction model based on routine administrative health-care data from older persons can be used to find patients at risk of admission to hospital. Identifying the risk population can enable proactive intervention for older patients with as-yet unknown needs for health care.

scholarly journals Determinants and predictors for the long-term disease burden of intracranial meningioma patients

2020 ◽  
Author(s):  
Amir H. Zamanipoor Najafabadi ◽  
◽  
Pim B. van der Meer ◽  
Florien W. Boele ◽  
Martin J. B. Taphoorn ◽  
...  
Keyword(s):  
At Risk ◽  
Disease Burden ◽  
Prediction Models ◽  
Standardized Test ◽  
Neurocognitive Function ◽  
Tumor Diameter ◽  
Who Grade ◽  
C Statistic ◽  
Patients At Risk

Abstract Introduction Meningioma is a heterogeneous disease and patients may suffer from long-term tumor- and treatment-related sequelae. To help identify patients at risk for these late effects, we first assessed variables associated with impaired long-term health-related quality of life (HRQoL) and impaired neurocognitive function on group level (i.e. determinants). Next, prediction models were developed to predict the risk for long-term neurocognitive or HRQoL impairment on individual patient-level. Methods Secondary data analysis of a cross-sectional multicenter study with intracranial WHO grade I/II meningioma patients, in which HRQoL (Short-Form 36) and neurocognitive functioning (standardized test battery) were assessed. Multivariable regression models were used to assess determinants for these outcomes corrected for confounders, and to build prediction models, evaluated with C-statistics. Results Data from 190 patients were analyzed (median 9 years after intervention). Main determinants for poor HRQoL or impaired neurocognitive function were patients’ sociodemographic characteristics, surgical complications, reoperation, radiotherapy, presence of edema, and a larger tumor diameter on last MRI. Prediction models with a moderate/good ability to discriminate between individual patients with and without impaired HRQoL (C-statistic 0.73, 95% CI 0.65 to 0.81) and neurocognitive function (C-statistic 0.78, 95%CI 0.70 to 0.85) were built. Not all predictors (e.g. tumor location) within these models were also determinants. Conclusions The identified determinants help clinicians to better understand long-term meningioma disease burden. Prediction models can help early identification of individual patients at risk for long-term neurocognitive or HRQoL impairment, facilitating tailored provision of information and allocation of scarce supportive care services to those most likely to benefit.

scholarly journals The Effect of Outcome Selection on the Performance of Prediction Models in Patients at Risk for Sepsis

2020 ◽  
Vol 2 (1) ◽  
pp. e0078
Author(s):  
Stephanie P. Taylor ◽  
Shih-Hsiung Chou ◽  
Andrew D. McWilliams ◽  
Mark Russo ◽  
Alan C. Heffner ◽  
...  
Keyword(s):  
At Risk ◽  
Prediction Models ◽  
Outcome Selection ◽  
Patients At Risk

scholarly journals Identification of preoperative predictors for acute postsurgical pain and for pain at three months after surgery: a prospective observational study

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Regina L. M. van Boekel ◽  
Ewald M. Bronkhorst ◽  
Lilian Vloet ◽  
Monique A. M. Steegers ◽  
Kris C. P. Vissers
Keyword(s):  
At Risk ◽  
Observational Study ◽  
Prospective Observational Study ◽  
Functional Disability ◽  
Prediction Models ◽  
Preoperative Pain ◽  
Postsurgical Pain ◽  
Wound Size ◽  
Patients At Risk ◽  
Preoperative Predictors

AbstractIdentifying patients at risk is the start of adequate perioperative pain management. We aimed to identify preoperative predictors for acute postsurgical pain (APSP) and for pain at 3 months after surgery to develop prediction models. In a prospective observational study, we collected preoperative predictors and the movement-evoked numerical rating scale (NRS-MEP) of postoperative pain at day 1, 2, 3, 7, week 1, 6 and 3 months after surgery from patients with a range of surgical procedures. Regression analyses of data of 2258 surgical in- and outpatients showed that independent predictors for APSP using the mean NRS-MEP over the first three days after surgery were hospital admittance, female sex, higher preoperative pain, younger age, pain catastrophizing, anxiety, higher score on functional disability, highest categories of expected pain, medical specialty, unknown wound size, and wound size > 10 cm compared to wound size ≤ 10 cm (RMSE = 2.11). For pain at three months, the only predictors were preoperative pain and a higher score on functional disability (RMSE = 1.69). Adding pain trajectories improved the prediction of pain at three months (RMSE = 1.37). Our clinically applicable prediction models can be used preoperatively to identify patients at risk, as well as in the direct postoperative period.

scholarly journals Clinically useful prediction of hospital admissions in an older population

2020 ◽  
Author(s):  
Jan Marcusson ◽  
Magnus Nord ◽  
Huan-Ji Dong ◽  
Johan Lyth
Keyword(s):  
At Risk ◽  
Prediction Model ◽  
Older Persons ◽  
Hospital Admissions ◽  
Model Fitting ◽  
Forward Selection ◽  
Healthcare Data ◽  
Patients At Risk ◽  
Predicted Values ◽  
Unplanned Hospital Admissions

Abstract Background: The healthcare for older adults is insufficient in many countries, not designed to meet their needs and is often described as disorganized and reactive. Prediction of older persons at risk of admission to hospital may be one important way for the future healthcare system to act proactively when meeting increasing needs for care. Therefore, we wanted to develop and test a clinically useful model for predicting hospital admissions of older persons based on routine healthcare data. Methods : We used the healthcare data on 40,728 persons, 75-109 years of age to predict hospital in-ward care in a prospective cohort. Multivariable logistic regression was used to identify significant factors predictive of unplanned hospital admission. Model fitting was accomplished using forward selection. The accuracy of the prediction model was expressed as area under the receiver operating characteristic (ROC) curve, AUC. Results: The prediction model consisting of 38 variables exhibited a good discriminative accuracy for unplanned hospital admissions over the following 12 months (AUC 0·69 [95% confidence interval, CI 0·68–0·70]) and was validated on external datasets. Clinically relevant proportions of predicted cases of 40 or 45% resulted in sensitivities of 62 and 66%, respectively. The corresponding positive predicted values (PPV) was 31% and 29%, respectively. Conclusion : A prediction model based on routine administrative healthcare data from older persons can be used to find patients at risk of admission to hospital. Identifying the risk population can enable proactive intervention for older patients with as-yet unknown needs for healthcare.

Sign in / Sign up

Export Citation Format

Share Document