scholarly journals The Roth score as a triage tool for detecting hypoxaemia in general practice: a diagnostic validation study in patients with possible COVID-19

2021 ◽  
Vol 22 ◽  
Author(s):  
Charlotte E.M. ten Broeke ◽  
Jelle C.L. Himmelreich ◽  
Jochen W.L. Cals ◽  
Wim A.M. Lucassen ◽  
Ralf E. Harskamp
Keyword(s):  
General Practice ◽  
Validation Study ◽  
Virus Disease ◽  
External Validation ◽  
Added Value ◽  
Cross Sectional ◽  
Predictive Values ◽  
Single Breath ◽  
C Statistic ◽  
Counting Time

Abstract Aim: To validate the Roth score as a triage tool for detecting hypoxaemia. Backgrounds: The virtual assessment of patients has become increasingly important during the corona virus disease (COVID-19) pandemic, but has limitations as to the evaluation of deteriorating respiratory function. This study presents data on the validity of the Roth score as a triage tool for detecting hypoxaemia remotely in potential COVID-19 patients in general practice. Methods: This cross-sectional validation study was conducted in Dutch general practice. Patients aged ≥18 with suspected or confirmed COVID-19 were asked to rapidly count from 1 to 30 in a single breath. The Roth score involves the highest number counted during exhalation (counting number) and the time taken to reach the maximal count (counting time). Outcome measures were (1) the correlation between both Roth score measurements and simultaneous pulse oximetry (SpO2) on room air and (2) discrimination (c-statistic), sensitivity, specificity and predictive values of the Roth score for detecting hypoxaemia (SpO2 < 95%). Findings: A total of 33 physicians enrolled 105 patients (52.4% female, mean age of 52.6 ± 20.4 years). A positive correlation was found between counting number and SpO2 (rs = 0.44, P < 0.001), whereas only a weak correlation was found between counting time and SpO2 (rs = 0.15, P = 0.14). Discrimination for hypoxaemia was higher for counting number [c-statistic 0.91 (95% CI: 0.85–0.96)] than for counting time [c-statistic 0.77 (95% CI: 0.62–0.93)]. Optimal diagnostic performance was found at a counting number of 20, with a sensitivity of 93.3% (95% CI: 68.1–99.8) and a specificity of 77.8% (95% CI: 67.8–85.9). A counting time of 7 s showed the best sensitivity of 85.7% (95% CI: 57.2–98.2) and specificity of 81.1% (95% CI: 71.5–88.6). Conclusions: A Roth score, with an optimal counting number cut-off value of 20, maybe of added value for signalling hypoxaemia in general practice. Further external validation is warranted before recommending integration in telephone triage.

scholarly journals A Prediction Model for Severe AKI in Critically Ill Adults That Incorporates Clinical and Biomarker Data

2019 ◽  
Vol 14 (4) ◽  
pp. 506-514 ◽  
Author(s):  
Pavan Kumar Bhatraju ◽  
Leila R. Zelnick ◽  
Ronit Katz ◽  
Carmen Mikacenic ◽  
Susanna Kosamo ◽  
...  
Keyword(s):  
Critically Ill ◽  
Critically Ill Patients ◽  
Prediction Models ◽  
Risk Model ◽  
External Validation ◽  
Variable Model ◽  
Internal Validation ◽  
Predictive Values ◽  
Derivation Cohort ◽  
C Statistic

Background and objectivesCritically ill patients with worsening AKI are at high risk for poor outcomes. Predicting which patients will experience progression of AKI remains elusive. We sought to develop and validate a risk model for predicting severe AKI within 72 hours after intensive care unit admission.Design, setting, participants, & measurementsWe applied least absolute shrinkage and selection operator regression methodology to two prospectively enrolled, critically ill cohorts of patients who met criteria for the systemic inflammatory response syndrome, enrolled within 24–48 hours after hospital admission. The risk models were derived and internally validated in 1075 patients and externally validated in 262 patients. Demographics and laboratory and plasma biomarkers of inflammation or endothelial dysfunction were used in the prediction models. Severe AKI was defined as Kidney Disease Improving Global Outcomes (KDIGO) stage 2 or 3.ResultsSevere AKI developed in 62 (8%) patients in the derivation, 26 (8%) patients in the internal validation, and 15 (6%) patients in the external validation cohorts. In the derivation cohort, a three-variable model (age, cirrhosis, and soluble TNF receptor-1 concentrations [ACT]) had a c-statistic of 0.95 (95% confidence interval [95% CI], 0.91 to 0.97). The ACT model performed well in the internal (c-statistic, 0.90; 95% CI, 0.82 to 0.96) and external (c-statistic, 0.93; 95% CI, 0.89 to 0.97) validation cohorts. The ACT model had moderate positive predictive values (0.50–0.95) and high negative predictive values (0.94–0.95) for severe AKI in all three cohorts.ConclusionsACT is a simple, robust model that could be applied to improve risk prognostication and better target clinical trial enrollment in critically ill patients with AKI.

Validation of the BRODERS classifier (Benign versus aggressive nODule Evaluation using Radiomic Stratification), a novel high-resolution computed tomography-based radiomic classifier for indeterminate pulmonary nodules

2020 ◽  
pp. 2002485
Author(s):  
Fabien Maldonado ◽  
Cyril Varghese ◽  
Srinivasan Rajagopalan ◽  
Fenghai Duan ◽  
Aneri Balar ◽  
...  
Keyword(s):  
Computed Tomography ◽  
External Validation ◽  
Lung Nodule ◽  
Pulmonary Nodules ◽  
Lung Cancer Screening ◽  
Pretest Probability ◽  
Imaging Features ◽  
High Resolution Computed Tomography ◽  
Cross Sectional ◽  
Predictive Values

IntroductionImplementation of low-dose chest computed tomography (CT) lung cancer screening and the ever-increasing use of cross-sectional imaging are resulting in the identification of many screen- and incidentally detected indeterminate pulmonary nodules. While the management of nodules with low or high pretest probability of malignancy is relatively straightforward, those with intermediate pretest probability commonly require advanced imaging or biopsy. Non-invasive risk stratification tools are highly desirable.MethodsWe previously developed the BRODERS classifier (Benign versus aggRessive nODule Evaluation using Radiomic Stratification), a conventional predictive radiomic model based on 8 imaging features capturing nodule location, shape, size, texture and surface characteristics. Herein we report its external validation using a dataset of incidentally identified lung nodules (Vanderbilt University Lung Nodule Registry) in comparison to the Brock model. Area under the curve (AUC), as well as sensitivity, specificity, negative and positive predictive values were calculated.ResultsFor the entire Vanderbilt validation set (n=170, 54% malignant), the AUC was 0.87 (95% CI=0.81–0.92) for the Brock model and 0.90 (95% CI=0.85–0.94) for the BRODERS model. Using the optimal cutoff determined by Youden's Index, the sensitivity was 92.3%, the specificity was 62.0%, the positive (PPV) and negative predictive values (NPV) were 73.7% and 87.5%, respectively. For nodules with intermediate pre-test probability of malignancy, Brock score of 5–65% (n=97), the Sensitivity and Specificity were 94% and 46%, the PPV was 78.4% and the NPV was 79.2%, respectively.ConclusionsThe BRODERS radiomic predictive model performs well on an independent dataset and may facilitate the management of indeterminate pulmonary nodules.

scholarly journals External Validation of the HLH-2004 Diagnostic Criteria and H-Score for Diagnosis of Hemophagocytic Lymphohistiocytosis in Adults

Blood ◽  
2020 ◽  
Vol 136 (Supplement 1) ◽  
pp. 44-45
Author(s):  
Jennifer Croden ◽  
Jennifer Grossman ◽  
Haowei Sun
Keyword(s):  
Bone Marrow ◽  
Diagnostic Criteria ◽  
Validation Study ◽  
Predictive Value ◽  
Hemophagocytic Lymphohistiocytosis ◽  
Chart Review ◽  
External Validation ◽  
Advisory Board ◽  
Discriminatory Power ◽  
C Statistic

Introduction: Hemophagocytic lymphohistiocytosis (HLH) is a hyperinflammatory syndrome associated with multi-organ failure and death. Diagnosis in adult patients is currently based on the HLH-2004 diagnostic criteria; however, these criteria were developed for pediatric HLH and have not been formally validated in adults. An alternative diagnostic score, the H-score, was developed for adults with reactive HLH. There have been few external validation studies comparing the diagnostic accuracy between the HLH-2004 criteria and H-score, mostly in critically ill patients. In this external validation study, we aimed to compare the discriminatory power of these two diagnostic criteria in predicting HLH in a multicenter cohort of adults with suspected HLH. Methods: We identified all adult inpatients (≥18 years) with an International Classification of Diseases (ICD) code for HLH in the province of Alberta, Canada from January 1999 to December 2019. Following independent chart review by two reviewers, cases were classified as positive, negative, or indeterminate cases of HLH. The HLH-2004 diagnostic criteria and H-score were determined for each case. The following performance characteristics of the diagnostic scoring systems were calculated: sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). C-statistic was calculated from the receiver operator curve (ROC) analysis. Results: Data on 101 patients were collected. The median age was 46 years (range 18-88), 66 (65%) were male. Active malignancy within 6 months of presentation, infections, and autoimmune diseases were present in 31%, 36%, and 18%, respectively. Of the 96 patients who underwent bone marrow aspirate and biopsy, hemophagocytosis was present in 79 (82%). Using chart review as the gold standard, 89 (88%) patients were determined to have HLH, whereas 5 (5%) and 7 (7%) were reclassified as negative and indeterminate cases, respectively. 83 (82%) patients met ≥5 of the 8 HLH-2004 diagnostic criteria; using the HLH-2004 criteria missed 8 cases of HLH. The sensitivity and specificity of HLH-2004 criteria was 91.0% and 83.3%, respectively, with a PPV of 97.6% and an NPV of 55.6%. The median overall H-score was 238 (range 129-337). An H-Score cut-off of &gt;169 (established as the optimal cut-off from the original derivation and validation paper) predicted HLH with a sensitivity of 95.5%, specificity of 16.7%, PPV of 89.5%, and NPV of 33.3%. The discriminatory power improved with an H-Score cut-off &gt;210, with a sensitivity of 86.5%, specificity of 66.7%, PPV of 95.1%, and NPV of 40.0%. The c-statistics for the HLH-2004 criteria and the H-Score were 0.872 and 0.737, respectively. In the malignant subgroup, all patients fulfilled the HLH-2004 criteria and all were deemed to have HLH upon chart review. All but one had an H-Score &gt;169, with a median H-Score of 238 (range 168-304) in the malignant group. Conclusion: In our highly selected patient population with suspected HLH, the HLH-2004 had better discriminatory power than the H-Score, with a high sensitivity and specificity and excellent c-statistic &gt;0.80. An H-Score cut-off of &gt;169 was highly sensitive but non-specific in identifying adults with HLH. The validity and applicability of our study is limited by a high prevalence of chart-confirmed HLH in our sample. We are completing ongoing data collection to expand our validation study in a cohort of adults with hyperferritinemia who underwent bone marrow evaluation and/or sCD25 testing. Disclosures Sun: Sanofi: Other: Advisory board; Octapharma: Other: Advisory board; Octapharma: Research Funding; Novo Nordisk: Other: Advisory board; Pfizer: Other: Advisory board.

scholarly journals Validation of claims-based algorithms for pulmonary arterial hypertension

2018 ◽  
Vol 8 (2) ◽  
pp. 204589401875924 ◽  
Author(s):  
Ravikanth Papani ◽  
Gulshan Sharma ◽  
Amitesh Agarwal ◽  
Sean J. Callahan ◽  
Winston J. Chan ◽  
...  
Keyword(s):  
Pulmonary Arterial Hypertension ◽  
Positive Predictive Value ◽  
Arterial Hypertension ◽  
Predictive Value ◽  
External Validation ◽  
Administrative Claims ◽  
Predictive Values ◽  
C Statistic ◽  
Pulmonary Arterial ◽  
The University

Administrative claims studies do not adequately distinguish pulmonary arterial hypertension (PAH) from other forms of pulmonary hypertension (PH). Our aim is to develop and validate a set of algorithms using International Classification of Diseases, Ninth Revision, Clinical Modification (ICD-9-CM) codes and electronic medical records (EMR), to identify patients with PAH. From January 2012 to August 2015, the EMRs of patients with ICD-9-CM codes for PH with an outpatient visit at the University of Texas Medical Branch were reviewed. Patients were divided into PAH or non-PAH groups according to EMR encounter diagnosis. Patient demographics, echocardiography, right heart catheterization (RHC) results, and PAH-specific therapies were assessed. RHC measurements were reviewed to categorize cases as hemodynamically determined PAH or not PAH. Weighted sensitivity, specificity, and positive and negative predictive values were calculated for the developed algorithms. A logistic regression analysis was conducted to determine how well the algorithms performed. External validation was performed at the University of Virginia Health System. The cohort for the development algorithms consisted of 683 patients with PH, PAH group (n = 191) and non-PAH group (n = 492). A hemodynamic diagnosis of PAH determined by RHC was recorded in the PAH (26%) and non-PAH (3%) groups. The positive predictive value for the algorithm that included ICD-9-CM and PAH-specific medications was 66.9% and sensitivity was 28.2% with a c-statistic of 0.66. The positive predictive value for the EMR-based algorithm that included ICD-9-CM, EMR encounter diagnosis, echocardiography, RHC, and PAH-specific medication was 69.4% and a c-statistic of 0.87. A validation cohort of 177 patients with PH examined from August 2015 to August 2016 using EMR-based algorithms yielded a similar positive predictive value of 62.5%. In conclusion, claims-based algorithms that included ICD-9-CM codes, EMR encounter diagnosis, echocardiography, RHC, and PAH-specific medications better-identified patients with PAH than ICD-9-CM codes alone.

scholarly journals Ziehl Neelsen vs. Auramine staining technique for detection of acid fast bacilli

2018 ◽  
Vol 1 (1) ◽  
pp. 59-66
Author(s):  
Rajendra Gurung ◽  
R Shrestha ◽  
N Poudyal ◽  
SK Bhattacharya
Keyword(s):  
Staining Technique ◽  
Developed Countries ◽  
Added Value ◽  
Limited Resources ◽  
Smear Microscopy ◽  
Molecular Test ◽  
Isolation And Identification ◽  
Cross Sectional ◽  
Predictive Values ◽  
Acid Fast Bacilli

Background: The culture and molecular test are the best methods for isolation and identification of Mycobacterium tuberculosis in developed countries. But, in developing countries like Nepal with a significant number of tuberculosis (TB) cases and limited resources, the diagnosis of TB relies primarily on smear microscopy for Acid fast bacilli (AFB).Objective: To compare the results of direct sputum examination for AFB stained by Ziehl Neelsen and Auramine technique.Method: Cross sectional comparative study was conducted in tuberculosis research laboratory, BPKIHS from April to June 2013. A total of 100 sputum samples were collected randomly. Four slides were smeared and labeled for each as neat ZN, neat Auramine, concentrate ZN and concentrate Auramine. Slides were processed as per WHO laboratory guidelines.Results: The findings of this study revealed that 3% positive with neat Auramine was negative for ZN stain. Similarly, 5% positive cases with Auramine concentrate were negative with ZN concentrate technique. Auramine stain was able to detect all ZN positive as positive but only 83 cases were detected as negative among 88 case of ZN negative. Both concentration techniques showed 12% of positive with significant relationship. With this; Auramine showed 100% sensitivity, 94.6% specificity, positive predictive values and negative predictive values 70.5, 100% respectively.Conclusion: Auramine stain stands efficient on comparison and can be used as an alternative to ZN stain, with added value of allowing a large number of sputum specimens to be examined in a given time as low power is used for examination.Journal of BP Koirala Institute of Health Sciences, Vol. 1, No. 1, 2018, Page: 59-66

scholarly journals Performance of popular pulse oximeters compared with simultaneous arterial oxygen saturation or clinical-grade pulse oximetry: a cross-sectional validation study in intensive care patients

2021 ◽  
Vol 8 (1) ◽  
pp. e000939
Author(s):  
Ralf E Harskamp ◽  
Luuk Bekker ◽  
Jelle C L Himmelreich ◽  
Lukas De Clercq ◽  
Evert P M Karregat ◽  
...  
Keyword(s):  
Intensive Care ◽  
Blood Sample ◽  
Validation Study ◽  
Arterial Oxygen ◽  
Index Test ◽  
Cross Sectional ◽  
Predictive Values ◽  
Iso Standards ◽  
Direct To Consumer ◽  
Pulse Oximeters

ObjectivesTo evaluate the performance of direct-to-consumer pulse oximeters under clinical conditions, with arterial blood gas measurement (SaO2) as reference standard.DesignCross-sectional, validation study.SettingIntensive care.ParticipantsAdult patients requiring SaO2-monitoring.InterventionsThe studied oximeters are top-selling in Europe/USA (AFAC FS10D, AGPTEK FS10C, ANAPULSE ANP 100, Cocobear, Contec CMS50D1, HYLOGY MD-H37, Mommed YM101, PRCMISEMED F4PRO, PULOX PO-200 and Zacurate Pro Series 500 DL). Directly after collection of a SaO2 blood sample, we obtained pulse oximeter readings (SpO2). SpO2-readings were performed in rotating order, blinded for SaO2 and completed <10 min after blood sample collection.Outcome measuresBias (SpO2–SaO2) mean, root mean square difference (ARMS), mean absolute error (MAE) and accuracy in identifying hypoxaemia (SaO2 ≤90%). As a clinical index test, we included a hospital-grade SpO2-monitor (Philips).ResultsIn 35 consecutive patients, we obtained 2258 SpO2-readings and 234 SaO2-samples. Mean bias ranged from −0.6 to −4.8. None of the pulse oximeters met ARMS ≤3%, the requirement set by International Organisation for Standardisation (ISO)-standards and required for Food and Drug Administration (FDA) 501(k)-clearance. The MAE ranged from 2.3 to 5.1, and five out of ten pulse oximeters met the requirement of ≤3%. For hypoxaemia, negative predictive values were 98%–99%. Positive predictive values ranged from 11% to 30%. Highest accuracy (95% CI) was found for Contec CMS50D1; 91% (86–94) and Zacurate Pro Series 500 DL; 90% (85–94). The hospital-grade SpO2-monitor had an ARMS of 3.0% and MAE of 1.9, and an accuracy of 95% (91%–97%).ConclusionTop-selling, direct-to-consumer pulse oximeters can accurately rule out hypoxaemia, but do not meet ISO-standards required for FDA-clearance

scholarly journals Prognostication of Patients with Spinal Bone Metastases (SBM): External Validation Study Comparing the Utility of Two Current Prediction Models

2020 ◽  
pp. 1-7
Author(s):  
I. Sanli ◽  
I. Sanli ◽  
Terhaag K ◽  
van Baardwijk A ◽  
van Kuijk SMJ ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Clinical Practice ◽  
Cancer Patients ◽  
Validation Study ◽  
Prediction Models ◽  
External Validation ◽  
Breast Cancer Patients ◽  
Predictive Capacity ◽  
C Statistic ◽  
External Validation Study

Purpose: A majority of developed prediction models for SBM are not used in clinical practice, where there is lack of external validation studies describing their performance on independent patient data. Methods: Primary aim was to externally validate two prediction models and to demonstrate whether these can be generalized for patients treated in different centers. Secondary aim was to identify additional prognostic factors predicting survival in patients with SBM. Results: Our results show modest predictive capacity for patients with symptomatic SBM in daily clinical practice by use of the existing two prediction models Van der Linden and Bollen. A slightly better performance in discrimination and calibration is found for the Bollen model with a C-statistic of 0.67 (95% CI: 0.63 –0.71) based on the validation dataset (95% CI: 0.65 –0.73) in contrast to Van der Linden with a C-statistic of 0.65 (95% CI: 0.60–0.71). Impact of brain or visceral metastases was significantly associated with survival, with a Hazard Ratio (HR) of 3.8 and 1.34 respectively. For breast cancer patients with SBM, hormone receptor status was of importance for prognostication (C-statistic of 0.67). Conclusion: With this first external validation study, we found modest predictive capacity for the prediction models by van der Linden and Bollen, with a slightly better performance for the Bollen model. Predictive impact of overall visceral and brainmetastases should not be underestimated. Breast tumor subtypes based on immunohistochemistry markers, seem to be of importance for the prognostication of breast cancer patients with SBM.

scholarly journals The value of inquiring about functional impairments for early identification of inflammatory arthritis: a large cross-sectional derivation and validation study from the Netherlands

BMJ Open ◽  
2020 ◽  
Vol 10 (12) ◽  
pp. e040148
Author(s):  
Bastiaan van Dijk ◽  
Hanna W van Steenbergen ◽  
Ellis Niemantsverdriet ◽  
Elisabeth Brouwer ◽  
Annette van der Helm-van Mil
Keyword(s):  
The Netherlands ◽  
Validation Study ◽  
Inflammatory Arthritis ◽  
Healthcare Professionals ◽  
Functional Impairments ◽  
Discriminative Ability ◽  
Cross Sectional ◽  
Predictive Values ◽  
Derivation Cohort ◽  
Joint Examination

ObjectivesHealthcare professionals other than rheumatologists experience difficulties in detecting early inflammatory arthritis (IA) by joint examination. Self-reported symptoms are increasingly considered as helpful and could be incorporated in online tools to assist healthcare professionals, but first their discriminative ability must be assessed. As part of this effort, we evaluated whether inquiring about functional impairments could aid early IA identification.DesignCross-sectional derivation and validation study.SettingData from two Early Arthritis Recognition Clinics (EARC) in the Netherlands were studied, which are easy access outpatient rheumatology clinics intermediary between primary and secondary care for patients in whom general practitioners suspect but are unsure about IA presence.ParticipantsBetween 2010 and 2014, 997 patients consecutively visited the Leiden-EARC (derivation cohort). Patients consecutively visiting the Groningen EARC (2010–2014, n=506) and Leiden-EARC (2015–2018, n=557) served as validation cohorts.Primary and secondary outcome measuresPhysical functioning was assessed with the Health Assessment Questionnaire Disability-Index (HAQ); IA presence by physical joint examination by rheumatologists. HAQ questions were studied individually regarding discriminative ability for IA presence. For the best discriminating question, ORs and positive predictive values (PPVs) for IA presence were determined.ResultsIA was ascertained in 43% (derivation cohort), 53% and 35% (validation cohorts). In the derivation cohort, IA presence associated with higher mean HAQ scores (0.84 vs 0.73, p=0.003). One question on difficulties with dressing equalled discriminative ability of the total HAQ score. ‘Difficulties with dressing’ yielded ORs for IA presence of 1.8 (95% CI 1.4 to 2.4) in the derivation cohort; 2.0 (1.4 to 2.9) and 2.1 (1.5 to 3.1) in the validation cohorts. After adjustments for clinical characteristics these were 1.7 (1.3 to 2.3), 1.6 (1.1 to 2.5) and 1.9 (1.2 to 2.9). PPVs (probabilities of IA for positive answers) ranged 42%–60% and negative predictive values (probabilities of no IA for negative answers) ranged 57%–74%.ConclusionsPatient-reported difficulties with dressing in patients with suspected IA associated with actual IA presence. Although further validation is required, for example, in primary care, this simple question could be of help in future early IA detection tools for healthcare professionals with limited experience in joint examination.

Predicting nonroutine discharge after elective spine surgery: external validation of machine learning algorithms

2019 ◽  
Vol 31 (5) ◽  
pp. 742-747 ◽  
Author(s):  
Brittany M. Stopa ◽  
Faith C. Robertson ◽  
Aditya V. Karhade ◽  
Melissa Chua ◽  
Marike L. D. Broekman ◽  
...  
Keyword(s):  
Machine Learning ◽  
Spine Surgery ◽  
Learning Algorithm ◽  
Lumbar Disc ◽  
External Validation ◽  
Machine Learning Algorithms ◽  
Multidisciplinary Teams ◽  
Machine Learning Algorithm ◽  
Predictive Values ◽  
C Statistic

OBJECTIVENonroutine discharge after elective spine surgery increases healthcare costs, negatively impacts patient satisfaction, and exposes patients to additional hospital-acquired complications. Therefore, prediction of nonroutine discharge in this population may improve clinical management. The authors previously developed a machine learning algorithm from national data that predicts risk of nonhome discharge for patients undergoing surgery for lumbar disc disorders. In this paper the authors externally validate their algorithm in an independent institutional population of neurosurgical spine patients.METHODSMedical records from elective inpatient surgery for lumbar disc herniation or degeneration in the Transitional Care Program at Brigham and Women’s Hospital (2013–2015) were retrospectively reviewed. Variables included age, sex, BMI, American Society of Anesthesiologists (ASA) class, preoperative functional status, number of fusion levels, comorbidities, preoperative laboratory values, and discharge disposition. Nonroutine discharge was defined as postoperative discharge to any setting other than home. The discrimination (c-statistic), calibration, and positive and negative predictive values (PPVs and NPVs) of the algorithm were assessed in the institutional sample.RESULTSOverall, 144 patients underwent elective inpatient surgery for lumbar disc disorders with a nonroutine discharge rate of 6.9% (n = 10). The median patient age was 50 years and 45.1% of patients were female. Most patients were ASA class II (66.0%), had 1 or 2 levels fused (80.6%), and had no diabetes (91.7%). The median hematocrit level was 41.2%. The neural network algorithm generalized well to the institutional data, with a c-statistic (area under the receiver operating characteristic curve) of 0.89, calibration slope of 1.09, and calibration intercept of −0.08. At a threshold of 0.25, the PPV was 0.50 and the NPV was 0.97.CONCLUSIONSThis institutional external validation of a previously developed machine learning algorithm suggests a reliable method for identifying patients with lumbar disc disorder at risk for nonroutine discharge. Performance in the institutional cohort was comparable to performance in the derivation cohort and represents an improved predictive value over clinician intuition. This finding substantiates initial use of this algorithm in clinical practice. This tool may be used by multidisciplinary teams of case managers and spine surgeons to strategically invest additional time and resources into postoperative plans for this population.

Sign in / Sign up

Export Citation Format

Share Document