Prediction Of Individual Outcome Research Articles

Evaluating individualized treatment effect predictions: A model-based perspective on discrimination and calibration assessment.

In recent years, there has been a growing interest in the prediction of individualized treatment effects. While there is a rapidly growing literature on the development of such models, there is little literature on the evaluation of their performance. In this paper, we aim to facilitate the validation of prediction models for individualized treatment effects. The estimands of interest are defined based on the potential outcomes framework, which facilitates a comparison of existing and novel measures. In particular, we examine existing measures of discrimination for benefit (variations of the c-for-benefit), and propose model-based extensions to the treatment effect setting for discrimination and calibration metrics that have a strong basis in outcome risk prediction. The main focus is on randomized trial data with binary endpoints and on models that provide individualized treatment effect predictions and potential outcome predictions. We use simulated data to provide insight into the characteristics of the examined discrimination and calibration statistics under consideration, and further illustrate all methods in a trial of acute ischemic stroke treatment. The results show that the proposed model-based statistics had the best characteristics in terms of bias and accuracy. While resampling methods adjusted for the optimism of performance estimates in the development data, they had a high variance across replications that limited their accuracy. Therefore, individualized treatment effect models are best validated in independent data. To aid implementation, a software implementation of the proposed methods was made available in R.

Outcome Prediction Model for Radiofrequency Uvulopalatopharyngoplasty with Tonsillectomy in Adult Obstructive Sleep Apnea: Retrospective Cohort Study

Introduction: Knowing an individualized outcome prediction is essential when counseling patients before surgery. We aim to identify predictors and build a model for the outcome of radiofrequency uvulopalatopharyngoplasty with tonsillectomy (rfUPPP + TE). Methods: All adult patients undergoing rfUPPP + TE for sleep-disordered breathing from 2015 to 2022 in our institution were included. Preoperative evaluations included detailed upper airway examinations and standardized questionnaires. Postoperative outcomes were measured through home sleep apnea testing and repeated questionnaires 3 months post-surgery. The primary endpoint was the postoperative apnea-hypopnea index (AHI) and the AHI responders using the Sher criteria. Results: We analyzed 247 patients with a mean age of 46 ± 11 years, predominantly male (88.7%), and a mean BMI of 29.0 kg/m2. The mean AHI was reduced from 26.4 ± 18.6/h preoperatively to 16.2 ± 14.6/h postoperatively. Daytime sleepiness improved from 8.9 ± 48 to 4.0 ± 3.1 and snoring from 7.9 ± 2.1 to 3.3 ± 2.2. Multivariate analysis indicated that higher tonsil grades, preoperative AHI, and snoring levels were associated with a greater reduction in AHI. Age and body weight were negative predictors for AHI reduction. For AHI responders, according to Sher, tonsil grade was the only predictor in a multivariate analysis. The ROC curve of this simple model, with a corrected AUC of 0.625, compared favorably against two established models. Conclusion: Our study highlights that tonsil grade, preoperative AHI, snoring, and, to a smaller extent, age and weight are key determinants of AHI reduction, emphasizing the importance of preoperative evaluation. Despite the multifactorial nature of obstructive sleep apnea, preoperative evaluation can predict the outcome of rfUPPP + TE and guide surgical planning.

Predicting outcome after aneurysmal subarachnoid hemorrhage by exploitation of signal complexity: a prospective two-center cohort study

BackgroundSignal complexity (i.e. entropy) describes the level of order within a system. Low physiological signal complexity predicts unfavorable outcome in a variety of diseases and is assumed to reflect increased rigidity of the cardio/cerebrovascular system leading to (or reflecting) autoregulation failure. Aneurysmal subarachnoid hemorrhage (aSAH) is followed by a cascade of complex systemic and cerebral sequelae. In aSAH, the value of entropy has not been established yet.MethodsaSAH patients from 2 prospective cohorts (Zurich—derivation cohort, Aachen—validation cohort) were included. Multiscale Entropy (MSE) was estimated for arterial blood pressure, intracranial pressure, heart rate, and their derivatives, and compared to dichotomized (1–4 vs. 5–8) or ordinal outcome (GOSE—extended Glasgow Outcome Scale) at 12 months using uni- and multivariable (adjusted for age, World Federation of Neurological Surgeons grade, modified Fisher (mFisher) grade, delayed cerebral infarction), and ordinal methods (proportional odds logistic regression/sliding dichotomy). The multivariable logistic regression models were validated internally using bootstrapping and externally by assessing the calibration and discrimination.ResultsA total of 330 (derivation: 241, validation: 89) aSAH patients were analyzed. Decreasing MSE was associated with a higher likelihood of unfavorable outcome independent of covariates and analysis method. The multivariable adjusted logistic regression models were well calibrated and only showed a slight decrease in discrimination when assessed in the validation cohort. The ordinal analysis revealed its effect to be linear. MSE remained valid when adjusting the outcome definition against the initial severity.ConclusionsMSE metrics and thereby complexity of physiological signals are independent, internally and externally valid predictors of 12-month outcome. Incorporating high-frequency physiological data as part of clinical outcome prediction may enable precise, individualized outcome prediction. The results of this study warrant further investigation into the cause of the resulting complexity as well as its association to important and potentially preventable complications including vasospasm and delayed cerebral ischemia.

The development and validation of a Multidimensional Perceived Work Ability Scale.

Research on the concept of existing unidimensional Perceived Work Ability scale (PWA) in organizational science has recently increased due to its prediction of important work, individual, and labor force outcomes. To date, PWA has been measured as a unidimensional construct. The present study outlines the need for the multidimensional conceptualization of PWA and its measurement. We describe the development and validation of the Multidimensional Perceived Work Ability Scale (M-PWAS), comprising four dimensions: physical, cognitive, interpersonal, and emotional. In line with Hinkin's (1998) approach to scale validation, we use four samples (total N = 1,152) to establish the M-PWAS as a reliable and valid measure of PWA. Through an iterative item generation and review process, we found evidence for content validity. Furthermore, each subscale demonstrated high internal consistency and factorial validity, and analysis of the PWA nomological network demonstrated evidence for convergent and discriminant validity. Finally, we found that the M-PWAS showed incremental validity over an existing unidimensional PWA measure in the prediction of perceived stress, emotional exhaustion, work engagement, and turnover. We discuss implications for theory, research, and workplace interventions. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Predicting Long-Term Childhood Survival of Newborns with Congenital Heart Defects: A Population-Based, Prospective Cohort Study (EPICARD).

Backgroud: Congenital heart defects (CHDs) are the most frequent group of major congenital anomalies, accounting for almost 1% of all births. They comprise a very heterogeneous group of birth defects in terms of their severity, clinical management, epidemiology, and embryologic origins. Taking this heterogeneity into account is an important imperative to provide reliable prognostic information to patients and their caregivers, as well as to compare results between centers or to assess alternative diagnostic and treatment strategies. The Anatomic and Clinical Classification of CHD (ACC-CHD) aims to facilitate both the CHD coding process and data analysis in clinical and epidemiological studies. The objectives of the study were to (1) Describe the long-term childhood survival of newborns with CHD, and (2) Develop and validate predictive models of infant mortality based on the ACC-CHD. Methods: This study wasbased on data from a population-based, prospective cohort study: Epidemiological Study of Children with Congenital Heart Defects (EPICARD). The final study population comprised 1881 newborns with CHDs after excluding cases that were associated with chromosomal and other anomalies. Statistical analysis included non-parametric survival analysis and flexible parametric survival models. The predictive performance of models was assessed by Harrell's C index and the Royston-Sauerbrei RD2, with internal validation by bootstrap. Results: The overall 8-year survival rate for newborns with isolated CHDs was 0.96 [0.93-0.95]. There was a substantial difference between the survival rate of the categories of ACC-CHD. The highest and lowest 8-year survival rates were 0.995 [0.989-0.997] and 0.34 [0.21-0.50] for "interatrial communication abnormalities and ventricular septal defects" and "functionally univentricular heart", respectively. Model discrimination, as measured by Harrell's C, was 87% and 89% for the model with ACC-CHD alone and the full model, which included other known predictors of infant mortality, respectively. The predictive performance, as measured by RD2, was 45% and 50% for the ACC-CHD alone and the full model. These measures were essentially the same after internal validation by bootstrap. Conclusions: The ACC-CHD classification provided the basis of a highly discriminant survival model with good predictive ability for the 8-year survival of newborns with CHDs. Prediction of individual outcomes remains an important clinical and statistical challenge.

Machine Learning Provides Individualized Prediction of Outcomes after First Complete Remission in Adult AML Patients - Results from the Harmony Platform

Background: Acute myeloid leukemia (AML) is a heterogeneous disease with high disease-related mortality and allogeneic hematopoietic stem cell transplantation (allo-HSCT) remains the only curative option for a large proportion of patients. However, allo-HSCT has a significant transplant-related mortality (TRM), so a careful evaluation between risk of disease relapse and TRM is needed for the challenging decision of whom to transplant in first complete remission (CR1). The European LeukemiaNet (ELN) provides a 3-tier static risk classification which is already a useful guidance, although dynamic risk assessment using measurable residual disease (MRD) information should also be taken into account. However, the intermediate-risk group is characterized by a wide heterogeneity and there are also some favorable-risk patients who require allo-HSCT because of early relapses after CR1. Therefore, more precise prediction tools are warranted to provide additional information valuable for clinical decision-making. Aims: To develop and validate a model that provides individualized outcome estimations in adult AML patients achieving CR1 with intensive treatment approaches. Methods: From the HARMONY Platform including 7467 AML patients at the time of the analysis, we selected patients aged 18-70 years old who received intensive treatment, achieved CR and were not consolidated with allo-HSCT in CR1. Patients who were refractory to first line chemotherapy or who had a relapse-free survival (RFS) of less than two months after achieving CR were excluded. A Bayesian Additive Regression Trees (BART) nonparametric machine learning model was used to predict the individualized likelihood of RFS, cumulative incidence of relapse (CIR) and overall survival (OS) in 1863 AML patients who were also selected based on the availability of comprehensive mutational information by next-generation sequencing analysis. Genomic aberrations that were present in at least 10 patients were included in the model. In order to test the accuracy of the model, a 10-fold cross-validation was applied using the area under receiver operating curve (AUC) at predefined time points (1, 2, 3, 4 and 5 years). Subsequently, the model was validated using an external publicly available database (Tazi et al, Nat. Commun. 2022) which included 722 patients based on identical inclusion criteria. Results: The study population of 1863 adult AML patients in CR1 included 51.2% of males and median age was 50 years. Regarding ELN2022 classification, 52% of patients were classified as favorable, 30% as intermediate and 18% as adverse risk. Most frequently mutated genes were NPM1 (35.9%), DNMT3A (25.6%) and NRAS (21.6%). The HARMONY model was able to estimate individualized likelihood of RFS, CIR and OS for all patients, providing confidence intervals for all estimations. Moreover, we could predict outcomes with increased accuracy over ELN2022 at all predefined time points. At 5 years, the AUC value was significantly better for the HARMONY model than ELN2022 in predicting RFS (0.729 vs 0.679, p=0.003), CIR (0.729 vs 0.680, p=0.002) and OS (0.733 vs 0.675, p<0.001) ( figure 1A). Validation in an external independent AML cohort confirmed superiority of the HARMONY model in predicting RFS (5-year AUC 0.714 vs 0.609, p <0.001), CIR (0.713 vs 0.610, p <0.001) and OS (0.737 vs 0.638, p <0.001) as compared to the ELN2022 risk stratification ( figure 1B), despite the fact that there was a different distribution of risk categories (28% favorable, 45% intermediate and 27% adverse risk). Conclusions: Analysis of large well-defined AML cohorts allows the development of increasingly precise predictive models for clinically relevant scenarios. The HARMONY machine learning model provides individualized outcome prediction for patients aged 18-70 years in CR1 consolidated without allo-HSCT and might be used in the future for clinical decision-making. The model can be accessed online via an interactive web calculator () and, while it has been validated using a large independent AML cohort, future studies are required focusing on prospective validation. Furthermore, the incorporation of additional variables such as MRD and the inclusion of patients treated with targeted therapies and non-intensive approaches will provide more accurate risk predictions.

Does the Metabolic and Bariatric Surgery Accreditation and Quality Improvement Program bariatric risk/benefit calculator hold its weight? An assessment of its accuracy

BackgroundBariatric clinical calculators have already been implemented in clinical practice to provide objective predictions of complications and outcomes. The Metabolic and Bariatric Surgery Accreditation and Quality Improvement Program (MBSAQIP) Surgical Risk/Benefit Calculator is the most comprehensive risk calculator in bariatric surgery. ObjectivesEvaluate the accuracy of the calculator predictions regarding the 30-day complication risk, 1-year weight loss outcomes, and comorbidity resolution. SettingMBSAQIP-accredited center. MethodsAll adult patients who underwent primary laparoscopic Roux-en-Y gastric bypass (RYGB) or sleeve gastrectomy at our institution between 2012 and 2019 were included. Baseline characteristics were used to generate the individualized outcome predictions for each patient through the bariatric risk calculator and were compared to actual patient outcomes. Statistical analysis was performed using c-statistics, linear regression models, and McNemmar chi-square test. ResultsOne thousand four hundred fifty-three patients with a median age of 45 (37, 55) and consisting of 80.1% females were included in the study. The c-statistics for the complications and comorbidity resolution ranged from .533 for obstructive sleep apnea remission to .675 for 30-day reoperation. The number of comorbidity resolutions predicted by the calculator was significantly higher than the actual remissions for diabetes, hyperlipidemia, hypertension and obstructive sleep apnea (P < .001). On average, the calculator body mass index (BMI) predictions deviated from the observed BMI measurement by 3.24 kg/m2. The RYGB procedure (Coef −.89; P = .005) and preoperative BMI (Coef −.4; P = .012) were risk factors associated with larger absolute difference between the predicted and observed BMI. ConclusionsThe MBSAQIP Surgical Risk/Benefit Calculator prediction models for 1-year BMI, 30-day reoperation, and reintervention risks were fairly well calibrated with an acceptable level of discrimination except for obstructive sleep apnea remission. The 1-year BMI estimations were less accurate for RYGB patients and cases with very high or low preoperative BMI measurements. Therefore, the bariatric risk calculator constitutes a helpful tool that has a place in preoperative counseling.

From conventional to cutting edge imaging in rheumatology

Imaging instruments, such as conventional X‑ray, ultrasound and magnetic resonance imaging (MRI) are now fully established and highly valued in the care of rheumatology patients. However, the information provided by these imaging modalities in their current form is of limited utility for the prognostic prediction of individual patient outcomes. This article illuminates an important part of the development of imaging and shows that the vision of personalized medicine is becoming increasingly more tangible due to the further development of high-resolution imaging techniques, molecular imaging and artificial intelligence.

Heart rate variability: reference values and role for clinical profile and mortality in individuals with heart failure.

To establish reference values and clinically relevant determinants for measures of heart rate variability (HRV) and to assess their relevance for clinical outcome prediction in individuals with heart failure. Data from the MyoVasc study (NCT04064450; N = 3289), a prospective cohort on chronic heart failure with a highly standardized, 5h examination, and Holter ECG recording were investigated. HRV markers were selected using a systematic literature screen and a data-driven approach. Reference values were determined from a healthy subsample. Clinical determinants of HRV were investigated via multivariable linear regression analyses, while their relationship with mortality was investigated by multivariable Cox regression analyses. Holter ECG recordings were available for analysis in 1001 study participants (mean age 64.5 ± 10.5years; female sex 35.4%). While the most frequently reported HRV markers in literature were from time and frequency domains, the data-driven approach revealed predominantly non-linear HRV measures. Age, sex, dyslipidemia, family history of myocardial infarction or stroke, peripheral artery disease, and heart failure were strongly related to HRV in multivariable models. In a follow-up period of 6.5years, acceleration capacity [HRperSD 1.53 (95% CI 1.21/1.93), p = 0.0004], deceleration capacity [HRperSD: 0.70 (95% CI 0.55/0.88), p = 0.002], and time lag [HRperSD 1.22 (95% CI 1.03/1.44), p = 0.018] were the strongest predictors of all-cause mortality in individuals with heart failure independently of cardiovascular risk factors, comorbidities, and medication. HRV markers are associated with the cardiovascular clinical profile and are strong and independent predictors of survival in heart failure. This underscores clinical relevance and interventional potential for individuals with heart failure. NCT04064450.

A Novel Cuproptosis-Associated Gene Signature to Predict Prognosis in Patients with Pancreatic Cancer.

Pancreatic cancer (PAAD) is a malignant tumor with a poor prognosis and lacks sensitive biomarkers for diagnosis and targeted therapy. Cuproptosis, a recently proposed form of cell death based on cellular copper ion concentration, plays a key role in cancer biology. This study is aimed at constructing a risk model for predicting the prognosis of PAAD patients based on cuproptosis-related genes. Pancreatic-related data from UCSC-TCGA and UCSC-GTEx databases were extracted for analysis, and TCGA-PAAD samples were randomly divided into the training and validation groups. Pearson correlation analysis was used to obtain cuproptosis-related genes coexpressed with 19 copper death genes. Univariate Cox and Lasso regression analyses were used to obtain cuproptosis-related prognostic genes. Multivariate Cox regression analysis was used to construct the final prognostic risk model. The risk score curve, Kaplan-Meier survival curves, and ROC curve were used to evaluate the predictive ability of the Cox risk model. Finally, the functional annotation of the risk model was obtained through enrichment analysis. The Cox risk model has an eight prognostic cuproptosis-related gene signature. Kaplan-Meier survival curves demonstrated that the high-risk group had a shorter survival time. The ROC curve of the risk score was well created to predict one-, three-, and five-year survival rates, and AUC of the risk score was higher than other clinical characteristics. Cox regression analysis revealed that the risk score has an independent prognostic value for PAAD. GSEA reveals specific tumor pathways associated with the risk model (Myc targets v1, mTORC1 signaling, and E2F targets). We constructed a prognostic model containing eight cuproptosis-related genes (AKR1B10, KLHL29, PROM2, PIP5K1C, KIF18B, AMIGO2, MRPL3, and PI4KB) that can accurately predict the prognosis of PAAD patients. The results will provide new perspectives for individualized outcome prediction and new therapy development for PAAD patients.

Individualised computational modelling of immune mediated disease onset, flare and clearance in psoriasis.

Despite increased understanding about psoriasis pathophysiology, currently there is a lack of predictive computational models. We developed a personalisable ordinary differential equations model of human epidermis and psoriasis that incorporates immune cells and cytokine stimuli to regulate the transition between two stable steady states of clinically healthy (non-lesional) and disease (lesional psoriasis, plaque) skin. In line with experimental data, an immune stimulus initiated transition from healthy skin to psoriasis and apoptosis of immune and epidermal cells induced by UVB phototherapy returned the epidermis back to the healthy state. Notably, our model was able to distinguish disease flares. The flexibility of our model permitted the development of a patient-specific “UVB sensitivity” parameter that reflected subject-specific sensitivity to apoptosis and enabled simulation of individual patients’ clinical response trajectory. In a prospective clinical study of 94 patients, serial individual UVB doses and clinical response (Psoriasis Area Severity Index) values collected over the first three weeks of UVB therapy informed estimation of the “UVB sensitivity” parameter and the prediction of individual patient outcome at the end of phototherapy. An important advance of our model is its potential for direct clinical application through early assessment of response to UVB therapy, and for individualised optimisation of phototherapy regimes to improve clinical outcome. Additionally by incorporating the complex interaction of immune cells and epidermal keratinocytes, our model provides a basis to study and predict outcomes to biologic therapies in psoriasis.

Multimodal resting-state connectivity predicts affective neurofeedback performance.

Neurofeedback has been suggested as a potential complementary therapy to different psychiatric disorders. Of interest for this approach is the prediction of individual performance and outcomes. In this study, we applied functional connectivity-based modeling using electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) modalities to (i) investigate whether resting-state connectivity predicts performance during an affective neurofeedback task and (ii) evaluate the extent to which predictive connectivity profiles are correlated across EEG and fNIRS techniques. The fNIRS oxyhemoglobin and deoxyhemoglobin concentrations and the EEG beta and gamma bands modulated by the alpha frequency band (beta-m-alpha and gamma-m-alpha, respectively) recorded over the frontal cortex of healthy subjects were used to estimate functional connectivity from each neuroimaging modality. For each connectivity matrix, relevant edges were selected in a leave-one-subject-out procedure, summed into “connectivity summary scores” (CSS), and submitted as inputs to a support vector regressor (SVR). Then, the performance of the left-out-subject was predicted using the trained SVR model. Linear relationships between the CSS across both modalities were evaluated using Pearson’s correlation. The predictive model showed a mean absolute error smaller than 20%, and the fNIRS oxyhemoglobin CSS was significantly correlated with the EEG gamma-m-alpha CSS (r = −0.456, p = 0.030). These results support that pre-task electrophysiological and hemodynamic resting-state connectivity are potential predictors of neurofeedback performance and are meaningfully coupled. This investigation motivates the use of joint EEG-fNIRS connectivity as outcome predictors, as well as a tool for functional connectivity coupling investigation.

The emerging role of artificial intelligence in adult spinal deformity

Artificial intelligence (AI) refers to computer-based technologies that seek to replicate human intelligence by allowing software to make decisions and provide recommendations based on the analysis of large datasets. Present applications of AI in spine deformity surgery have focused on improving safety and efficacy by automating, standardizing, and facilitating data guided approaches. In this review, the authors focus on 3 types of AI technology: 1) Surgical classification, 2) individualized outcome prediction, and 3) surgical planning. It is anticipated that AI will become an essential part of the preoperative, intraoperative, and postoperative phases of adult spinal deformity surgery.

Personalized neurorehabilitative precision medicine: from data to therapies (MWKNeuroReha) – a multi-centre prospective observational clinical trial to predict long-term outcome of patients with acute motor stroke

BackgroundStroke is one of the most frequent diseases, and half of the stroke survivors are left with permanent impairment. Prediction of individual outcome is still difficult. Many but not all patients with stroke improve by approximately 1.7 times the initial impairment, that has been termed proportional recovery rule. The present study aims at identifying factors predicting motor outcome after stroke more accurately than before, and observe associations of rehabilitation treatment with outcome.MethodsThe study is designed as a multi-centre prospective clinical observational trial. An extensive primary data set of clinical, neuroimaging, electrophysiological, and laboratory data will be collected within 96 h of stroke onset from patients with relevant upper extremity deficit, as indexed by a Fugl-Meyer-Upper Extremity (FM-UE) score ≤ 50. At least 200 patients will be recruited. Clinical scores will include the FM-UE score (range 0–66, unimpaired function is indicated by a score of 66), Action Research Arm Test, modified Rankin Scale, Barthel Index and Stroke-Specific Quality of Life Scale. Follow-up clinical scores and applied types and amount of rehabilitation treatment will be documented in the rehabilitation hospitals. Final follow-up clinical scoring will be performed 90 days after the stroke event. The primary endpoint is the change in FM-UE defined as 90 days FM-UE minus initial FM-UE, divided by initial FM-UE impairment. Changes in the other clinical scores serve as secondary endpoints. Machine learning methods will be employed to analyze the data and predict primary and secondary endpoints based on the primary data set and the different rehabilitation treatments.DiscussionIf successful, outcome and relation to rehabilitation treatment in patients with acute motor stroke will be predictable more reliably than currently possible, leading to personalized neurorehabilitation. An important regulatory aspect of this trial is the first-time implementation of systematic patient data transfer between emergency and rehabilitation hospitals, which are divided institutions in Germany.Trial registrationThis study was registered at ClinicalTrials.gov (NCT04688970) on 30 December 2020.

Validation of Adult Spinal Deformity Surgical Outcome Prediction Tools in Adult Symptomatic Lumbar Scoliosis.

A post hoc analysis. Advances in machine learning (ML) have led to tools offering individualized outcome predictions for adult spinal deformity (ASD). Our objective is to examine the properties of these ASD models in a cohort of adult symptomatic lumbar scoliosis (ASLS) patients. ML algorithms produce patient-specific probabilities of outcomes, including major complication (MC), reoperation (RO), and readmission (RA) in ASD. External validation of these models is needed. Thirty-nine predictive factors (12 demographic, 9 radiographic, 4 health-related quality of life, 14 surgical) were retrieved and entered into web-based prediction models for MC, unplanned RO, and hospital RA. Calculated probabilities were compared with actual event rates. Discrimination and calibration were analyzed using receiver operative characteristic area under the curve (where 0.5=chance, 1=perfect) and calibration curves (Brier scores, where 0.25=chance, 0=perfect). Ninety-five percent confidence intervals are reported. A total of 169 of 187 (90%) surgical patients completed 2-year follow up. The observed rate of MCs was 41.4% with model predictions ranging from 13% to 68% (mean: 38.7%). RO was 20.7% with model predictions ranging from 9% to 54% (mean: 30.1%). Hospital RA was 17.2% with model predictions ranging from 13% to 50% (mean: 28.5%). Model classification for all three outcome measures was better than chance for all [area under the curve=MC 0.6 (0.5-0.7), RA 0.6 (0.5-0.7), RO 0.6 (0.5-0.7)]. Calibration was better than chance for all, though best for RA and RO (Brier Score=MC 0.22, RA 0.16, RO 0.17). ASD prediction models for MC, RA, and RO performed better than chance in a cohort of adult lumbar scoliosis patients, though the homogeneity of ASLS affected calibration and accuracy. Optimization of models require samples with the breadth of outcomes (0%-100%), supporting the need for continued data collection as personalized prediction models may improve decision-making for the patient and surgeon alike.

Development of a novel signature derived from single cell RNA-sequencing for preoperative prediction of lymph node metastasis in head and neck squamous cell carcinoma.

Lymph node metastasis (LNM) is considered as an adverse prognostic indicator for cancer patients. Preoperative knowledge of LNM is valuable for pretreatment decision making. Here, we sought to develop and validate an LNM signature for preoperative prediction of LNM in patients with head and neck squamous cell carcinoma (HNSCC). By studying single cell RNA-sequencing data (scRNA-seq), differentially expressed mRNA were selected and analyzed through univariate logistic regression and least absolute shrinkage and selection operator (LASSO) to identify an LNM signature. Multivariate logistic regression was utilized to establish an LNM nomogram incorporating LNM signature and T-classification. The LNM signature was significantly associated with lymph node status and prognosis. The LNM signature and LNM nomogram displayed a robust predictive effect. Our study reveals that LNM signature is a powerful biomarker for preoperative prediction of LNM in patients with HNSCC, which may be effective to realize individualized outcome prediction.

Abstract 5789: Multi-omic artificial intelligence outcome modeling of ovarian cancer, phase I: Whole exome and whole transcriptome data

Abstract Background: Over a decade ago, the Cancer Genome Atlas (TCGA) provided the initial genomic characterization of ovarian cancer with targeted exome capture and sequencing. Unlike other TCGA analysis, they were unable to identify prognostic mutational profiles outside of BRCA status. There has been limited characterization of the ovarian cancer genomic profile since. Our objective presented here was to perform whole exome and whole transcriptome analysis of 241 ovarian cancer samples and compare to the TCGA dataset. This is the first phase of a muti-step ongoing analysis wherein we will input and correlate the complete genomic profile, complete patient outcome data, and immunohistochemical staining into a multi-omic artificial intelligence (AI) machine learning model with the aim of improved individualized outcome prediction. Methods: Tumor samples from 2000-2016 were obtained at time of surgery under approved University of Pittsburgh approved IRB consent. Whole exome and whole transcriptome sequencing were performed in collaboration with Helomics Corporation. Sequencing analysis was compared to TCGA data. Results: 241 patient samples underwent sequencing analysis. Similar to TCGA, most mutations were missense. I am having a difficulty interpreting the magee vs tcga comparison graphs, how to discuss the TP53 and BRCA comparison without using the lollipop charts and highlighting the rna-seq data into written form. Please add. Conclusions: We present our findings of one of the largest molecular characterizations of ovarian cancer. Similar to the TCGA, there is noted heterogeneity to the genomic profile of ovarian cancer. Multi-omic AI outcome modeling has the potential to overcome the gap defining prognostic sub-groups so that we can tailor therapies to the individual Citation Format: Brian Orr, Robert P. Edwards, Mackenzy Radolec. Multi-omic artificial intelligence outcome modeling of ovarian cancer, phase I: Whole exome and whole transcriptome data [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 5789.

Development and Validation of a Clinical-Based Signature to Predict the 90-Day Functional Outcome for Spontaneous Intracerebral Hemorrhage.

We aimed to develop and validate an objective and easy-to-use model for identifying patients with spontaneous intracerebral hemorrhage (ICH) who have a poor 90-day prognosis. This three-center retrospective study included a large cohort of 1,122 patients with ICH who presented within 6 h of symptom onset [training cohort, n = 835; internal validation cohort, n = 201; external validation cohort (center 2 and 3), n = 86]. We collected the patients’ baseline clinical, radiological, and laboratory data as well as the 90-day functional outcomes. Independent risk factors for prognosis were identified through univariate analysis and multivariate logistic regression analysis. A nomogram was developed to visualize the model results while a calibration curve was used to verify whether the predictive performance was satisfactorily consistent with the ideal curve. Finally, we used decision curves to assess the clinical utility of the model. At 90 days, 714 (63.6%) patients had a poor prognosis. Factors associated with prognosis included age, midline shift, intraventricular hemorrhage (IVH), subarachnoid hemorrhage (SAH), hypodensities, ICH volume, perihematomal edema (PHE) volume, temperature, systolic blood pressure, Glasgow Coma Scale (GCS) score, white blood cell (WBC), neutrophil, and neutrophil-lymphocyte ratio (NLR) (p < 0.05). Moreover, age, ICH volume, and GCS were identified as independent risk factors for prognosis. For identifying patients with poor prognosis, the model showed an area under the receiver operating characteristic curve of 0.874, 0.822, and 0.868 in the training cohort, internal validation, and external validation cohorts, respectively. The calibration curve revealed that the nomogram showed satisfactory calibration in the training and validation cohorts. Decision curve analysis showed the clinical utility of the nomogram. Taken together, the nomogram developed in this study could facilitate the individualized outcome prediction in patients with ICH.

Modified dynamic risk stratification system further predicts individual outcome in patients with intermediate-risk papillary thyroid cancer

ObjectiveWe assessed the contribution of initial treatment response to further refining prediction of individual outcomes in intermediate-risk papillary thyroid cancer (PTC) on the American Thyroid Association (ATA) risk stratification system. Dynamic risk stratification (DRS) as originally proposed by Tuttle et al. in 2010 was modified to also include serum antithyroglobulin antibodies (TgAb) as a surrogate marker of the likelihood of persistent disease, specifically in patients with thyroglobulin assay interference by TgAb. MethodsThree hundred and seventy-three patients with ATA intermediate-risk PTC were enrolled retrospectively upon reviewing medical records. Patients were followed at the National Cancer Institute in Bogota, Colombia after being treated with total thyroidectomy and I-131 therapy between 2009 and 2013. Best response to initial therapy was classified as excellent, indeterminate, biochemically incomplete or structurally incomplete. Final disease status after a median follow-up of 7.1 years was classified as no evidence of disease (NED), indeterminate, or persistent disease (either biochemically or structurally). The rate of recurrence was determined in excellent responders. ResultsExcellent response was achieved by 164 patients (43.9%). At a median follow-up of 42 months, 19 (11.6%) had experienced recurrence. 87.4% of initially excellent responders available at the final checkpoint were NED, compared to 28% of those with biochemically or structurally incomplete response and to 60.2% of all ATA intermediate-risk PTC patients in our cohort. ConclusionsModified DRS further predicted individual outcomes in intermediate-risk PTC, potentially allowing ongoing management to be tailored accordingly.

Delivering patient-centered care through shared decision making in overactive bladder.

IntroductionMen and women living with overactive bladder (OAB) face many treatment decisions as they progress through the treatment pathway. Decisions to pursue specific therapies are highly preference sensitive and ideal for shared decision making (SDM). The aim of this narrative review is to provide urologists with a practical summary of methods to elicit preferences and facilitate SDM to promote patient‐centered care for OAB.MethodsWe explore OAB as a preference sensitive condition through a review of treatment outcomes and present available data on prediction tools, patient preferences, and decision aids. We propose a paradigm for applying Everyday SDM to OAB care.ResultsClinical outcome data points to equipoise (balanced outcomes) between options for first‐, second‐, and third‐line OAB therapies, making OAB preference sensitive and appropriate for SDM. Methods to personalize care through individualized outcome prediction calculators and tools to elicit patient preferences are emerging. While patient information about OAB is readily available, we identified few OAB decision aids that facilitate patient preference elicitation and SDM.ConclusionsOAB is a preference sensitive condition, where treatment is largely based on the patient's preferences and values. SDM is an ideal approach to supporting patients through these treatment decisions. We propose the application of Everyday SDM, a personalized, clinically efficient methodology as a method to support patient‐centered OAB care.