Predictor Of Clinical Outcome Research Articles

Transcranial Magnetic Stimulation-Based Machine Learning Prediction of Tumor Grading in Motor-Eloquent Gliomas.

Navigated transcranial magnetic stimulation (nTMS) is a well-established preoperative mapping tool for motor-eloquent glioma surgery. Machine learning (ML) and nTMS may improve clinical outcome prediction and histological correlation. This was a retrospective cohort study of patients who underwent surgery for motor-eloquent gliomas between 2018 and 2022. Ten healthy subjects were included. Preoperative nTMS-derived variables were collected: resting motor threshold (RMT), interhemispheric RMT ratio (iRMTr)-abnormal if above 10%-and cortical excitability score-number of abnormal iRMTrs. World Health Organization (WHO) grade and molecular profile were collected to characterize each tumor. ML models were fitted to the data after statistical feature selection to predict tumor grade. A total of 177 patients were recruited: WHO grade 2-32 patients, WHO grade 3-65 patients, and WHO grade 4-80 patients. For the upper limb, abnormal iRMTr were identified in 22.7% of WHO grade 2, 62.5% of WHO grade 3, and 75.4% of WHO grade 4 patients. For the lower limb, iRMTr was abnormal in 23.1% of WHO grade 2, 67.6% of WHO grade 3%, and 63.6% of WHO grade 4 patients. Cortical excitability score (P = .04) was statistically significantly related with WHO grading. Using these variables as predictors, the ML model had an accuracy of 0.57 to predict WHO grade 4 lesions. In subgroup analysis of high-grade gliomas vs low-grade gliomas, the accuracy for high-grade gliomas prediction increased to 0.83. The inclusion of molecular data into the model-IDH mutation and 1p19q codeletion status-increases the accuracy of the model in predicting tumor grading (0.95 and 0.74, respectively). ML algorithms based on nTMS-derived interhemispheric excitability assessment provide accurate predictions of HGGs affecting the motor pathway. Their accuracy is further increased when molecular data are fitted onto the model paving the way for a joint preoperative approach with radiogenomics.

Optimal intraventricular hemorrhage volume cutoff for predicting poor outcome in patients with intracerebral hemorrhage

Background and objectivesThe prognosis of patients with spontaneous intracerebral hemorrhage (ICH) is often influenced by hematoma volume, a well-established predictor of poor outcome. However, the optimal intraventricular hemorrhage (IVH) volume cutoff for predicting poor outcome remains unknown. MethodsWe analyzed 313 patients with spontaneous ICH not undergoing evacuation, including 7 cases with external ventricular drainage (EVD). These patients underwent a baseline CT scan, followed by a 24-hour CT scan for measurement of both hematoma and IVH volume. We defined hematoma growth as hematoma growth > 33 % or 6 mL at follow-up CT, and poor outcome as modified Rankin Scale score≥3 at three months. Cutoffs with optimal sensitivity and specificity for predicting poor outcome were identified using receiver operating curves. ResultsThe receiver operating characteristic analysis identified 6 mL as the optimal cutoff for predicting poor outcome. IVH volume> 6 mL was observed in 53 (16.9 %) of 313 patients. Patients with IVH volume>6 mL were more likely to be older and had higher NIHSS score and lower GCS score than those without. IVH volume>6 mL (adjusted OR 2.43, 95 % CI 1.13-5.30; P = 0.026) was found to be an independent predictor of poor clinical outcome at three months in multivariable regression analysis. ConclusionsOptimal IVH volume cutoff represents a powerful tool for improving the prediction of poor outcome in patients with ICH, particularly in the absence of clot evacuation or common use of EVD. Small amounts of intraventricular blood are not independently associated with poor outcome in patients with intracerebral hemorrhage. The utilization of optimal IVH volume cutoffs may improve the clinical trial design by targeting ICH patients that will obtain maximal benefit from therapies.

Clinical outcome prediction with an automated EEG trend, Brain State of the Newborn, after perinatal asphyxia

ObjectiveTo evaluate the utility of a fully automated deep learning -based quantitative measure of EEG background, Brain State of the Newborn (BSN), for early prediction of clinical outcome at four years of age. MethodsThe EEG monitoring data from eighty consecutive newborns was analyzed using the automatically computed BSN trend. BSN levels during the first days of life (a of total 5427 hours) were compared to four clinical outcome categories: favorable, cerebral palsy (CP), CP with epilepsy, and death. The time dependent changes in BSN-based prediction for different outcomes were assessed by positive/negative predictive value (PPV/NPV) and by estimating the area under the receiver operating characteristic curve (AUC). ResultsThe BSN values were closely aligned with four visually determined EEG categories (p < 0·001), as well as with respect to clinical milestones of EEG recovery in perinatal Hypoxic Ischemic Encephalopathy (HIE; p < 0·003). Favorable outcome was related to a rapid recovery of the BSN trend, while worse outcomes related to a slow BSN recovery. Outcome predictions with BSN were accurate from 6 to 48 hours of age: For the favorable outcome, the AUC ranged from 95 to 99% (peak at 12 hours), and for the poor outcome the AUC ranged from 96 to 99% (peak at 12 hours). The optimal BSN levels for each PPV/NPV estimate changed substantially during the first 48 hours, ranging from 20 to 80. ConclusionsWe show that the BSN provides an automated, objective, and continuous measure of brain activity in newborns. SignificanceThe BSN trend discloses the dynamic nature that exists in both cerebral recovery and outcome prediction, supports individualized patient care, rapid stratification and early prognosis.

Prognostic Value of Pretreatment Fetal Hemoglobin Levels in Patients with Myelodysplastic Syndromes and Acute Myeloid Leukemia Treated with Azacitidine: A Single-center Retrospective Study.

Objective Azacitidine (AZA) has been the standard of care for elderly patients with high-risk myelodysplastic syndromes (MDS). However, reliable clinical predictors of outcome have yet to be identified. The prognostic value of fetal hemoglobin (HbF) levels has been reported for decitabine therapy. We evaluated pretreatment HbF levels in AZA monotherapy as a prognostic marker in MDS/acute myeloid leukemia (AML). Methods This study included chemotherapy-naïve patients who had received seven-day treatment schedules of AZA and whose HbF levels were measured at the onset of treatment between March 2011 and July 2020. Patients were grouped into HbF-normal (<1.0%) or HbF-elevated (≥1.0%) groups. Responses were classified according to the International Working Group 2006 criteria. Patients Twenty-nine patients were included and classified as having either MDS (n=21), chronic myelomonocytic leukemia (n=5), myelodysplastic/myeloproliferative neoplasm unclassifiable (n=1), or AML with <30% marrow blasts (n=2) based on the World Health Organization 2016 diagnostic criteria. According to the revised International Prognostic Scoring System classification, 20/29 patients were at intermediate, high, or very high risk. Pretreatment HbF levels were elevated in 13/29 patients. Results The median follow-up duration was 13.0 (range 1.5-93.5) months. The HbF-elevated group was associated with a significantly higher hematologic improvement rate (76.9% vs. 25%, p=0.009) and better overall survival (median, 21.0 vs. 13.0 months, p=0.048) than the HbF-normal group. Conclusion These results suggest that elevated pretreatment HbF levels can predict better outcomes in patients with MDS/AML treated with AZA.

Developing Novel Genomic Risk Stratification Models in Soft Tissue and Uterine Leiomyosarcoma.

Leiomyosarcomas (LMS) are clinically and molecularly heterogeneous tumors. Despite recent large-scale genomic studies, current LMS risk stratification is not informed by molecular alterations. We propose a clinically applicable genomic risk stratification model. We performed comprehensive genomic profiling in a cohort of 195 soft tissue LMS (STLMS), 151 primary at presentation, and a control group of 238 uterine LMS (ULMS), 177 primary at presentation, with at least 1-year follow-up. In STLMS, French Federation of Cancer Centers (FNCLCC) grade but not tumor size predicted progression-free survival (PFS) or disease-specific survival (DSS). In contrast, in ULMS, tumor size, mitotic rate, and necrosis were associated with inferior PFS and DSS. In STLMS, a 3-tier genomic risk stratification performed well for DSS: high risk: co-occurrence of RB1 mutation and chr12q deletion (del12q)/ATRX mutation; intermediate risk: presence of RB1 mutation, ATRX mutation, or del12q; low risk: lack of any of these three alterations. The ability of RB1 and ATRX alterations to stratify STLMS was validated in an external AACR GENIE cohort. In ULMS, a 3-tier genomic risk stratification was significant for both PFS and DSS: high risk: concurrent TP53 mutation and chr20q amplification/ATRX mutations; intermediate risk: presence of TP53 mutation, ATRX mutation, or amp20q; low risk: lack of any of these three alterations. Longitudinal sequencing showed that most molecular alterations were early clonal events that persisted during disease progression. Compared with traditional clinicopathologic models, genomic risk stratification demonstrates superior prediction of clinical outcome in STLMS and is comparable in ULMS.

The value of minimal residual disease and IKZF1 deletion for predicting prognosis in adult patients with B-cell acute lymphoblastic leukemia

Objective: To reassess the prognostic value of minimal residual disease (MRD) and IKZF1 gene deletions in adults with B-cell acute lymphoblastic leukemia (B-ALL) who received pediatric-specific chemotherapy regimens during the Nanfang Hospital PDT-ALL-2016 trial. Methods: We retrospectively analyzed the prognosis of 149 adult patients with B-ALL who were admitted to Nanfang Hospital from January 2016 to September 2020. Prognostic factors were identified using Cox regression models. Results: The complete remission rate was 93.2% in 149 patients, with a 5-year overall survival (OS) rate of (54.3±5.0) % and a cumulative incidence of relapse (CIR) of (47.5±5.2) %. The Cox regression analysis revealed that MRD positivity at day 45 (MRD(3)) after induction therapy was independently associated with relapse risk (HR=2.535, 95%CI 1.122-5.728, P=0.025). Deletion of IKZF1 gene was independently associated with mortality risk (HR=1.869, 95%CI 1.034-3.379, P=0.039). Based on MRD(3) and IKZF1 gene status, we categorized adult patients with B-ALL into the low-risk (MRD(3)-negative and IKZF1 gene deletion-negative) and high-risk (MRD(3)-positive and/or IKZF1 gene wild type) groups. The 5-year OS and CIR rates were (45.5±6.0) % vs (69.4±8.6) % (P<0.001) and (61.6±8.3) % vs (25.5±6.5) % (P<0.001), respectively, in the high-risk and low-risk groups, respectively. The multivariate analysis showed that the high-risk group was an independent risk factor for OS (HR=3.937, 95%CI 1.975-7.850, P<0.001) and CIR (HR=4.037, 95%CI 2.095-7.778, P<0.001) . Conclusion: The combined use of MRD and IKZF1 gene in prognostic stratification can improve clinical outcome prediction in adult patients with B-ALL, helping to guide their treatment.

TCRpred: incorporating T-cell receptor repertoire for clinical outcome prediction.

T-cell receptor (TCR) plays critical roles in recognizing antigen peptides and mediating adaptive immune response against disease. High-throughput technologies have enabled the sequencing of TCR repertoire at the single nucleotide level, allowing researchers to characterize TCR sequences with high resolutions. The TCR sequences provide important information about patients' adaptive immune system, and have the potential to improve clinical outcome prediction. However, it is challenging to incorporate the TCR repertoire data for prediction, because the data is unstructured, highly complex, and TCR sequences vary widely in their compositions and abundances across different individuals. We introduce TCRpred, an analytic tool for incorporating TCR repertoire for clinical outcome prediction. The TCRpred is able to utilize features that can be extracted from the TCR amino acid sequences, as well as features that are hidden in the TCR amino acid sequences and are hard to extract. Simulation studies show that the proposed approach has a good performance in predicting clinical outcome and tends to be more powerful than potential alternative approaches. We apply the TCRpred to real cancer datasets and demonstrate its practical utility in clinical outcome prediction.

Assessment of fatty infiltration of the hamstring muscles in chronic proximal hamstring ruptures and effect on clinical outcomes after surgical repair: a novel application of the Goutallier classification.

Increased time to surgery has been previously associated with poorer clinical outcomes after surgical treatment of proximal hamstring ruptures, though the etiology remains unclear. The purpose of this study was to evaluate whether degree of muscle atrophy, as assessed using the Goutallier classification system, is associated with worse outcomes following surgical treatment of chronic proximal hamstring ruptures. This was a retrospective case series of patients who underwent repair of proximal hamstring ruptures from 2012 to 2020 with minimum 2-year follow-up. Patients were included if they underwent primary repair of a proximal hamstring rupture ≥ 6weeks after the date of injury and had accessible preoperative magnetic resonance imaging (MRI). Exclusion criteria were allograft reconstruction, endoscopic repair, or prior ipsilateral hip surgery. Patients were administered validated surveys: the modified Harris Hip Score (mHHS) and Perth Hamstring Assessment Tool (PHAT). Fatty atrophy on preoperative MRI was independently graded by two musculoskeletal radiologists using the Goutallier classification. Multivariate regression analysis was performed to evaluate associations of preoperative characteristics with muscle atrophy, as well as mHHS and PHAT scores. Complete data sets were obtained for 27 patients. A majority of this cohort was male (63.0%), with a mean age of 51.5 ± 11.8years and BMI of 26.3 ± 3.8. The mean follow-up time was 62.6 ± 23.1months, and the mean time from injury-to-surgery was 20.4 ± 15.3weeks. The Goutallier grading inter-reader weighted kappa coefficient was 0.655. Regression analysis demonstrated that atrophy was not significantly associated with PHAT (p = 0.542) or mHHS (p = 0.574) at latest follow-up. Increased age was significantly predictive of muscle atrophy (β = 0.62, p = 0.005) and was also found to be a significant predictor of poorer mHHS (β = - 0.75; p = 0.037). The degree of atrophy was not found to be an independent predictor of clinical outcomes following repair of chronic proximal hamstring ruptures. Increasing age was significantly predictive of increased atrophy and poorer patient-reported outcomes.

Effects of ovarian response prediction index and follicle-oocyte index on pregnancy outcomes: a retrospective cohort study of 12,218 fresh transfer cycles

Objective: To investigate the potential relationships among the ovarian response prediction index (ORPI), follicle-oocyte index (FOI), and clinical pregnancy rate (CPR) in women undergoing their first in vitro fertilization/intracytoplasmic sperm injection-embryo transfer (IVF/ICSI-ET) fresh cycle transfer. Methods: In this retrospective cohort study, we included 12,218 women who underwent their first IVF/ICSI-ET cycle between December 2014 and January 2021. The primary and secondary outcomes of our study were CPR and cumulative live birth rate (CLBR), respectively. The data were divided into three groups according to the ORPI and FOI tertiles. Multivariate logistic regression analyses, stratification analyses, interaction, restricted cubic splines, and receiver operating characteristic (ROC) curves were constructed to identify the relationships among ORPI, FOI, and CPR. Results: A statistically significant increase in CPR was detected from the lowest to the highest tertile group (ORPI: 48.12%, 54.07%, and 53.47%, P &lt;0.001; FOI:49.99%, 52.95%, and 52.71%, P=0.012). A higher CLBR was observed in the high group (ORPI: 38.63%, 44.62%, and 44.19%, P &lt;0.001; FOI: 41.02%, 43.78%, and 42.59%, P=0.039). Multivariate logistic regression analysis revealed no statistically significant differences between ORPI, FOI, and neither CPR [odds ratio (OR) (95% confidence interval (CI), 0.99 (0.97-1.00) vs. (1.02 (0.84-1.24)] nor CLBR [OR (95% CI), 0.99 (0.97-1.01) vs. 0.99 (0.81-1.20)]. No significant association was found among FOI, ORPI, and CPR, even in the subgroups. Restricted cubic spline analyses indicated the existence of a nonlinear relationship across the entire range of FOI and ORPI. The ORPI and FOI variables had poor predictive ability (AUC&lt; 0.60) for CPR. Conclusions: Both ORPI and FOI are not reliable predictors of clinical pregnancy or live birth outcomes in fresh embryo transfers. Clinicians and researchers should avoid using FOI and ORPI to assess pregnancy outcomes after fresh embryo transfer because of their limited relevance and predictive value.

Incidence and Predictors of Worsening Renal Function in Edoxaban-Treated Atrial Fibrillation Patients Within ETNA-AF-Europe Registry

BackgroundManaging patients with atrial fibrillation (AF) and worsening renal function (WRF) remains a clinical challenge due to the need of dose adjustment of non-vitamin K antagonist oral anticoagulants. ObjectivesTo determine the incidence of WRF in patients with AF treated with edoxaban, the association of WRF with clinical outcomes, and predictors of WRF and clinical outcomes in these patients. MethodsThis is a subanalysis of the Edoxaban Treatment in routiNe clinical prActice for patients with non-valvular Atrial Fibrillation in Europe study (NCT02944019), an observational study of edoxaban-treated patients with AF. WRF was defined as a ≥25% reduction in creatinine clearance between baseline and 2 years. ResultsOf the 9,054 patients included (69% of the total 13,133 enrolled), most did not experience WRF (90.3%) during the first 2 years of follow-up. WRF occurred in 9.7% of patients. Patients with WRF had significantly higher rates of all-cause death (3.88%/y vs 1.88%/y; P < 0.0001), cardiovascular death (2.09%/y vs 0.92%/y; P < 0.0001), and major bleeding (1.51%/y vs 0.98%/y; P = 0.0463) compared with those without WRF. Rates of intracranial hemorrhage (0.18%/y vs 0.18%/y) and of any stroke/systemic embolic events were low (0.90%/y vs 0.69%/y; P = 0.3161) in both subgroups. The strongest predictors of WRF were a high CHA2DS2-VASc score, high baseline creatinine clearance, low body weight, and older age. Most predictors of WRF were also predictors of clinical outcomes. ConclusionsWRF occurred in approximately 10% of edoxaban-treated AF patients. Rates of death and major bleeding were significantly higher in patients with WRF than without. Stroke events were low in both subgroups.

Treatment-Sensitive and Treatment-Dependent Chronic Graft-versus-Host Disease Yield Superior Failure-Free and Overall Survival Compared to Treatment-Resistant Chronic Graft-versus-Host Disease

Response to treatment of chronic graft-versus-host disease (cGVHD) may help predict prognosis and outcomes. We hypothesized that the response of cGVHD to treatment and the ability to taper immunosuppression define distinct treatment response categories that differ in terms of risk factors and prognosis. Our aim was to determine specific clinical characteristics and outcomes associated with 3 distinct cGVHD treatment response groups based on the response to and duration of immunosuppressive therapy (IST) as treatment-sensitive (TS), treatment-resistant (TR), and treatment-dependent (TD) cGVHD. This retrospective single-institution cohort study included 1142 consecutive adult and pediatric recipients of allogeneic hematopoietic cell transplantation (HCT) performed for malignant and nonmalignant disorders at the University of Minnesota between 2008 and 2016. All donor, graft, conditioning regimen, and GVHD prophylaxis strategies were included, but only patients who commenced systemic treatment within 30 days of cGVHD diagnosis were included. A total of 185 patients who developed cGVHD necessitating IST within 30 days of cGVHD diagnosis were included in this analysis. At 1 year after cGVHD onset, 13% of the patients were TS, 27% were TD, and 60% were TR (including 14% deceased), whereas at 2 years after cGVHD onset, 29% were TS, 5% were TD, and 66% were TR (including 22% deceased). In a landmark analysis starting at 1 year after cGVHD onset, 5-year failure-free survival (FFS) and overall survival (OS) were lowest in the TR group (FFS, 38%; OS, 70%), with comparable outcomes in the TD (74% and 82%, respectively) and TS (79% for both) groups. Compared to no cGVHD, TR cGVHD was associated with worse OS at 5 years after cGVHD (hazard ratio, 2.09 versus no cGVHD; 95% confidence interval, 1.3 to 3.3; P < .01). Our findings suggest that refining cGVHD classification into 3 treatment response states defines important predictors of early and late clinical outcomes and identifies patients needing more effective treatment.

The clinical and genetic spectrum of inherited glycosylphosphatidylinositol deficiency disorders.

Inherited glycosylphosphatidylinositol deficiency disorders (IGDs) are a group of rare multisystem disorders arising from pathogenic variants in glycosylphosphatidylinositol anchor pathway (GPI-AP) genes. Despite associating 24 of at least 31 GPI-AP genes with human neurogenetic disease, prior reports are limited to single genes without consideration of the GPI-AP as a whole and with limited natural history data. In this multinational retrospective observational study, we systematically analyse the molecular spectrum, phenotypic characteristics, and natural history of 83 individuals from 75 unique families with IGDs, including 70 newly reported individuals: the largest single cohort to date. Core clinical features were developmental delay or intellectual disability (DD/ID, 90%), seizures (83%), hypotonia (72%), and motor symptoms (64%). Prognostic and biologically significant neuroimaging features included cerebral atrophy (75%), cerebellar atrophy (60%), callosal anomalies (57%), and symmetric restricted diffusion of the central tegmental tracts (60%). Sixty-one individuals had multisystem involvement including gastrointestinal (66%), cardiac (19%), and renal (14%) anomalies. Though dysmorphic features were appreciated in 82%, no single dysmorphic feature had a prevalence >30%, indicating substantial phenotypic heterogeneity. Follow-up data were available for all individuals, 15 of whom were deceased at the time of writing. Median age at seizure onset was 6 months. Individuals with variants in synthesis stage genes of the GPI-AP exhibited a significantly shorter time to seizure onset than individuals with variants in transamidase and remodelling stage genes of the GPI-AP (P=0.046). Forty individuals had intractable epilepsy. The majority of individuals experienced delayed or absent speech (95%); motor delay with non-ambulance (64%); and severe-to-profound DD/ID (59%). Individuals with a developmental epileptic encephalopathy (51%) were at greater risk of intractable epilepsy (P=0.003), non-ambulance (P=0.035), ongoing enteral feeds (P<0.001), and cortical visual impairment (P=0.007). Serial neuroimaging showed progressive cerebral volume loss in 87.5% and progressive cerebellar atrophy in 70.8%, indicating a neurodegenerative process. Genetic analyses identified 93 unique variants (106 total), including 22 novel variants. Exploratory analyses of genotype-phenotype correlations using unsupervised hierarchical clustering identified novel genotypic predictors of clinical phenotype and long-term outcome with meaningful implications for management. In summary, we expand both the mild and severe phenotypic extremities of the IGDs; provide insights into their neurological basis; and, vitally, enable meaningful genetic counselling for affected individuals and their families.

Hemorrhage Volume Drives Early Brain Injury and Outcome in Poor-Grade Aneurysmal SAH.

Early brain injury is a major determinant of clinical outcome in poor-grade (World Federation of Neurosurgical Societies [WFNS] IV-V) aneurysmal SAH and is radiologically defined by global cerebral edema. Little is known, though, about the effect of global intracranial hemorrhage volume on early brain injury development and clinical outcome. Data from the multicentric prospective Poor-Grade Aneurysmal Subarachnoid Hemorrhage (POGASH) Registry of consecutive patients with poor-grade aneurysmal SAH admitted from January 1, 2015, to August 31, 2022, was retrospectively evaluated. Poor grade was defined according to the worst-pretreatment WFNS grade. Global intracranial hemorrhage volume as well as the volumes of intracerebral hemorrhage, intraventricular hemorrhage, and SAH were calculated by means of analytic software in a semiautomated setting. Outcomes included severe global cerebral edema (defined by Subarachnoid Hemorrhage Early Brain Edema Score grades 3-4), in-hospital mortality (mRS 6), and functional independence (mRS 0-2) at follow-up. Among 400 patients (median global intracranial hemorrhage volume of 91 mL; interquartile range, 59-128), severe global cerebral edema was detected in 218/400 (54.5%) patients. One hundred twenty-three (30.8%) patients died during the acute phase of hospitalization. One hundred fifty-five (38.8%) patients achieved mRS 0-2 at a median of 13 (interquartile range, 3-26) months of follow-up. Multivariable analyses showed global intracranial hemorrhage volume as independently associated with severe global cerebral edema (adjusted OR, 1.009; 95% CI, 1.004-1.014; P < .001), mortality (adjusted OR, 1.006; 95% CI, 1.001-1.01; P = .018) and worse clinical outcome (adjusted OR, 0.992; 95% CI, 0.98-0.996; P < .010). The effect of global intracranial hemorrhage volume on clinical-radiologic outcomes changed significantly according to different age groups (younger than 50, 50-70, older than 70 year of age). Volumes of intracerebral hemorrhage, intraventricular hemorrhage, and SAH affected the 3 predefined outcomes differently. Intracerebral hemorrhage volume independently predicted global cerebral edema and long-term outcome, intraventricular hemorrhage volume predicted mortality and long-term outcome, and SAH volume predicted long-term clinical outcome. Global intracranial hemorrhage volume plays a pivotal role in global cerebral edema development and emerged as an independent predictor of both mortality and long-term clinical outcome. Aging emerged as a reducing predictor in the relationship between global intracranial hemorrhage volume and global cerebral edema.

How do stochastic processes and genetic threshold effects explain incomplete penetrance and inform causal disease mechanisms?

Incomplete penetrance is the rule rather than the exception in Mendelian disease. In syndromic monogenic disorders, phenotypic variability can be viewed as the combination of incomplete penetrance for each of multiple independent clinical features. Within genetically identical individuals, such as isogenic model organisms, stochastic variation at molecular and cellular levels is the primary cause of incomplete penetrance according to a genetic threshold model. By defining specific probability distributions of causal biological readouts and genetic liability values, stochasticity and incomplete penetrance provide information about threshold values in biological systems. Ascertainment of threshold values has been achieved by simultaneous scoring of relatively simple phenotypes and quantitation of molecular readouts at the level of single cells. However, this is much more challenging for complex morphological phenotypes using experimental and reductionist approaches alone, where cause and effect are separated temporally and across multiple biological modes and scales. Here I consider how causal inference, which integrates observational data with high confidence causal models, might be used to quantify the relative contribution of different sources of stochastic variation to phenotypic diversity. Collectively, these approaches could inform disease mechanisms, improve predictions of clinical outcomes and prioritize gene therapy targets across modes and scales of gene function. This article is part of a discussion meeting issue 'Causes and consequences of stochastic processes in development and disease'.

Comparison of collateral status in anterior circulation acute ischemic stroke on single-phase and multiphase CT angiography in prediction of clinical and radiological outcome

Objectives Various collateral scoring systems are used to assess the collateral status on single or multiphase CT angiography (CTA) to forecast outcomes in anterior circulation acute ischemic stroke patients. Our study aimed to compare the predictive ability of these collateral scoring systems in determining clinical and radiological outcomes in patients with anterior circulation acute ischemic stroke. Material and Methods In this observational prospective study, data was obtained from December 2020 to June 2022 in consecutive acute ischemic stroke patients referred to our department for neuroimaging. The collateral scores were assessed using Tan and Menon scoring systems described for single and multiphase CTA, respectively. The correlations between various collateral scores, the National Institute of Health Stroke Scale (NIHSS), Modified Rankin Scale (mRS), and final infarct volume were studied. Receiver operating characteristics (ROC) curves and multivariate logistic regression analysis were performed to assess the predictive ability of scoring systems for clinical and radiological outcomes Results A total of 32 patients met the inclusion criteria. Both single- and multiphase collateral scores showed statistically significant negative correlations with clinical and radiological outcomes. Spearman correlation coefficient and p-value for the radiological outcome being -Tan score (r- -0.73, p- &lt; 0.001), single-phase Menon score (r- -0.81, p- &lt; 0.001), and multiphase Menon score (r- -0.79, p- &lt; 0.001). ROC curve analysis revealed that the multiphase Menon score performed slightly better than the single-phase Menon score (area under the curve [AUC], 0.815 vs 0.810) in predicting a favorable 90-day modified Rankin scale score. Conclusion Our study concluded that collateral status on both multiphase CTA (mCT) and conventional (Single phase arterial CTA) showed statistically significant results in the prediction of clinical and radiological outcomes.

Conventional and unconventional T-cell responses contribute to the prediction of clinical outcome and causative bacterial pathogen in sepsis patients.

Sepsis is characterized by a dysfunctional host response to infection culminating in life-threatening organ failure that requires complex patient management and rapid intervention. Timely diagnosis of the underlying cause of sepsis is crucial, and identifying those at risk of complications and death is imperative for triaging treatment and resource allocation. Here, we explored the potential of explainable machine learning models to predict mortality and causative pathogen in sepsis patients. By using a modelling pipeline employing multiple feature selection algorithms, we demonstrate the feasibility of identifying integrative patterns from clinical parameters, plasma biomarkers, and extensive phenotyping of blood immune cells. While no single variable had sufficient predictive power, models that combined five and more features showed a macro area under the curve (AUC) of 0.85 to predict 90-day mortality after sepsis diagnosis, and a macro AUC of 0.86 to discriminate between Gram-positive and Gram-negative bacterial infections. Parameters associated with the cellular immune response contributed the most to models predictive of 90-day mortality, most notably, the proportion of T cells among PBMCs, together with expression of CXCR3 by CD4+ T cells and CD25 by mucosal-associated invariant T (MAIT) cells. Frequencies of Vδ2+ γδ T cells had the most profound impact on the prediction of Gram-negative infections, alongside other T-cell-related variables and total neutrophil count. Overall, our findings highlight the added value of measuring the proportion and activation patterns of conventional and unconventional T cells in the blood of sepsis patients in combination with other immunological, biochemical, and clinical parameters.

The use of medial joint opening rather than mechanical axis deviation to determine the clinical outcomes after high tibial osteotomy.

The aim of this study was to evaluate whether achieving medial joint opening, as measured by the change in the joint line convergence angle (∆JLCA), is a better predictor of clinical outcomes after high tibial osteotomy (HTO) compared with the mechanical axis deviation, and to find individualized targets for the redistribution of load that reflect bony alignment, joint laxity, and surgical technique. This retrospective study analyzed 121 knees in 101 patients. Patient-reported outcome measures (PROMs) were collected preoperatively and one year postoperatively, and were analyzed according to the surgical technique (opening or closing wedge), postoperative mechanical axis deviation (deviations above and below 10% from the target), and achievement of medial joint opening (∆JLCA > 1°). Radiological parameters, including JLCA, mechanical axis deviation, and the difference in JLCA between preoperative standing and supine radiographs (JLCAPD), an indicator of medial soft-tissue laxity, were measured. Cut-off points for parameters related to achieving medial joint opening were calculated from receiver operating characteristic (ROC) curves. Patients in whom the medial joint opening was achieved had significantly better postoperative PROMs compared with those without medial opening (all p < 0.05). Patients who were outliers with deviation of > 10% from the target mechanical axis deviation had significantly similar PROMs compared with patients with an acceptable axis deviation (all p > 0.05). Medial joint opening was affected by postoperative mechanical axis deviation and JLCAPD. The influence of JLCAPD on postoperative axis deviation was more pronounced in a closing wedge than in an opening wedge HTO. Medial joint opening rather than the mechanical axis deviation determined the clinical outcome in patients who underwent HTO. The JLCAPD identified the optimal postoperative axis deviation necessary to achieve medial joint opening. For patients with increased laxity, lowering the target axis deviation is recommended to achieve medial joint opening. The target axis deviation should also differ according to the technique of undergoing HTO.

Hybrid artificial intelligence outcome prediction using features extraction from stress perfusion cardiac magnetic resonance images and electronic health records.

Prediction of clinical outcomes in coronary artery disease (CAD) has been conventionally achieved using clinical risk factors. The relationship between imaging features and outcome is still not well understood. This study aims to use artificial intelligence to link image features with mortality outcome. A retrospective study was performed on patients who had stress perfusion cardiac magnetic resonance (SP-CMR) between 2011 and 2021. The endpoint was all-cause mortality. Convolutional neural network (CNN) was used to extract features from stress perfusion images, and multilayer perceptron (MLP) to extract features from electronic health records (EHRs), both networks were concatenated in a hybrid neural network (HNN) to predict study endpoint. Image CNN was trained to predict study endpoint directly from images. HNN and image CNN were compared with a linear clinical model using area under the curve (AUC), F1 scores, and McNemar's test. Total of 1,286 cases were identified, with 201 death events (16%). The clinical model had good performance (AUC =80%, F1 score =37%). Best Image CNN model showed AUC =72% and F1 score =38%. HNN outperformed the other two models (AUC =82%, F1 score =43%). McNemar's test showed statistical difference between image CNN and both clinical model (P<0.01) and HNN (P<0.01). There was no significant difference between HNN and clinical model (P=0.15). Death in patients with suspected or known CAD can be predicted directly from stress perfusion images without clinical knowledge. Prediction can be improved by HNN that combines clinical and SP-CMR images.

A Risk Model for 28-Day in-Hospital Mortality in 173 COVID-19 Patients Admission to ICU: A Retrospective Study.

The surge in the number of patients diagnosed with COVID-19 since China's open-door policy has placed a huge burden on the public healthcare system, especially the intensive care system. This study's objective was to discover possible clinical outcome predictors in COVID-19 patients treated in intensive care units (ICUs) and to provide useful information for future preventative efforts and therapies. This retrospective study included 173 COVID-19 critically ill patients and reviewed the 28-day survival outcome in the First Affiliated Hospital of Nanjing Medical University. Competing risk analysis was performed to predict the cumulative incidence function (CIF) of mortality in hospital. The independent prognostic factors were identified by applying the Fine-Gray proportional subdistribution hazard model. Receiver operating characteristic (ROC) curves were used to evaluate model efficacy, and calibration curves were used to validate the model. Finally, we compared the competing risk model with the traditional proportional hazards model (Cox regression model) using CIF. Of these 173 patients, 66 (38.2%) survived, 55 (31.8%) died, and 52 (30.0%) discharged. In univariate analysis, 12 variables were significantly correlated with mortality. In multivariate analysis, Age, Neutrophil ratio, Direct Bilirubin (DBIL) and Renal disease were independent predictors of 28-day outcome. The ROC curve of the multivariate prediction model showed an AUC (area under the curve) of 0.790. The results of the calibration curve and the concordance index (C-index) show that the model has good discriminatory power. The competing risk model we applied was more accurate than the Cox model. We presented a more accurate multivariate prediction model for 28-day in-hospital mortality for ICU COVID-19 patients using a competing risk model.

Transurethral Resection of Bladder Tumor Outcomes Are Predicted by a 5-Item Frailty Index

ObjectiveTo evaluate the mFI-5 as a predictor of post-operative outcomes following transurethral resection of bladder tumor (TURBT). MethodsThe National Surgical Quality Improvement Program database was queried for TURBT cases from 2015-2019. mFI-5 scores were calculated by assigning a point to COPD, CHF, dependent functional status, hypertension, and diabetes. Patients were stratified by mFI-5 scores. Demographics and 30-day outcomes including Clavien-Dindo (CD) complications, mortality, and increased healthcare resource utilization (HCRU) were compared. HCRU outcomes included prolonged length of stay (PLOS), unplanned readmission (UR), and discharge to continued care (DCC). Multivariate regression assessed the predictive value of mFI-5 scores on outcomes. Results40,278 TURBT cases were identified (mFI-5 = 0: 12,400, mFI-5 = 1: 17,328, mFI-5 = 2: 9,225, mFI-5 ≥ 3: 1,416). Patients with higher mFI-5 scores were more likely to be older, male, White, and have larger tumors, all p < 0.05. Increasing mFI-5 scores resulted in increased frequency of all adverse outcomes, all p < 0.001. On multivariate analysis, mFI-5 ≥ 3 classification was a predictor of CD I/II (OR = 1.280), CD IV (OR = 2.539), mortality (OR = 2.202), HCRU (OR = 2.094), PLOS (OR = 2.136), DCC (OR = 3.401), and UR (OR = 1.705), all p < 0.05. A mFI-5 ≥ 3 demonstrated a sensitivity ranging from 6.0 – 13.5% and a specificity ranging from 96.6 – 97.0% for all outcomes. ConclusionsThe mFI-5 is an easily ascertainable pre-operative risk assessment tool that is a predictor of adverse clinical and HCRU outcomes following TURBT.