Predictors Of Success Research Articles

Machine Learning Prediction of On/Off Target-driven Clinical Adverse Events.

Currently, 90% of clinical drug development fails, where 30% of these failures are due to clinical toxicity. The current extensive animal toxicity studies are not predictive of clinical adverse events (AEs) at clinical doses, while current computation models only consider very few factors with limited success in clinical toxicity prediction. We aimed to address these issues by developing a machine learning (ML) model to directly predict clinical AEs. Using a dataset with 759 FDA-approved drugs with known AEs, we first adapted the ConPLex ML model to predict IC values of these FDA-approved drugs against their on-target and off-target binding among 477 protein targets. Subsequently, we constructed a new ML model to predict clinical AEs using IC values of 759 drugs' primary on-target and off-target effects along with tissue-specific protein expression profiles. The adapted ConPLex model predicted drug-target interactions for both on- and off-target effects, as shown by co-localization of the 6 small molecule kinase inhibitors with their respective kinases. The coupled ML models demonstrated good predictive capability of clinical AEs, with accuracy over 75%. Our approach provides a new insight into the mechanistic understanding of in vivo drug toxicity in relationship with drug on-/off-target interactions. The coupled ML models, once validated with larger datasets, may offer advantages to directly predict clinical AEs using in vitro/ex vivo and preclinical data, which will help to reduce drug development failure due to clinical toxicity.

Factors affecting the outcome of primary rabies vaccination in young cats

Limited data exist on the factors affecting feline rabies vaccination outcomes during primary immunization. This study aimed to assess if specific factors (signalment, vaccination count, vaccine brand, and time since last vaccination) correlated with meeting global antibody titer standards and absolute titers in young cats given monovalent inactivated rabies vaccines. Analyzing a dataset from cats tested before their first annual booster using the FAVN test, logistic and linear regression models were applied. Among 379 cats, 94.2% achieved titers meeting or exceeding the standard threshold (≥0.5 IU/ml). Time since last vaccination proved to be the primary predictor of vaccination success. Cats receiving two vaccinations tended toward higher titers. Age, sex, breed, and vaccine type showed no impact on outcomes. The present study indicates that vaccination failure in young cats is uncommon, and that the time interval from the latest vaccination is the single most important predictor of successful rabies vaccination.

Machine Learning Investigation of Tuberculosis with Medicine Immunity Impact

Tuberculosis (T.B.) remains a prominent global cause of health challenges and death, exacerbated by drug-resistant strains such as multidrug-resistant tuberculosis MDR-TB and extensively drug-resistant tuberculosis XDR-TB. For an effective disease management strategy, it is crucial to understand the dynamics of T.B. infection and the impacts of treatment. In the present article, we employ AI-based machine learning techniques to investigate the immunity impact of medications. SEIPR epidemiological model is incorporated with MDR-TB for compartments susceptible to disease, exposed to risk, infected ones, preventive or resistant to initial treatment, and recovered or healed population. These masses' natural trends, effects, and interactions are formulated and described in the present study. Computations and stability analysis are conducted upon endemic and disease-free equilibria in the present model for their global scenario. Both numerical and AI-based nonlinear autoregressive exogenous NARX analyses are presented with incorporating immediate treatment and delay in treatment. This study shows that the active patients and MDR-TB, both strains, exist because of the absence of permanent immunity to T.B. Furthermore, patients who have recovered from tuberculosis may become susceptible again by losing their immunity and contributing to transmission again. This article aims to identify patterns and predictors of treatment success. The findings from this research can contribute to developing more effective tuberculosis interventions.

Efficacy of Urethral Sphincter Botulinum Toxin A Injection in Patients with Spinal Cord Injury with Dysuria: A Retrospective Cohort Study

Spinal cord injury (SCI) often leads to neurogenic lower urinary tract dysfunction, causing dysuria and affecting patients’ well-being. This study aimed to evaluate the efficacy of a urethral sphincter botulinum toxin A (BoNT-A) injection in patients with SCI and dysuria. This was a retrospective study including 118 patients with SCI who underwent a urethral BoNT-A injection following a standardized protocol for refractory voiding dysfunction. The protocol involved injecting BoNT-A into the urethral sphincter under cystoscopic guidance. Patient demographics, bladder condition parameters, and treatment outcomes were analyzed. Logistic regression and receiver operating characteristic curve analyses were performed to identify predictors of treatment success. Of the 118 patients, 71 (60.1%) showed satisfactory treatment outcomes after the injection. Post-injection status, bladder management, and injection frequency varied significantly among patients with satisfactory and unsatisfactory treatment outcomes. Age, bladder compliance, intravesical pressure, and bladder contractility were indicators of satisfactory outcomes. The first sensation of bladder filling of ≤263 mL, intravesical pressure of ≤28, and bladder contractility index of ≥14 were highly correlated with satisfactory outcomes. A urethral sphincter BoNT-A injection shows promise in managing dysuria in patients with SCI. Understanding bladder condition parameters and patient demographics helps optimize patient selection for this intervention. Further studies are needed to validate these findings and refine treatment protocols.

Posttraumatic stress disorder following childhood sexual and physical abuse: a study protocol for an 11-week randomised controlled trial comparing imaginal exposure and imagery rescripting

ABSTRACT Background: There is a vast amount of evidence supporting the effectiveness of trauma-focused cognitive-behavioral therapy in treating posttraumatic stress disorder (PTSD). However, it remains unclear which specific treatment is most effective for patients with PTSD following childhood sexual and physical abuse (CSPA). Although Imaginal Exposure (IE) has proven highly effective in treating PTSD and is widely acknowledged as a standard method, Imagery Rescripting (IR) may be more suitable for CSPA-related PTSD. IR not only addresses fear but also targets other emotions and cognitions associated with childhood maladaptive schemas. Preliminary findings suggest lower drop-out rates for IR compared to IE, but no Randomized Controlled Trial (RCT) currently assesses the effectiveness of IR for CSPA-related PTSD. Objective: This article presents a study protocol designed to investigate the optimal treatment (IE or IR) for individuals with CSPA-related PTSD and explore predictors of treatment success. Method: In our study protocol, we suggest the inclusion of 173 patients (N = 64 in IR, N = 64 in IE, and N = 45 in the waitlist condition). The therapy procedures for both IE and IR will consist of 16 sessions lasting 90 min each, with treatment durations of 11 weeks. Measurements take place at baseline, at start of treatment, 11 weeks after the start of treatment (after 16 sessions) and at follow-up at 26 weeks after the last session. A mixed regression will be used to compare the three active conditions before and after measurement. Results: This article serves as a study protocol. The results are not yet available but they will be presented in a subsequent article. Conclusion: This study protocol outlines a RCT which will be the first to provide information on the effectiveness of IR versus IE versus a control group in CSPA-related PTSD. Trial registration: Netherlands Trial Register NTR 4817. Registered 26 September 2014.

A machine learning model that outperforms conventional global subseasonal forecast models

Skillful subseasonal forecasts are crucial for various sectors of society but pose a grand scientific challenge. Recently, machine learning-based weather forecasting models outperform the most successful numerical weather predictions generated by the European Centre for Medium-Range Weather Forecasts (ECMWF), but have not yet surpassed conventional models at subseasonal timescales. This paper introduces FuXi Subseasonal-to-Seasonal (FuXi-S2S), a machine learning model that provides global daily mean forecasts up to 42 days, encompassing five upper-air atmospheric variables at 13 pressure levels and 11 surface variables. FuXi-S2S, trained on 72 years of daily statistics from ECMWF ERA5 reanalysis data, outperforms the ECMWF’s state-of-the-art Subseasonal-to-Seasonal model in ensemble mean and ensemble forecasts for total precipitation and outgoing longwave radiation, notably enhancing global precipitation forecast. The improved performance of FuXi-S2S can be primarily attributed to its superior capability to capture forecast uncertainty and accurately predict the Madden-Julian Oscillation (MJO), extending the skillful MJO prediction from 30 days to 36 days. Moreover, FuXi-S2S not only captures realistic teleconnections associated with the MJO but also emerges as a valuable tool for discovering precursor signals, offering researchers insights and potentially establishing a new paradigm in Earth system science research.

Changes in Serum Metabolome Following Low-Energy Diet-Induced Weight Loss in Women with Overweight and Prediabetes: A PREVIEW-New Zealand Sub-Study

As obesity develops, metabolic changes increase the risk of non-communicable diseases such as type 2 diabetes (T2D). Weight loss is crucial for improving health in T2D and cardiometabolic conditions. However, weight loss rates vary between individuals, even with identical diets or energy restrictions, highlighting the need to identify markers or predictors of weight loss success to enhance intervention outcomes. Using nuclear magnetic resonance (NMR) spectroscopy-based metabolomics, we investigated the change in serum polar metabolites in 28 women with overweight or obesity and prediabetes who completed an 8-week low-energy diet (LED) as part of the PREVIEW (PREVention of diabetes through lifestyle intervention and population studies in Europe and around the World) clinical trial. We aimed to characterize the metabolic shift in substrate oxidation under fixed energy intake (~4 MJ/day) and its relation to weight loss success. Nine of the thirty-four serum metabolites identified significantly changed during the LED phase: 3-hydroxybutyrate, O-acetylcarnitine, 2-hydroxybutyrate, mannose, dimethyl sulfone and isobutyrate increased, whilst choline, creatine and tyrosine decreased. These results confirmed a shift towards lipid oxidation, but no metabolites predicted the response to the LED-induced weight loss. Further studies in larger populations are required to validate these metabolites as biomarkers of diet exposure.

Emotional competence and help-seeking intentions as predictors of educational success in vocational training students

Given the high prevalence of psychological distress among vocational training (VT) students, this study aimed to assess the role of interpersonal emotional competence as a resilience factor promoting the educational success of this population. We postulated that emotional competence would promote educational success, both directly and indirectly by fostering students’ help-seeking intentions when facing a personal or school-related problem. To test these hypotheses, we used a sample of 219 VT students from the Canadian province of Quebec (68% women, Mage = 24.58; SDage = 7.95) enrolled in various programs (e.g. institutional and home care assistance, welding and fitting, secretarial studies, and professional cooking). These students were assessed two times, during the first half of their training and again after their training. Results from structural equation modelling revealed that emotional competence was a positive predictor of help-seeking intentions and educational success. However, having the intention to seek help did not translate into higher levels of educational success. Overall, these results highlight the importance of supporting VT students in the development and strengthening of their emotional competence to promote their educational success. Future research is needed to further understand the help-seeking process among VT students and its implications for their academic outcomes.

The impact of visual, auditory, textual stimuli on crowdfunding: evidence from tourism projects

ABSTRACT Discover the secrets to crowdfunding triumph. In start-up tourism enterprises, mastering the art of captivating and converting users into sponsors through multimodal stimuli is paramount. Researchers used deep learning to deeply mine the text, images and video promotional content of 3,659 travel crowdfunding projects and nine classifiers to predict crowdfunding project success dynamically. We unearthed fascinating insights: Images spark attention, but video and text drive user conversion to sponsorship. Speech tends to deliver information, facts, or opinions. Key successful project predictors include positive emotions, pro-social engagement, cognitive vocabulary, increased video scenes and rapid visual variation. While consistent multimodal data bolsters model clarity, it does not markedly boost prediction. Lastly, linear and tree-based models outperform their nonlinear counterparts and have better prediction results.

Machine learning that predicts well may not learn the correct physical descriptions of glassy systems

The complexity of glasses makes it challenging to explain their dynamics. Machine learning (ML) has emerged as a promising pathway for understanding glassy dynamics by linking their structural features to rearrangement dynamics. Support vector machine (SVM) was one of the first methods used to detect such correlations. Specifically, a certain output of SVMs trained to predict dynamics from structure, the distance from the separating hyperplane, was interpreted as being linearly related to the activation energy for the rearrangement. By numerical analysis of toy models, we explore under which conditions it is possible to infer the energy barrier to rearrangements from the distance to the separating hyperplane. We observe that such successful inference is possible only under very restricted conditions. Typical tests, such as the apparent Arrhenius dependence of the probability of rearrangement on the inferred energy and the temperature, or high cross-validation accuracy do not guarantee success. Since even in such relatively simple toy models, prediction success of ML models does not necessarily translate into success of learning the underlying physics, we suggest that more careful investigations are needed when such claims are made. For this, we propose practical approaches for measuring the quality of the energy inference and for modifying the inferred model to improve the inference, which should be usable in the context of realistic datasets. Published by the American Physical Society 2024

Outcomes and Predictors of Success Following Multilevel Surgery in Positional and Nonpositional Obstructive Sleep Apnea.

To assess the surgical outcomes and identify predictors of surgical success in patients with positional and non-positional obstructive sleep apnea following multilevel airway surgery. Retrospective cohort study. Singe-tertiary medical center. This study included 158 patients with obstructive sleep apnea who underwent multilevel airway surgery. Patients were divided into 2 groups according to position dependency: "positional patients" group (n = 100), and "nonpositional patients" group (n = 58). The characteristics and surgical outcomes of the 2 groups were compared. The nonpositional group included younger and more obese patients in comparison to the positional group. Moreover, the nonpositional group had more severe disease than the positional group. Both groups showed overall improvement after surgery, and the surgical success rate did not differ significantly between the 2 groups (nonpositional, 41.4% vs positional, 48.0%; P = .424). Notably, 69.0% of patients belonging to the non-positional group converted to positional group postoperatively. Logistic regression analysis revealed that larger tonsil size, female sex, and higher mean O2 saturation were associated with higher success rate in the positional group, whereas larger tonsil size was associated with surgical success in the nonpositional group. Both nonpositional and positional groups showed improvements following multilevel airway surgery, and surgery induced a transition from nonpositional to positional group. Given that the factors related to surgical success differed between the two groups, surgeons should consider position dependency and these distinct factors during decision-making.

Prognostic factors for endoscopic third ventriculostomy success in hydrocephalus with myelomeningocele.

Myelomeningocele (MMC) is a prevalent neural tube closure defect often associated with hydrocephalus, necessitating surgical intervention in a significant proportion of cases. While ventriculoperitoneal shunting (VPS) has been a standard treatment approach, endoscopic third ventriculostomy (ETV) has emerged as a promising alternative. However, factors influencing the success of ETV in MMC patients remain uncertain. This retrospective observational study aimed to identify clinical and radiological factors correlating with a higher success rate of ETV in MMC patients. Medical records of MMC patients who underwent ETV at a tertiary care center between 2015 and 2021 were reviewed. Demographic, clinical, and radiological data were analyzed. ETV success was defined as the absence of further hydrocephalus treatment during follow-up. Of 131 MMC patients, 21 met inclusion criteria and underwent ETV. The overall success rate of ETV was 57.1%, with a six-month success rate of 61.9%. Age ≤ 6months was significantly associated with lower ETV success (25%) compared to older patients (76.9%) (OR: 0.1; 95% CI 0.005-2.006; p = 0.019). Radiological factors, including posterior fossa dimensions and linear indices, did not exhibit statistically significant associations with ETV success. Age emerged as a significant factor affecting ETV success in MMC patients, with younger patients exhibiting lower success rates. Radiological variables did not significantly influence ETV outcomes in this study. Identifying predictors of ETV success in MMC patients is crucial for optimizing treatment strategies and improving patient outcomes.

Predictors of Therapy Success in Weekly Adalimumab for Refractory Uveitis: A Retrospective Cohort Study

PurposeTo determine predictors of treatment success after dose escalation of adalimumab, including measurement of anti-adalimumab antibodies as a predictor of success DesignRetrospective clinical cohort study SettingSingle-center academic institution Study PopulationPatients with noninfectious uveitis who were inadequately controlled or developed recurrent disease on biweekly adalimumab and required dose escalation or therapy modification Observation ProceduresPatients who had anti-adalimumab antibodies checked with resultant low to intermediate levels were compared to patients who had no testing performed prior to adalimumab dose escalation. Of note, patients with testing and resultant high levels of anti-adalimumab antibodies were not escalated. Predictors of escalation success and utility of antibody testing prior to escalation were analyzed using Kaplan Meier survival analysis and Cox proportional hazard models. Main Outcome MeasuresTreatment success defined as anterior chamber grade ≤0.5+ cell, topical corticosteroids ≤1 drop/day, oral prednisone ≤5 mg/day, resolution of macular edema, and resolution of angiographic signs of inflammation without any addition or escalation of therapy. Results24 patients had antibodies tested with low to intermediate levels (average: 32.3 ng/mL, range: 0 – 154), while 41 did not have antibody testing. A greater treatment success rate post escalation was observed among the “low antibody” group compared to the “no testing” group (HR: 2.63, standard error: 1.19, p=0.031, 95% CI 1.09 – 6.37). Among the entire cohort, patients with panuveitis (n = 14) had a lower treatment success rate compared to the reference of anterior uveitis (n = 26) (HR: 0.09, standard error: 0.11, p = 0.05, 95% CI 0.01 – 0.99). ConclusionsPatients with low anti-adalimumab antibodies had a greater treatment success compared to patients in whom antibodies were not checked. This suggests a utility to checking antibodies prior to dose escalation and that low levels of antibodies may confer a success advantage. Overall, patients with panuveitis had a lower rate of success after escalation while patients with anterior uveitis patients had a very high rate of success suggesting that certain disease characteristics may guide clinicians when determining who to escalate versus changing therapy.

Ultrasound‐assisted and landmark‐based nusinersen delivery in spinal muscular atrophy adults: A retrospective analysis

AbstractIntroduction/PurposeNusinersen, the first treatment approved for all spinal muscular atrophy (SMA) types, is administered intrathecally through lumbar puncture. We used ultrasound assistance or a landmark‐based technique to access the lumbar intrathecal space in adult SMA patients. This study aimed to evaluate the technical success and adverse events (AEs) in such patients using either technique over a long observation period.MethodsFifty‐one adult patients received 507 consecutive interlaminar nusinersen administrations. Patients presented with both ‘uncomplicated spines’ or ‘complicated spines’; two patients had previous back surgery. Technical success and AEs were recorded using either technique. A generalised linear mixed model was applied to evaluate predictors of technical success and complications.ResultsAn overall success rate of 99.6%, with only two procedures failing to reach the intrathecal space, and an overall optimal procedure rate of 90.3% have been reported. A total of 455 procedures (89.7%) were uneventfully performed. One (0.2%) case of severe AE (puncture of a bulky abdominal annexal cyst) was recorded. Twenty‐seven episodes (5.3%) of post‐dural puncture headache (PDPH) and 24 episodes (4.7%) of radicular or back pain, both successfully treated with medical therapy, have also been reported. Technical success was significantly associated with ‘complicated spines’ (P = 0.022) and the use of ultrasound assistance (P = 0.01), and the use of ultrasound was the only independent predictor of uncomplicated procedures (P = 0.007).DiscussionIn adult patients with SMA both landmark‐based and ultrasound‐assisted techniques are safe and effective even in the long term. The use of assistance is associated with technical success and can predict uncomplicated procedures.ConclusionOur results support the use of ultrasonography in order to improve the success and reduce the burden of nusinersen intrathecal administration.

Mapping model of ribbon contour and tool influence function based on distributed parallel neural networks in magneto-rheological finishing

Magnetorheological finishing (MRF) stands out as a notable polishing technology, characterized by high precision and minimal damage. However, establishing an accurate and practical model for the tool influence function (TIF) of MRF poses a significant challenge. In this paper, a TIF modeling method of MRF based on distributed parallel neural networks is proposed for the first time. Assessment of the viability of this approach through multiple sets of robot-assisted MRF experiments is detailed. The experimental results conclusively demonstrate the successful intelligent prediction of TIF, with key indicators such as volume removal rate and peak removal rate achieving an average prediction accuracy exceeding 95%. This method can remarkably advance the intelligence of the TIF model in MRF and serve as a valuable reference for other optical fabrication methods.

Utilizing connectome fingerprinting functional MRI models for motor activity prediction in presurgical planning: A feasibility study.

Presurgical planning prior to brain tumor resection is critical for the preservation of neurologic function post-operatively. Neurosurgeons increasingly use advanced brain mapping techniques pre- and intra-operatively to delineate brain regions which are "eloquent" and should be spared during resection. Functional MRI (fMRI) has emerged as a commonly used non-invasive modality for individual patient mapping of critical cortical regions such as motor, language, and visual cortices. To map motor function, patients are scanned using fMRI while they perform various motor tasks to identify brain networks critical for motor performance, but it may be difficult for some patients to perform tasks in the scanner due to pre-existing deficits. Connectome fingerprinting (CF) is a machine-learning approach that learns associations between resting-state functional networks of a brain region and the activations in the region for specific tasks; once a CF model is constructed, individualized predictions of task activation can be generated from resting-state data. Here we utilized CF to train models on high-quality data from 208 subjects in the Human Connectome Project (HCP) and used this to predict task activations in our cohort of healthy control subjects (n = 15) and presurgical patients (n = 16) using resting-state fMRI (rs-fMRI) data. The prediction quality was validated with task fMRI data in the healthy controls and patients. We found that the task predictions for motor areas are on par with actual task activations in most healthy subjects (model accuracy around 90%-100% of task stability) and some patients suggesting the CF models can be reliably substituted where task data is either not possible to collect or hard for subjects to perform. We were also able to make robust predictions in cases in which there were no task-related activations elicited. The findings demonstrate the utility of the CF approach for predicting activations in out-of-sample subjects, across sites and scanners, and in patient populations. This work supports the feasibility of the application of CF models to presurgical planning, while also revealing challenges to be addressed in future developments. PRACTITIONER POINTS: Precision motor network prediction using connectome fingerprinting. Carefully trained models' performance limited by stability of task-fMRI data. Successful cross-scanner predictions and motor network mapping in patients with tumor.

Multicenter Study on Physician-Modified Endografts for Thoracoabdominal and Complex Abdominal Aortic Aneurysm Repair.

Physician modified endografts (PMEGs) have been widely used in the treatment of complex abdominal aortic aneurysm and thoracoabdominal aortic aneurysm, however, previous data are limited to small single center studies and robust data on safety and effectiveness of PMEGs are lacking. We aimed to perform an international multicenter study analyzing the outcomes of PMEGs in complex abdominal aortic aneurysms and thoracoabdominal aortic aneurysms. An international multicenter single-arm cohort study was performed analyzing the outcomes of PMEGs in the treatment of elective, symptomatic, and ruptured complex abdominal aortic aneurysms and thoracoabdominal aortic aneurysms. Variables and outcomes were defined according to the Society for Vascular Surgery reporting standards. Device modification and procedure details were collected and analyzed. Efficacy outcomes included technical success and safety outcomes included major adverse events and 30-day mortality. Follow-up outcomes included reinterventions, endoleaks, target vessel patency rates and overall and aortic-related mortality. Multivariable analysis was performed aiming at identifying predictors of technical success, 30-day mortality, and major adverse events. Overall, 1274 patients were included in the study from 19 centers. Median age was 74 (IQR, 68-79), and 75.7% were men; 45.7% were complex abdominal aortic aneurysms, and 54.3% were thoracoabdominal aortic aneurysms; 65.5% patients presented electively, 24.6% were symptomatic, and 9.9% were ruptured. Most patients (83.1%) were submitted to a fenestrated repair, 3.6% to branched repair, and 13.4% to a combined fenestrated and branched repair. Most patients (85.8%) had ≥3 target vessels included. The overall technical success was 94% (94% in elective, 93.4% in symptomatic, and 95.1% in ruptured cases). Thirty-day mortality was 5.8% (4.1% in elective, 7.6% in symptomatic, and 12.7% in ruptured aneurysms). Major adverse events occurred in 25.2% of cases (23.1% in elective, 27.8% in symptomatic, and 30.3% in ruptured aneurysms). Median follow-up was 21 months (5.6-50.6). Freedom from reintervention was 73.8%, 61.8%, and 51.4% at 1, 3, and 5 years; primary target vessel patency was 96.9%, 93.6%, and 90.3%. Overall survival and freedom from aortic-related mortality was 82.4%/92.9%, 69.9%/91.6%, and 55.0%/89.1% at 1, 3, and 5 years. PMEGs were a safe and effective treatment option for elective, symptomatic, and ruptured complex aortic aneurysms. Long-term data and future prospective studies are needed for more robust and detailed analysis.

Identifying SCS Trial Responders Immediately After Postoperative Programming with ECAP Dose-Controlled Closed-Loop Therapy.

Drawbacks of fixed-output spinal cord stimulation (SCS) screening trials may lead to compromised trial outcomes and poor predictability of long-term success. Evoked compound action potential (ECAP) dose-controlled closed-loop (CL) SCS allows objective confirmation of therapeutic neural activation and pulse-to-pulse stimulation adjustment. We report on the immediate patient-reported and neurophysiologic treatment response post-physiologic CL-SCS and feasibility of early SCS trial responder prediction. Patient-reported pain relief, functional improvement, and willingness to proceed to permanent implant were compared between the day of the trial procedure (Day 0) and end of trial (EOT) for 132 participants in the ECAP Study undergoing a trial stimulation period. ECAP-based neurophysiologic measurements from Day 0 and EOT were compared between responder groups. A high positive predictive value (PPV) was achieved with 98.4% (60/61) of patients successful on the Day 0 evaluation also responding at EOT. The false-positive rate (FPR) was 5.6% (1/18). ECAP-based neurophysiologic measures were not different between patients who passed all Day 0 success criteria ("Day 0 successes") and those who did not ("needed longer to evaluate the therapy"). However, at EOT, responders had higher therapeutic usage and dose levels compared to non-responders. The high PPV and low FPR of the Day 0 evaluation provide confidence in predicting trial outcomes as early as the day of the procedure. Day 0 trials may be beneficial for reducing patient burden and complication rates associated with extended trials. ECAP dose-controlled CL-SCS therapy may provide objective data and rapid-onset pain relief to improve prognostic ability of SCS trials in predicting outcomes. The ECAP Study is registered with ClinicalTrials.gov (NCT04319887).

Achieving Clinical Success in Nonsedated Velopharyngeal MRI: Insights for Optimal Data Quality & Effective Patient Selection.

The ability of MRI for in vivo visualization of the velopharyngeal (VP) musculature makes it the only imaging modality for this purpose. This underscores a need for exploration into clinical translation of this imaging modality on craniofacial teams. The purpose of this study was to assess outcomes of a clinically feasible VP MRI protocol and describe the ideal patient population for utilization of this imaging protocol. Sixty children (2-12 years) with velopharyngeal insufficiency (VPI) underwent a nonsedated, child-friendly MRI protocol. No exclusions based on syndromic conditions were made. Logistic regression assessed predictors of VP MRI success and multinomial logistic regression evaluated factors influencing quality of anatomic data. An 85% overall success rate was achieved, including children as young as two and those with syndromic diagnoses. Stratifying by age revealed a 97.5% success rate in children ages four and up. The regression model [χ2(5) = 37.443, p < 0.001] explained 81.4% of success rate variance, correctly classifying 93.3% of cases. Increased age significantly predicted success (p=0.046), while sex and syndromic conditions did not. Multinomial regression identified preparatory materials (p=0.011) and audio/video during the scan (p=0.024) as predictors for improved image quality. Implementation of VP MRI is feasible for a broad population of children with VPI, including those with concomitant syndromic diagnoses. Quality is improved by incorporating pre-scan preparation and audio/visual stimuli during scans. This underscores the potential of VP MRI as a valuable tool in clinical settings, especially for pre-surgical assessments.

Enhancing adult learner success in higher education through decision tree models: A machine learning approach

This article explores the use of machine learning, specifically Classification and Regression Trees (CART), to address the unique challenges faced by adult learners in higher education. These learners confront socio-cultural, economic, and institutional hurdles, such as stereotypes, financial constraints, and systemic inefficiencies. The study utilizes decision tree models to evaluate their effectiveness in predicting graduation outcomes, which helps in formulating tailored educational strategies. The research analyzed a comprehensive dataset spanning the academic years 2013–2014 to 2021–2022, evaluating the predictive accuracy of CART models using precision, recall, and F1 score. Findings indicate that attendance, age, and Pell Grant eligibility are key predictors of academic success, demonstrating the strong capability of the model across various educational metrics. This highlights the potential of machine learning (ML) to improve data-driven decision-making in educational settings. The results affirm the effectiveness of Decision Tree (DT) models in meeting the educational needs of adult learners and underscore the need for institutions to adapt their strategies to provide more inclusive and supportive environments. This study advocates for a shift towards nuanced, data-driven approaches in higher education, emphasizing the development of strategies that address the distinct challenges of adult learners, aiming to enhance inclusivity and support within the sector.