Citations

Background As the use of flow diverters has expanded in recent years, predicting successful outcomes has become more challenging for certain aneurysms. Objective To provide neurointerventionalists with an understanding of the available machine learning algorithms for predicting the success of flow diverters in occluding aneurysms. Methods This study followed Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, and the four major medical databases (PubMed, Embase, Scopus, Web of Science) were screened. The study included original research articles that evaluated the predictive abilities of various machine learning algorithms for determining the success of flow diverters in achieving aneurysm occlusion. Results Five studies out of 217 were included based on our criteria. The included studies used various variables (patient demographics, aneurysm and parent artery characteristics, flow diverter and hemodynamic-related features, and angiographic parametric imaging) to predict flow diverter treatment outcomes. The machine learning algorithms used, along with their respective accuracy rates, were as follows: logistic regression (61% and 85%), support vector machine (88%), Gaussian support vector machine (90%), linear support vector machine (85%), decision tree (80%), random forest (87%), k-nearest neighbors (83% and 85%), XGBoost (87%), CatBoost (86%), deep neural networks (77.9%), and recurrent neural networks (74%).Two studies trained the machine learning models with both all features and the most significant features. Both studies observed that the accuracy of machine learning models decreased by removing the insignificant features. Conclusion The current literature indicates that machine learning algorithms can be trained to predict the success of flow diverters with an accuracy of up to 90%.

ABSTRACTFood security is one of the most researched social determinants of health (SDoH), however, there is a lack of literature on the impact of food security on cardiovascular disease in pregnancy. The primary objective was to examine the association between food security with hypertensive disorders of pregnancy. We performed a cross‐sectional analysis of 2019–2022 data from the National Health Interview Survey. The study population included women of childbearing age who were either pregnant or recently pregnant. Logistic regression models were developed to examine the association between food security and hypertensive disorders of pregnancy. Of the 1635 women included in the analysis, the rate of hypertensive disorders of pregnancy was 11.1% and the rate of low and very low food security was 5.3% and 4.0%, respectively. The prevalence was 5.8% for hyperlipemia, 0.3% for cardiovascular disease, and 10.5% for diabetes mellitus. The odds of hypertensive disorders of pregnancy were statistically significantly increased among women with low food security compared to women with high food security (odds ratio [OR] 2.40, 95% confidence interval [CI]: 1.19–4.81) after adjusting for age, race, ethnicity, insurance status, body mass index, hyperlipidemia, diabetes mellitus, and cardiovascular disease. Further studies are needed to elucidate the causes of hypertensive disorders of pregnancy and interventions to address including the Special Supplemental Nutrition Program for Women, Infants, and Children (WIC) and food pantries, as it may be more feasible to address issues of food security among pregnant women.

Background/Objectives: Adult hearing-impaired patients qualifying for cochlear implants typically exhibit less than 60% sentence recognition under the best hearing aid conditions, either in quiet or noisy environments, with speech and noise presented through a single speaker. This study examines the influence of deep neural network-based (DNN-based) noise reduction on cochlear implant evaluation. Methods: Speech perception was assessed using AzBio sentences in both quiet and noisy conditions (multi-talker babble) at 5 and 10 dB signal-to-noise ratios (SNRs) through one loudspeaker. Sentence recognition scores were measured for 10 hearing-impaired patients using three hearing aid programs: calm situation, speech in noise, and spheric speech in loud noise (DNN-based noise reduction). Speech perception results were compared to bench analyses comprising the phase inversion technique, employed to predict SNR improvement, and the Hearing-Aid Speech Perception Index (HASPI v2), utilized to predict speech intelligibility. Results: The spheric speech in loud noise program improved speech perception by 20 to 32% points as compared to the calm situation program. Thus, DNN-based noise reduction can improve speech perception in noisy environments, potentially reducing the need for cochlear implants in some cases. The phase inversion method showed a 4–5 dB SNR improvement for the DNN-based noise reduction program compared to the other two programs. HASPI v2 predicted slightly better speech intelligibility than was measured in this study. Conclusions: DNN-based noise reduction might make it difficult for some patients with significant residual hearing to qualify for cochlear implantation, potentially delaying its adoption or eliminating the need for it entirely.

Abstract Chemotherapy regimens for triple-negative breast cancer (TNBC) combine agents without knowing which agents drive response. Consequently, predictors derived from multi-agent regimens cannot be assumed to generalize to individual drugs or other regimens, motivating development of treatment-matched predictors. Here, we used TNBC patient-derived xenografts (PDXs) treated with carboplatin, docetaxel, or the combination to deconvolute drug-specific responses and identify associated molecular features. Combination treatment rarely improved upon the best single agent, with enhanced responses in only 13% of PDXs and antagonism in a comparable fraction. Proteogenomic analyses identified high cytokeratin-5 (KRT5) as a general marker of chemotherapy responsiveness and KRT5 immunohistochemistry discriminated responsive PDXs (AUROC, 0.83). To train treatment-specific predictors, we integrated these data with independent PDX and clinical cohorts with responses assessed after anthracycline-free platinum, taxane, or platinum-taxane therapy, ensuring response corresponded to the modeled treatment. Four feature selection strategies yielded largely nonoverlapping biomarker panels converging on treatment-relevant pathways. On independent test data, RNA-based predictors of complete response (CR) to platinum-based (carboplatin or cisplatin) and taxane-based (docetaxel or paclitaxel) chemotherapy achieved AUROCs of 0.80 and 0.86, respectively. For platinum-taxane regimens (carboplatin plus docetaxel or paclitaxel), proteomic-guided feature selection generated a 10-biomarker, protein- informed RNA predictor of pathologic complete response (pCR) that outperformed RNA-only feature selection and achieved an AUROC of 0.85 in an independent clinical cohort, while retaining practicality as an RNA-based assay. Treatment-matched integration of multi-omic PDX and clinical datasets provides a framework for chemotherapy-specific predictors with clinically relevant performance, supporting biomarker-guided precision selection and treatment optimization for patients with TNBC. Statement of significance Integration of multi-omic data from patient-derived xenografts with treatment-matched clinical cohorts yielded three retrospectively validated predictors of platinum, taxane, and platinum+taxane response, enabling biomarker-guided chemotherapy selection for patients with triple-negative breast cancer.

Background: Reverse shoulder arthroplasty (RSA) is increasingly used in the treatment of displaced proximal humerus fractures (PHFs) with reliable clinical improvement. However, the preferred techniques for humeral stem fixation are varied and may be influenced by patient and injury characteristics, including bone quality and fracture pattern. This systematic review and meta-analysis sought to determine the effect of humeral component cementing and bone grafting on tuberosity healing rates and functional outcomes after RSA for PHFs. Methods: A systematic review was performed per Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. PubMed/MEDLINE, EMBASE, Web of Science, and Cochrane were queried for clinical studies on RSA performed for PHFs that reported on the use of cemented humeral stems and autograft bone. The primary outcome was the rate of greater tuberosity healing between the various techniques. Secondarily, the authors compared clinical outcomes including postoperative external rotation, forward elevation, abduction, Constant score, and the incidence of complications and revision surgery. Outcomes were compared based on the use of an uncemented press-fit stem, a fully cemented stem without bone graft, or a partially cemented stem with humeral head autograft (i.e., black and tan technique). Results: Forty-eight studies reporting on 1,797 RSAs were included (mean patient age, 75 years; follow-up, 34 months; 81% female). Tuberosity healing was highest in the uncemented cohort, then the black and tan cohort, and lowest in the cemented cohort (80% vs. 70% vs. 61%, p = 0.006). No significant differences in postoperative range of motion, Constant score, complication rates, or revision rates were found. Conclusion: Uncemented fixation with a press-fit stem was associated with superior greater tuberosity healing rates; however, functional outcomes and complications did not differ among techniques. Level of Evidence: Therapeutic Level IV . See Instructions for Authors for a complete description of levels of evidence.

Objectives To evaluate the pre‐ and intraoperative variables that impact the integrity of the corporal bodies over time after inflatable penile prosthesis (IPP) placement, as predictors of intraoperative corporal perforation and delayed cylinder complications have not been well characterized. Patients and Methods We retrospectively reviewed a 16‐centre multi‐institutional database of IPP surgeries performed by experienced implanters from 2016 to 2021. Poor corporal integrity (PCI) was defined as intraoperative (iPCI) corporal complications or postoperative (pPCI) corporal complications. Multivariable analysis was performed to identify independent predictors of PCI, iPCI, and pPCI. Primary outcomes included intra‐ and postoperative corporal complications. Results We identified 5153 patients for analysis from 5406 IPP cases, finding 152 (2.95%) cases of PCI. On multivariable analysis, predictors of PCI included revision IPP surgery (odds ratio [OR] 8.16, 95% confidence interval [CI] 5.15–12.92; P < 0.001), sequential dilatation (OR 2.12, 95% CI 1.32–3.39; P = 0.002), coronary artery disease (CAD)/peripheral vascular disease (PVD) (OR 1.81, 95% CI 1.18–2.77; P = 0.006), older age (OR 1.02, 95% CI 1.01–1.04; P = 0.013), and corporal scarring (OR 1.58, 95% CI 1.0–2.5; P = 0.049). Predictors of iPCI included revision IPP surgery (OR 7.34, 95% CI 4.18–12.88; P < 0.001), corporal scarring (OR 2.77, 95% CI 1.64–4.69; P < 0.001), radiation therapy (OR 2.25, 95% CI 1.0–5.04; P = 0.049), and older age (OR 1.03, 95% CI 1.0–1.05; P = 0.025). Revision IPP surgery (OR 7.92, 95% CI 3.69–17.01; P < 0.001), sequential dilatation (OR 3.4, 95% CI 1.61–7.19; P = 0.001), CAD/PVD (OR 2.98, 95% CI 1.56–5.72; P = 0.001), and history of priapism (OR 3.59, 95% CI 1.08–11.99; P = 0.038) were predictive of pPCI. Conclusion Coronary artery disease/PVD, being of older age, having corporal scarring, undergoing IPP revision surgery and sequential dilatation were predictive risk factors for complications associated with PCI. Identifying patients who are at risk of having PCI may improve patient‐specific counselling, consideration of referral to more experienced implanters, and surgical planning to potentially promote longer‐term device viability.

Abstract Purpose: NFE2L2/KEAP1/CUL3 mutations have been validated for radioresistance in cell-based assays and animal models. However, clinical validation of these biomarkers has been challenging because of multimodality treatment regimens. This study aims to investigate the association between NFE2L2/KEAP1/CUL3 mutations and patient outcomes, including local failure, locoregional failure, disease-free survival (DFS), and overall survival, using samples from a phase III trial in which patients were treated with radiation monotherapy at two controlled doses. Patients and Methods: We investigated NFE2L2/KEAP1/CUL3 mutations in 250 randomized patients with T2N0 glottic squamous cell carcinoma receiving definitive radiotherapy in the NRG/RTOG 9512 trial. A total of 119 patients had available biospecimens that were subjected to amplicon-based next-generation sequencing to assess for the presence of NFE2L2/KEAP1/CUL3 mutations without regard to outcomes. Mutations in NFE2L2/KEAP1/CUL3 were assessed blinded to clinical outcomes. Cox models (two-sided α = 0.05) were used to evaluate the association with clinical outcomes, performed by an independent statistical team. Results: Nineteen of 119 patients (16.0%) had NFE2L2/KEAP1/CUL3 mutations. Patient, treatment, and tumor characteristics were similar between those with and without mutations. Patients with mutation compared with those without had significantly more local failure [HR = 3.50; 95% confidence interval (CI), 1.56–7.89; P = 0.0025] and locoregional failure (HR = 3.80; 95% CI, 1.80–8.03; P = 0.0005). DFS was significantly worse for the mutated compared with the nonmutated group in the first 2 years (HR = 2.88; 95% CI, 1.46–5.66; P = 0.0022). The median DFS was shorter in the mutation group (10.3 months) versus those with intact NFE2L2/KEAP1/CUL3 (4.2 years). Conclusions: NFE2L2/KEAP1/CUL3 mutations may predict radiation treatment failure in T2N0 glottic cancer. See related commentary by Rao, p. 1563

Objective: The pattern, rate, and natural history of bone flap resorption following cranioplasty with frozen, autologous bone flap has not been fully defined. The authors sought to quantify the progression and natural history of bone flap resorption. Methods: Patients who had craniectomy and delayed cranioplasty with stored, frozen bone flap between 2012 and 2022 were included in this study. Results: Ninety patients (63% male) were included, with a median age of 44.8 years (range: 4.2–84.4 y) at the time of autologous bone flap cranioplasty. Delayed, autologous cranioplasty occurred at a median time of 29.5 days (range: 2 d–10 y) from the index craniectomy. The median follow-up was 16.6 months (range: 3.4–85.4 mo). Radiographically quantifiable bone flap resorption occurred in 50 patients (56%). During the follow-up, the average percentage volume loss was 17%, with a nonlinear pattern of resorption. Following delayed, autologous cranioplasty, 11 patients had clinically significant bone flap resorption requiring secondary alloplastic cranioplasty at a median time of 13.8 months (range: 5.9–57.2 mo), with a mean percentage volume loss of 61%. Younger age was a risk factor for bone flap resorption (P < 0.05), whereas active smoking, presence of comorbidities, and number of days of bone flap storage were not risk factors for bone flap resorption. Penalized B-spline regression analysis showed that bone flap resorption followed a nonlinear pattern. Conclusion: Radiographically quantifiable bone flap resorption occurred in about 56% of patients following delayed autologous cranioplasty. Resorption followed a non-linear pattern. Young age is a risk factor for bone flap resorption.