Category: Nevin Manimala

J Thorac Dis. 2024 Apr 30;16(4):2644-2653. doi: 10.21037/jtd-23-1659. Epub 2024 Apr 24.

ABSTRACT

BACKGROUND AND OBJECTIVE: Machine learning (ML) is increasingly being utilized to provide data driven solutions to challenges in medicine. Within the field of cardiac surgery, ML methods have been employed as risk stratification tools to predict a variety of operative outcomes. However, the clinical utility of ML in this domain is unclear. The aim of this review is to provide an overview of ML in cardiac surgery, particularly with regards to its utility in predictive analytics and implications for use in clinical decision support.

METHODS: We performed a narrative review of relevant articles indexed in PubMed since 2000 using the MeSH terms “Machine Learning”, “Supervised Machine Learning”, “Deep Learning”, or “Artificial Intelligence” and “Cardiovascular Surgery” or “Thoracic Surgery”.

KEY CONTENT AND FINDINGS: ML methods have been widely used to generate pre-operative risk profiles, consistently resulting in the accurate prediction of clinical outcomes in cardiac surgery. However, improvement in predictive performance over traditional risk metrics has proven modest and current applications in the clinical setting remain limited.

CONCLUSIONS: Studies utilizing high volume, multidimensional data such as that derived from electronic health record (EHR) data appear to best demonstrate the advantages of ML methods. Models trained on post cardiac surgery intensive care unit data demonstrate excellent predictive performance and may provide greater clinical utility if incorporated as clinical decision support tools. Further development of ML models and their integration into EHR’s may result in dynamic clinical decision support strategies capable of informing clinical care and improving outcomes in cardiac surgery.

PMID:38738250 | PMC:PMC11087616 | DOI:10.21037/jtd-23-1659

J Thorac Dis. 2024 Apr 30;16(4):2472-2481. doi: 10.21037/jtd-24-309. Epub 2024 Apr 26.

ABSTRACT

BACKGROUND: Esophageal malignancies have a high morbidity rate worldwide, and minimally invasive surgery has emerged as the primary approach for treating esophageal cancer. In recent years, there has been increasing discussion about the potential of employing inflatable mediastinoscopic and laparoscopic approaches as an option for esophagectomy. Building on the primary modification of the inflatable mediastinoscopic technique, we introduced a secondary modification to further minimize surgical trauma.

METHODS: We conducted a retrospective analysis of patients who underwent inflatable mediastinoscopy combined with laparoscopic esophagectomy at the Second Affiliated Hospital of Naval Medical University from March 2020 to March 2023. The patients were allocated to the following two groups: the traditional (primary modification) group, and the secondary modification group. Operation times, intraoperative bleeding, and postoperative complications were compared between the groups.

RESULTS: The procedure was successfully performed in all patients, and conversion to open surgery was not required in any case. There were no statistically significant differences in the surgical operation time, intraoperative bleeding, number of dissected lymph nodes, and rate of postoperative anastomotic leakage between the two groups. However, a statistically significant difference was observed in the length of the mobilized esophagus between the two groups. The mobilization of esophagus to the level of diaphragmatic hiatus via the cervical incision was successfully achieved in more patients in the secondary modification group than the primary modification group.

CONCLUSIONS: Inflatable mediastinoscopy combined with single-incision plus one-port laparoscopic esophagectomy is a safe and effective surgical procedure. The use of a 5-mm flexible endoscope, ultra-long five-leaf forceps, and LigaSure Maryland forceps facilitates esophageal mobilization and lymph node dissection through a single cervical incision.

PMID:38738243 | PMC:PMC11087624 | DOI:10.21037/jtd-24-309

Int J Numer Method Biomed Eng. 2024 May 12:e3824. doi: 10.1002/cnm.3824. Online ahead of print.

ABSTRACT

Thyroid nodules are commonly diagnosed with ultrasonography, which includes internal characteristics, varying looks, and hazy boundaries, making it challenging for a clinician to differentiate between malignant and benign forms based only on visual identification. The advancement of AI, particularly DL, provides significant breakthroughs in the domain of medical image identification. Yet, there are certain obstacles to achieving accuracy as well as efficacy in thyroid nodule detection. The thyroid nodules in this study are detected and classified using an inventive hybrid deep learning-assisted multi-classification method. The median blur method is applied in this work to eliminate the salt and pepper noise from the image. Then MPIU-Net-based segmentation is utilized to segment the image. The LGBPNP-based features are retrieved from the segmented image to obtain a single histogram sequence of the LGBP pattern in addition to other features like extraction of multi-texton and LTP-based features. After the feature extraction, the data augmentation process is applied and then the features are fed to the hybrid classification-based nodule classification model that comprises Deep Maxout and CNN, this hybrid classification trains the features and predicts the thyroid nodule. Additionally, the TIRADS score classification is used for the projected malignant thyroid nodule coupled with statistical features collected from the segmented. The DBNAAF with transfer learning model is employed to classify the grading of malignant thyroid nodules, where the weights of the model are learned with transfer learning. The MCC of the Hybrid Model is 0.9445, whereas the DCNN is 0.6858, YOLOV3-DMRF is 0.7229, CNN is 0.7780, DBN is 0.7601, Bi-GRU is 0.7038, Deep Maxout is 0.7528, and RNN is 0.8522, respectively.

PMID:38736034 | DOI:10.1002/cnm.3824

New Phytol. 2024 May 12. doi: 10.1111/nph.19806. Online ahead of print.

ABSTRACT

As temperature rises, net carbon uptake in tropical forests decreases, but the underlying mechanisms are not well understood. High temperatures can limit photosynthesis directly, for example by reducing biochemical capacity, or indirectly through rising vapor pressure deficit (VPD) causing stomatal closure. To explore the independent effects of temperature and VPD on photosynthesis we analyzed photosynthesis data from the upper canopies of two tropical forests in Panama with Generalized Additive Models. Stomatal conductance and photosynthesis consistently decreased with increasing VPD, and statistically accounting for VPD increased the optimum temperature of photosynthesis (T_opt) of trees from a VPD-confounded apparent T_opt of c. 30-31°C to a VPD-independent T_opt of c. 33-36°C, while for lianas no VPD-independent T_opt was reached within the measured temperature range. Trees and lianas exhibited similar temperature and VPD responses in both forests, despite 1500 mm difference in mean annual rainfall. Over ecologically relevant temperature ranges, photosynthesis in tropical forests is largely limited by indirect effects of warming, through changes in VPD, not by direct warming effects of photosynthetic biochemistry. Failing to account for VPD when determining T_opt misattributes the underlying causal mechanism and thereby hinders the advancement of mechanistic understanding of global warming effects on tropical forest carbon dynamics.

PMID:38736030 | DOI:10.1111/nph.19806

Pediatr Radiol. 2024 May 13. doi: 10.1007/s00247-024-05946-0. Online ahead of print.

ABSTRACT

BACKGROUND: Magnetic resonance imaging (MRI) findings associated with athletic pubalgia are well documented in the adult literature.

OBJECTIVE: To describe the spectrum of MRI findings in adolescents with pubic symphyseal injuries/athletic pubalgia.

MATERIALS AND METHODS: This is an institutional review board approved, retrospective study of all patients < 18 years who were referred for MRI, over the last 10 years. Two pediatric musculoskeletal radiologists evaluated the MRI in consensus for the following findings: Chronic Salter-Harris (SH)-I equivalent fracture or asymmetric parasymphyseal ossific fraying, non-retractile muscular tear or retraction, and edema of the aponeurosis and arcuate ligament. Radiographs were also reviewed for Risser stage.

RESULTS: Fifteen patients were identified (100% male, median age 17 years, IQR 16-17.6). Most patients (14/15, 93%) had either asymmetric parasymphyseal ossific fraying (4/15, 27%) or chronic SH-1 equivalent fracture (10/15, 67%) of the pubic symphysis, and all patients (15/15, 100%) had aponeurotic and arcuate ligament edema. Few patients had rectus abdominis muscular retraction (2/15, 13%), non-retractile muscular tear of the rectus abdominis (2/15, 13%), and/or adductor muscle (4/15, 27%). Risser stage was as follows: stages 0 (13%), 3 (7%), 4 (47%), and 5 (33%). The injuries in our limited data set were independent of skeletal maturity with no statistically significant association between any of the MRI findings and Risser stage.

CONCLUSION: The MR imaging spectrum of adolescent athletic pubalgia differs from the described findings in adults due to skeletal immaturity. The cleft sign described in adults manifests in adolescents as asymmetric parasymphyseal ossific fraying and chronic SH-1 equivalent fractures.

PMID:38736018 | DOI:10.1007/s00247-024-05946-0

Geroscience. 2024 May 13. doi: 10.1007/s11357-024-01191-3. Online ahead of print.

ABSTRACT

Stochastic epigenetic mutations (SEMs) have been proposed as novel aging biomarkers to capture heterogeneity in age-related DNA methylation changes. SEMs are defined as outlier methylation patterns at cytosine-guanine dinucleotide sites, categorized as hypermethylated (hyperSEM) or hypomethylated (hypoSEM) relative to a reference. Because SEMs are defined by their outlier status, it is critical to differentiate extreme values due to technical noise or data artifacts from those due to real biology. Using technical replicate data, we found SEM detection is not reliable: across 3 datasets, 24 to 39% of hypoSEM and 46 to 67% of hyperSEM are not shared between replicates. We identified factors influencing SEM reliability-including blood cell type composition, probe beta-value statistics, genomic location, and presence of SNPs. We used these factors in a training dataset to build a machine learning-based filter that removes unreliable SEMs, and found this filter enhances reliability in two independent validation datasets. We assessed associations between SEM loads and aging phenotypes in the Framingham Heart Study and discovered that associations with aging outcomes were in large part driven by hypoSEMs at baseline methylated probes and hyperSEMs at baseline unmethylated probes, which are the same subsets that demonstrate highest technical reliability. These aging associations were preserved after filtering out unreliable SEMs and were enhanced after adjusting for blood cell composition. Finally, we utilized these insights to formulate best practices for SEM detection and introduce a novel R package, SEMdetectR, which uses parallel programming for efficient SEM detection with comprehensive options for detection, filtering, and analysis.

PMID:38736015 | DOI:10.1007/s11357-024-01191-3

Sci Rep. 2024 May 13;14(1):10845. doi: 10.1038/s41598-024-61583-5.

ABSTRACT

With growing recognition of the importance of community engagement in addressing public health challenges, its role in promoting healthy behaviors and preventing infectious diseases has gained attention. However, vaccination coverage remains a significant concern in many developing countries. While previous studies have linked community engagement to positive health outcomes, there is a gap in understanding its influence on individual vaccination choices, particularly in the context of developing countries. Utilizing data from the 2021 Chinese General Social Survey (CGSS), this study examines the impact of community engagement on COVID-19 and flu vaccination uptake among 7281 individuals. Community engagement, measured by community vaccination notifications, serves as the key independent variable. The study employs Ordinary Least Squares (OLS) regression and Propensity Score Matching (PSM) methods to analyze the relationship between community engagement and vaccination behavior. The analysis reveals a positive association between community engagement and vaccination rates. Specifically, individuals receiving notifications were more likely to get the COVID-19 vaccine compared to non-recipients (vaccination rates: 100% vs. 53.3%), and flu vaccination rates were also significantly higher among those notified (2.7% vs. 1.9%). Mechanism analysis suggests that individuals receiving community notifications are more aware of the benefits of vaccination, leading to higher vaccination rates among this group. This study underscores the effectiveness of community engagement strategies in promoting positive vaccination behavior among individuals in China. By enhancing awareness and trust in immunization, community engagement initiatives play a crucial role in shaping health behaviors and improving vaccination uptake. These findings emphasize the importance of integrating community engagement approaches into public health interventions to address vaccination challenges.

PMID:38736012 | DOI:10.1038/s41598-024-61583-5

Environ Sci Pollut Res Int. 2024 May 12. doi: 10.1007/s11356-024-33565-7. Online ahead of print.

ABSTRACT

The “dual-carbon” objective presents a huge challenge for China and the world, with profound implications for the advancement of China’s eco-friendly economy. Additionally, informatization development has a significant impact on the level of carbon emissions in both local and neighbouring regions. Therefore, we employ panel data from 30 provinces in China spanning the years 2012 to 2021, and use the Kernel density estimate and Moran’s index to explore informatization level and carbon emissions space agglomeration characteristics. We elucidate the nonlinear relationship and heterogeneity between informatization improvement and carbon emissions based on the spatial Durbin model. The primary findings are as follows. Firstly, we discover a distinct spatial clustering phenomenon which the informatization level is high in coastal areas and low in inland areas, whereas carbon emissions are low in the south and high in the north. Secondly, the effect of the informatization level on carbon emissions is shown as a U-shaped and non-linear correlation, signifying inhibitory and subsequently promoting phases. Thirdly, we reveal the negative influence on carbon emissions caused by spatial lag terms of the informatization level, and find that a higher local informatization level will have an inhibitory effect on carbon emissions in neighbouring areas. Finally, there is a spatial heterogeneity in the impact of the informatization level on carbon emissions, which presents the U-shaped relation between informatization level and carbon emissions varies across the North-South subregion and the three major economic subregion of China.

PMID:38735997 | DOI:10.1007/s11356-024-33565-7

Langenbecks Arch Surg. 2024 May 13;409(1):157. doi: 10.1007/s00423-024-03349-1.

ABSTRACT

PURPOSE: The JCOG (Japan Clinical Oncology Group) 0212 study did not confirm the noninferiority of mesorectal excision (ME) alone to ME with LLND for rectal or anal adenocarcinomas. Furthermore, the significance of LLND for SCCs remains unknown. We evaluated the significance of lateral lymph node dissection (LLND) of squamous cell carcinoma (SCC) of the anal canal.

METHODS: This retrospective cohort study was conducted in 435 patients with SCCs among 1,781 patients with anal canal tumors. In 40 patients who underwent LLND, the 5-year relapse-free survival (5y-RFS) and 5-year overall survival (5y-OS) were compared between groups with positive and negative histopathological findings. In 71 patients with negative lateral lymph node metastasis in the preoperative diagnosis, the 5y-RFS, 5y-OS, and 5-year local recurrence-free survival were compared between patients who did and did not undergo LLND.

RESULTS: The clinical and pathological T stages predicted pathological lateral pelvic lymph node metastasis. There was no statistically significant difference in 5y-RFS and 5y-OS between patients who did and did not undergo LLND. Among patients who underwent LLND, 5y-RFS in those with positive histopathological findings (15.0%) was worse than that in those without (59.2%) (p = 0.002).

CONCLUSIONS: In patients who underwent LLND, 5y-RFS in those with positive histopathological findings than in those without LLND did not contribute to prognosis.

PMID:38735992 | DOI:10.1007/s00423-024-03349-1

Sci Rep. 2024 May 12;14(1):10843. doi: 10.1038/s41598-024-61391-x.

ABSTRACT

The Johns Hopkins Learning Environment Scale (JHLES) was developed by Robert B. Shochet, Jorie M. Colbert and Scott M. Wright of the Johns hopkins university school of medicine and consists of 28 items used to evaluate perception of the academic environment. The objective was to translate and adapt the JHLES to Polish cultural conditions and to validate the Polish version of the tool. The JHLES questionnaire was completed by students of all years (first-fifth) of the faculties of dental medicine at the Medical University of Lublin and the Medical University of Gdańsk. The total surveyed population consisted of 597 students. The overall reliability of the tool was excellent. Confirmatory factor analysis was performed in order to confirm structural consistency with the original JHLES tool. Consequently, all indices had acceptable values (close to 1 or 0, depending on the case), and there was consistency in the results, which shows that the JHLES model is supported by the data. In the present study, the JHLES has been validated in a sample of dental students for the first time in Poland and Europe. Our study provided good evidence for the reliability and validity of the Polish version of the JHLES. In conclusion, the Polish-language version of the JHLES questionnaire is a reliable and valid instrument for analysing the learning environment for students, and its factor structure is supported by the data.

PMID:38735990 | DOI:10.1038/s41598-024-61391-x