Search

BackgroundArtificial intelligence (AI) based computer-aided detection devices are recommended for screening and triaging of pulmonary tuberculosis (TB) using digital chest x-ray (CXR) images (soft copies). Most AI algorithms are trained using input data from digital CXR Digital Imaging and Communications in Medicine (DICOM) files. There can be scenarios when only digital CXR films (hard copies) are available for interpretation. A smartphone-captured photo of the digital CXR film may be used for AI to process in such a scenario. There is a gap in the literature investigating if there is a significant difference in the performance of AI algorithms when digital CXR DICOM files are used as input for AI to process as opposed to photos of the digital CXR films being used as input. ObjectiveThe primary objective was to compare the agreement of AI in detecting radiological signs of TB when using DICOM files (denoted as CXRd) as input versus when using smartphone-captured photos of digital CXR films (denoted as CXRp) with human readers. MethodsPairs of CXRd and CXRp images were obtained retrospectively from patients screened for TB. AI results were obtained using both the CXRd and CXRp files. The majority consensus on the presence or absence of TB in CXR pairs was obtained from a panel of 3 independent radiologists. The positive and negative percent agreement of AI in detecting radiological signs of TB in CXRd and CXRp were estimated by comparing with the majority consensus. The distribution of AI probability scores was also compared. ResultsA total of 1278 CXR pairs were analyzed. The positive percent agreement of AI was found to be 92.22% (95% CI 89.94-94.12) and 90.75% (95% CI 88.32-92.82), respectively, for CXRd and CXRp images (P=.09). The negative percent agreement of AI was 82.08% (95% CI 78.76-85.07) and 79.23% (95% CI 75.75-82.42), respectively, for CXRd and CXRp images (P=.06). The median of the AI probability score was 0.72 (IQR 0.11-0.97) in CXRd and 0.72 (IQR 0.14-0.96) in CXRp images (P=.75). ConclusionsWe did not observe any statistically significant differences in the output of AI in digital CXRs and photos of digital CXR films.

Introduction: Benign Prostatic Hyperplasia (BPH) is one of the most frequent diseases in men. The laser treatment for BPH has challenged TURP due to advances in laser technology, a better understanding of tissue-laser interactions and rowing clinical experience. Objective: To evaluate the safety and efficacy of HoLEP, comparing it to Bipolar TURP. Material and methods: This was a prospective study to evaluate the outcomes in BPH patients undergoing surgery by HOLEP and Bipolar TURP done between January 2018 to December 2019. A total of 80 Patients were enrolled, 40 undergoing HoLEP and the other 40 Bipolar TURP for BPH. The procedures were performed by a single surgeon. All patients with symptomatic BPH and who were candidates for surgical treatment were included. Patients with previous prostate surgery, urethral surgery, history of prostate cancer or neurogenic bladder were excluded. Results: Baseline parameters were almost similar between both the groups in terms of age, IPSS, QOL, Q max, PVR, and gland size. Operative time and resected gland weight were more in HoLEP arm (p Conclusion: Both Bipolar TURP and HoLEP were effective in relieving BOO. HoLEP has equal efficacy compared to conventional bipolar TURP, with decreased hospital stay and catheter indwelling time. The learning curve of HoLEP is steep; however, it can be overcome gradually.

In clinical trial monitoring, substantial resources are allocated to perform source data verification (SDV). SDV ensures accurate and reliable transcription of trial participant information. Clinical site visits are typically scheduled at a fixed frequency for SDV, without objectively factoring in individual site workload. This often results in wasted resources and directly influences clinical trial cost. We leveraged historical data from several hundred clinical trials to predict SDV workload at trial sites using machine learning. Specifically, we adopted cross industry standard process for data mining (CRISP-DM) process model and devised a novel deep learning pipeline for longitudinal clinical trial data. The deep learning pipeline, which comprises recurrent neural network-based encoder and decoder, ingests multivariate sequence data from study sites and predicts SDV workload for future months. We also developed an efficient model enhancement workflow, in a data science platform that facilitates machine learning operations best practices, for timely adaptation of new features and changes. Several enhancement iterations have been performed since the launch of first SDV workload prediction model, resulting in a more accurate latest model compared to previous versions. We discuss these enhancements in the context of CRISP-DM phases. In conclusion, the SDV workload prediction model has enabled informed planning and optimization of resources within clinical trial operations.

Background: percutaneous nephrolithotomy (PCNL) is a minimally invasive surgery to treat renal stones. Post-operative pain is distressing to the patient due to the injury to the capsule. Efficacy of ultrasound-guided thoracic paravertebral block at multiple level (T9–T10, T10–T11, T11–T12) was evaluated to manage postoperative analgesia in percutaneous nephrolithotomy surgeries. Methodology: a prospective randomized double-blind study of 60 cases of the American Society of Anesthesiologists I–II patients who underwent percutaneous nephrolithotomy were allocated into group P (test) and group N (control). Immediately after surgery, group P were given ultrasound-guided paravertebral block at T9–T10, T10–T11, T11–T12 on operated side using 5 ml of 0.25 % Levobupivacine at each level, while group N did not receive paravertebral block. The patients were assessed for visual analogue scale (VAS), time for first rescue analgesic, number of rescue analgesics in first 24 hrs postoperatively. Results: VAS pain scale shows significant difference between group P (4.2 + 0.8) and group N (5.3 + 1.1) (p < 0.05) at 30 mins, 2, 4, 8 hrs postoperatively. Total opioid consumption at postoperative 2, 6, and 24 hrs was less in group P than group N (P < 0.05). Number of rescue analgesics in first 24 hrs post-surgery in group P was 3.0 ± 0.4, and 4.0 ± 1.1 in group N with statistical significant difference (p = 0.0001). Total dose of opioid consumption (mg) in group P was 110 ± 40.45, and 155 ± 64.87 mg in group N with statistical significant difference (p = 0.002). The group N cases used more opioid than group P, with lower scores for satisfaction (p < 0.05). Analgesic consumption in postoperative 24 hrs of group P was less than that of group N (P = 0.001). Patient satisfaction score was significantly higher in group P than group N (P = 0.0001) in 24 hrs. No nausea and/or vomiting were noted in both groups. Conclusion: ultrasound-guided thoracic paravertebral block had more analgesic, and reduce the requirement of opioids and maintains stable hemodynamics.

Background: The chest radiograph (CXR) is the most frequently performed radiological examination worldwide. The increasing volume of CXRs performed in hospitals causes reporting backlogs and increased waiting times for patients, potentially compromising timely clinical intervention and patient safety. Implementing computer-aided detection (CAD) artificial intelligence (AI) algorithms capable of accurate and rapid CXR reporting could help address such limitations. A novel use for AI reporting is the classification of CXRs as ‘abnormal’ or ‘normal’. This classification could help optimize resource allocation and aid radiologists in managing their time efficiently. Methods: qXR is a CE-marked computer-aided detection (CAD) software trained on over 4.4 million CXRs. In this retrospective cross-sectional pre-deployment study, we evaluated the performance of qXR in stratifying normal and abnormal CXRs. We analyzed 1040 CXRs from various referral sources, including general practices (GP), Accident and Emergency (A&E) departments, and inpatient (IP) and outpatient (OP) settings at East Kent Hospitals University NHS Foundation Trust. The ground truth for the CXRs was established by assessing the agreement between two senior radiologists. Results: The CAD software had a sensitivity of 99.7% and a specificity of 67.4%. The sub-group analysis showed no statistically significant difference in performance across healthcare settings, age, gender, and X-ray manufacturer. Conclusions: The study showed that qXR can accurately stratify CXRs as normal versus abnormal, potentially reducing reporting backlogs and resulting in early patient intervention, which may result in better patient outcomes.

Background: Benign prostatic hyperplasia (BPH) is a common disease in elderly men. Monopolar transurethral resection of prostate (M-TURP) is considered the gold standard for the treatment of bladder outlet obstruction due to BPH. Its modification, bipolar TURP (B-TURP), promises to overcome its most prominent drawbacks, such as bleeding and dilutional hyponatremia. Aims and Objectives: This study aims to study the feasibility, effectiveness, and safety of B-TURP over M-TURP. Materials and Methods: A total of 110 patients with BPH were prospectively randomly assigned to undergo B-TURP (55) or M-TURP (55). Patient characteristics of the two groups were similar. Hemoglobin was measured preoperatively and postoperatively. IPSS, maximal flow rate, and post-void residual urine volume were assessed preoperatively. Duration of surgery, mean weight of resected tissue, mean irrigation fluid used, mean drop in hemoglobin, mean change in sodium, and mean post-operative irrigation used were also compared. Results: Duration of resection time was significantly shorter in M-TURP (P=0.0034). The mean change in sodium and mean post-operative irrigation used were significantly lower in bipolar group with P

In medical practice, chest X-rays are the most ubiquitous diagnostic imaging tests. However, the current workload in extensive health care facilities and lack of well-trained radiologists is a significant challenge in the patient care pathway. Therefore, an accurate, reliable, and fast computer-aided diagnosis (CAD) system capable of detecting abnormalities in chest X-rays is crucial in improving the radiological workflow. In this prospective multicenter quality-improvement study, we have evaluated whether artificial intelligence (AI) can be used as a chest X-ray screening tool in real clinical settings. Methods: A team of radiologists used the AI-based chest X-ray screening tool (qXR) as a part of their daily reporting routine to report consecutive chest X-rays for this prospective multicentre study. This study took place in a large radiology network in India between June 2021 and March 2022. Results: A total of 65,604 chest X-rays were processed during the study period. The overall performance of AI achieved in detecting normal and abnormal chest X-rays was good. The high negatively predicted value (NPV) of 98.9% was achieved. The AI performance in terms of area under the curve (AUC), NPV for the corresponding subabnormalities obtained were blunted CP angle (0.97, 99.5%), hilar dysmorphism (0.86, 99.9%), cardiomegaly (0.96, 99.7%), reticulonodular pattern (0.91, 99.9%), rib fracture (0.98, 99.9%), scoliosis (0.98, 99.9%), atelectasis (0.96, 99.9%), calcification (0.96, 99.7%), consolidation (0.95, 99.6%), emphysema (0.96, 99.9%), fibrosis (0.95, 99.7%), nodule (0.91, 99.8%), opacity (0.92, 99.2%), pleural effusion (0.97, 99.7%), and pneumothorax (0.99, 99.9%). Additionally, the turnaround time (TAT) decreased by about 40.63% from pre-qXR period to post-qXR period. Conclusions: The AI-based chest X-ray solution (qXR) screened chest X-rays and assisted in ruling out normal patients with high confidence, thus allowing the radiologists to focus more on assessing pathology on abnormal chest X-rays and treatment pathways.

Background: Missed findings in chest X-ray interpretation are common and can have serious consequences. Methods: Our study included 2407 chest radiographs (CXRs) acquired at three Indian and five US sites. To identify CXRs reported as normal, we used a proprietary radiology report search engine based on natural language processing (mPower, Nuance). Two thoracic radiologists reviewed all CXRs and recorded the presence and clinical significance of abnormal findings on a 5-point scale (1—not important; 5—critical importance). All CXRs were processed with the AI model (Qure.ai) and outputs were recorded for the presence of findings. Data were analyzed to obtain area under the ROC curve (AUC). Results: Of 410 CXRs (410/2407, 18.9%) with unreported/missed findings, 312 (312/410, 76.1%) findings were clinically important: pulmonary nodules (n = 157), consolidation (60), linear opacities (37), mediastinal widening (21), hilar enlargement (17), pleural effusions (11), rib fractures (6) and pneumothoraces (3). AI detected 69 missed findings (69/131, 53%) with an AUC of up to 0.935. The AI model was generalizable across different sites, geographic locations, patient genders and age groups. Conclusion: A substantial number of important CXR findings are missed; the AI model can help to identify and reduce the frequency of important missed findings in a generalizable manner.

Abstract The expanding knowledge of the variety of synthetic genetic elements has enabled the construction of new and more efficient genetic circuits and yielded novel insights into molecular mechanisms. However, context dependence, in which interactions between cis‐ or trans‐genetic elements affect the behavior of these elements, can reduce their general applicability or predictability. Genetic insulators, which mitigate unintended context‐dependent cis‐interactions, have been used to address this issue. One of the most commonly used genetic insulators is a self‐splicing ribozyme called RiboJ, which can be used to decouple upstream 5′ UTR in mRNA from downstream sequences (e.g., open reading frames). Despite its general use as an insulator, there has been no systematic study quantifying the efficiency of RiboJ splicing or whether this autocatalytic activity is robust to trans‐ and cis‐genetic context. Here, we determine the robustness of RiboJ splicing in the genetic context of six widely divergent E. coli strains. We also check for possible cis‐effects by assessing two SNP versions close to the catalytic site of RiboJ. We show that mRNA molecules containing RiboJ are rapidly spliced even during rapid exponential growth and high levels of gene expression, with a mean efficiency of 98%. We also show that neither the cis‐ nor trans‐genetic context has a significant impact on RiboJ activity, suggesting this element is robust to both cis‐ and trans‐genetic changes.

Purpose: We assessed whether a CXR AI algorithm was able to detect missed or mislabeled chest radiograph (CXR) findings in radiology reports. Methods: We queried a multi-institutional radiology reports search database of 13 million reports to identify all CXR reports with addendums from 1999–2021. Of the 3469 CXR reports with an addendum, a thoracic radiologist excluded reports where addenda were created for typographic errors, wrong report template, missing sections, or uninterpreted signoffs. The remaining reports contained addenda (279 patients) with errors related to side-discrepancies or missed findings such as pulmonary nodules, consolidation, pleural effusions, pneumothorax, and rib fractures. All CXRs were processed with an AI algorithm. Descriptive statistics were performed to determine the sensitivity, specificity, and accuracy of the AI in detecting missed or mislabeled findings. Results: The AI had high sensitivity (96%), specificity (100%), and accuracy (96%) for detecting all missed and mislabeled CXR findings. The corresponding finding-specific statistics for the AI were nodules (96%, 100%, 96%), pneumothorax (84%, 100%, 85%), pleural effusion (100%, 17%, 67%), consolidation (98%, 100%, 98%), and rib fractures (87%, 100%, 94%). Conclusions: The CXR AI could accurately detect mislabeled and missed findings. Clinical Relevance: The CXR AI can reduce the frequency of errors in detection and side-labeling of radiographic findings.

Recently, continuous glucose monitoring has gained global importance in diabetes management, leading to increased interest in noninvasive technologies as more convenient alternatives to traditional finger-pricking methods for frequent glucose monitoring. Sweat has emerged as a promising alternative, although challenges persist regarding the stability of disposable biosensors and the reliability of enzymes for detecting glucose concentration in human sweat. This study focuses on synthesizing Ti3C2Tx/polyaniline (PANI; MXP2; 1% Ti3C2Tx) ratios as electrocatalysts for enzyme-free glucose sensing, aiming to address these issues in noninvasive glucose detection. Furthermore, the parent Ti3C2Tx, PANI, and MXP2 were drop-coated over disposable screen-printed carbon electrodes (SPCE) to enable reliable, rapid, and easy glucose detection. The resulting MXP2, exhibiting semiconductor properties (Eg = −2.79 eV), showed excellent redox performance facilitated by its large active surface area, leading to enhanced electrocatalytic glucose oxidation. Modified PANI/SPCE, Ti3C2Tx/SPCE, and MXP2/SPCE sensors demonstrated excellent sensitivity values of 576.9, 687.44, and 1241.57 μA mM–1 cm–2, respectively, along with low detection limits of 25 nM, 18 nM, and 17 nM (considered S/N = 3). These sensitivities were observed in the linear dynamic range of 1–350 μM within the potential window of −0.5 V to +0.5 V. Furthermore, the MXP2/SPCE sensor exhibited repeatability with an RSD of 0.632% under artificial sweat conditions. Real glucose detection in human sweat was performed using the fast walking task. Overall, the MXP2/SPCE sensor shows promise as a stable, reliable, disposable, and cost-effective noninvasive enzyme-free device for wearable bioelectronics. [ABSTRACT FROM AUTHOR]

In this paper, Machine Learning Algorithms are used to implement the proposed approach to identify social distance, face masks, drowsiness detection, age-gender detection, and emotion detection. While dealing with social distancing initially, we need to detect humans' faces, which are available by using COCO (Common Objects in Context) datasets, and later on, polygon-shaped ROI (Rectangular-region of Interest) is warped with a rectangle, which helps to find the distance from each centroid (person). Similarly, we predict the facemask, age-gender, emotion, and drowsiness altogether using frontal-face detection and eye-detection via haarcascade dataset loaded into Convolutional Neural Network (CNN) to train and test the models on colour mapped images. In the proposed model, we are using machine-learning techniques such as linear discriminant Analysis (LDA), Independent Component Analysis (ICA), Principal Component Analysis (PCA) for age-gender detection and emotion detection, K-Nearest Neighbours (KNN) for Social Distancing, and Support Vector Machine (SVM) for facemask detection and drowsiness detection. The accuracy of proposed system depends on frame (i.e., 88.2%, 89.7%, 95.1% and 98.3% in 0~0.2s, 0.2~0.6s, 0.6~1s, >1s time windows respectively). The accuracy even depends upon the distance away from the camera (i.e., 60.4%, 73.9%, 89.3%, 95.2%, and 62.2% in >15, 15~10, 10~6, 6~0.5, <0.5 meters respectively). The resultant average accuracy of all the models is 96.3%, which is capable to predict various tasks as said above. This complete model is made accessible to users via a standalone software/Desktop GUI. The proposed approach is promising for performing all the tasks and activities more accurately and efficiently. the systemic health of the patient and avoiding possible drug interactions. [ABSTRACT FROM AUTHOR]

Background: Infertility is a crucial global public health issue that affects millions of people of reproductive age. Fertility-related stress can negatively impact infertile couples' quality of life (QoL). Aims: This study aimed to assess and compare the psychometric properties of fertility QoL between primary infertile couples' male and female partners. Settings and Design: This cross-sectional study included 114 primary infertile couples visiting the Andrology Laboratory referred from the Gynaecology and Obstetrics Department, AIIMS, Patna. Materials and Methods: Data were collected using the Fertility QoL (FertiQoL) tool, an internationally validated questionnaire to measure the reproductive QoL, demographic information and medical history. The FertiQoL questionnaire responses were recorded and analysed. Statistical Analyses Used: Statistical analyses used were performed using the SPSS 20.0 version. Descriptive statistics, Kolmogorov-Smirnov test, Cronbach's alpha and Student's independent t-tests were used. Statistical significance was set at P < 0.05. Results: In our study, the overall estimated Cronbach's a was 0.83, and males had a significantly better fertility-related QoL in all domains of the FertiQoL, such as emotional (P < 0.000), mind-body (P < 0.000), social (P < 0.004) and tolerability (P < 0.000), except relational and environmental domains, which were lower in them. However, between the groups, the relational domain was significant (0.000) and the environmental domain was non-significant (0.592). Overall, males had a significantly better total core score, total treatment score and overall total FertiQoL score, while females had lower scores. Conclusion: Amongst infertile couples, the reproductive QoL was poorer in females than in males. Our study suggests psychological counselling and mental support for females during infertility management. [ABSTRACT FROM AUTHOR]