Search

The vitellointestinal duct (VID) is an embryological remnant of the vitelline duct, a structure that connects the developing fetus to the yolk sac and is responsible for the nutritional support of the fetus during the early embryological days. The VID usually gets obliterated by the fifth to ninth week of gestational age after the establishment of placental nutrition. The patent VIDellointestinal duct is a relatively rare congenital condition that occurs in approximately 2% of the general population, with the most common presentation being Meckel's diverticulum. Complete patency is rarer, occurring in 0.1% of the general population. The complete persistence of the VID results in enterocutaneous fistula, and the presentation may vary, ranging from cutaneous manifestations like skin lesions, granulomas, abscesses, or umbilical discharge to abdominal symptoms including acute abdominal pain and hematochezia. Some patients are even asymptomatic and are detected incidentally. We present a rare case of complete patency of the VID in a 30-year-old adult male presenting with acute periumbilical pain. Imaging findings guided the diagnosis, and surgical resection with histopathological examination further confirmed the condition.

Pulmonary sequestration is a relatively rare phenomenon characterized by nonfunctional lung tissue supplied by one or more systemic arteries without direct connection to the tracheobronchial tree. Intra-lobar pulmonary sequestration comprises 75% of the total pulmonary sequestrations. Most patients with pulmonary sequestrations are often diagnosed with a childhood chest infection, so pulmonary sequestration is considered a childhood disease. However, few cases are found in adults and the elderly, with or without symptoms, and imaging findings on computed tomography (CT) or magnetic resonance imaging (MRI) are variable due to infection and inflammation. Failure to diagnose and treat this condition may lead to recurrent pneumonia and fatal hemoptysis. In this case report, we present cases of pulmonary sequestration at extremes of ages, one at 12 and the other at 65.

Congenital pulmonary airway malformation (CPAM) is a rare congenital dysplastic malformation characterized by failure of bronchial development and localized glandular overgrowth. Previously known as Congenital Cystic Adenoid Malformation (CCAM), CPAM is classified into 5 types, from type 0 to type IV, depending upon the origin of pulmonary areas of the lung, cyst size, and cyst appearance. CPAM is a rare congenital anomaly typically diagnosed prenatally in ultrasound. However, few cases are diagnosed in childhood and even fewer in adulthood. CPAM can be differentiated from pulmonary sequestration based on the origin of the arterial supply; the former has its arterial supply from the pulmonary artery, whereas pulmonary sequestration has its arterial supply from the systemic circulation. Another differential diagnosis of CPAM includes congenital bronchogenic cyst, congenital lobar emphysema, pleuropulmonary blastoma, congenital cystic bronchiectasis, and congenital diaphragmatic hernia. The most common presentation is recurrent chest infection and chest pain, whereas other presentation includes pneumothorax and hemoptysis. Here, we present a case of a 6-year-old child with recurrent episodes of fever and cough diagnosed as a type II CPAM based on computed tomography findings.

Abstract Background Liver is a complex, highly vascular organ, where anatomical variations are the norm. This study aimed to analyze all the three hepatic vascular anatomical variations in a single study which would help us understand the prevalence of hepatic vascular (arterial, portal, venous) anomalies in the population catered to by our institution. Methods A retrospective analysis of 545 contrast-enhanced CT scans was done from November 2019 from the institute PACS after satisfying the inclusion and exclusion criteria. The raw imaging data were processed in PACS software — Centricity™ Universal Viewer and Syngo.via Vb20 platform, for axial, coronal, and axial-oblique multiplanar reformation, maximum intensity projection (MIP), and volume rendering (VR) images. Data were analyzed in the three vascular phases to determine the anatomical variations. Analysis was done by two surgical residents in the division of HPB surgery, which was verified by a certified radiologist. Results There were no major differences in the prevalence rates of the vascular anomalies across gender and domicile distributions. The prevalence of normal hepatic artery and variant hepatic artery in our study was 69% and 31%, respectively. Accessory left hepatic artery (10%) was the most common hepatic artery variant in our study. Single RHV was seen in 77.4%, and other RHV variants like two RHV with common trunk, two RHV with independent drainage, and three RHV with common trunk contribute 22.6% of our study population. Accessory inferior RHV was seen in 19.8% of the study population. Normal portal vein anatomy was found in 81.1% in our study, and the most common variant in our study population was trifurcation of portal vein (16.1%). Conclusion This was the largest study until date from South India, studying all three hepatic vascular anatomical variations in a single study. Variations in the anatomy of hepatic arteries, portal veins, and hepatic veins are common. A good knowledge of the same is necessary especially for a hepatobiliary surgeon or for an interventional radiologist, to plan and avoid complications during a procedure. Preoperative contrast-enhanced CT scan and whenever necessary a VR or a MIP reconstruction will precisely help in identifying these variations.

Key Clinical Message Subarachnoid block with local anesthetic agents is a well‐established anesthesia technique among pregnant females for labor analgesia and cesarian delivery. Although it is considered a reliable and safe technique for both mothers and fetuses, unexpected high or low levels of block may occur due to accidental injection of these agents into different meningeal spaces other than intended. Hypotension, bradycardia, headache, and failed anesthesia are common complications of spinal anesthesia. Though rare, neurological complications like aphonia, dysphagia, and tingling sensation have also been reported. The article reports a case of a 22‐year‐old primigravida who sustained transient aphonia following intrathecal administration of bupivacaine for an emergency cesarian section for meconium‐stained liquor with fetal distress. There were no other neurological manifestations or features suggestive of high spinal block. The sensory level of the block was fixed to T6 with hemodynamic stability throughout aphasia with an episode of hypotension preceding aphonia. Aphonia commenced 9 min after the spinal anesthesia continued for a total duration of 15 min. Neurological examination, relevant investigations, and consultations were done to make a diagnosis. Thus, it is important to be aware of the possible neurological complications associated with spinal anesthesia.

Multiple sclerosis (MS) is a dangerous illness that strikes the central nervous system. The body’s immune system attacks myelin (an entity above the nerves) and impairs brain-to-body communication. To date, it is not possible to cure MS. However, symptoms can be managed, and treatments can be provided if the disease is diagnosed early. Hence, supervised machine learning (ML) algorithms and several hyperparameter tuning techniques, including Bayesian optimization, have been utilized in this study to predict MS in patients. Descriptive and inferential statistical analysis has been conducted before training the classifiers. The most essential markers were chosen using a technique called mutual information. Among the search techniques, the Bayesian optimization search technique prevailed to be pre-eminent, with an accuracy of 89%. To comprehend the diagnosis generated by the ML classifiers, four techniques of explainable artificial intelligence were utilized. According to them, the crucial attributes are periventricular magnetic resonance imaging (MRI), infratentorial MRI, oligoclonal bands, spinal cord MRI, breastfeeding, varicella disease, and initial symptoms. The models could be deployed in various medical facilities to detect MS in patients. The doctors could also use this framework to get a second opinion regarding the diagnosis.

Bacterial keratitis caused by Pseudomonas aeruginosa is indeed a serious concern due to its potential to cause blindness and its resistance to antibiotics, partly attributed to biofilm formation and cytotoxicity to the cornea. The present study uses a meta-analysis of a transcriptomics dataset to identify important genes and pathways in biofilm formation of P. aeruginosa induced keratitis. By combining data from several studies, meta-analysis can enhance statistical power and robustness, enabling the identification of 83 differentially expressed candidate genes, including fis that could serve as therapeutic targets. The approach of combining meta-analysis with virtual screening and in vitro methods provides a comprehensive strategy for identifying potential target genes and pathways crucial for bacterial biofilm formation and development anti-biofilm medications against P. aeruginosa infections. The study identified 83 candidate genes that exhibited differential expression in the biofilm state, with fis proposed as an ideal target for therapy for P. aeruginosa biofilm formation. These techniques, meta-analysis, virtual screening, and invitro methods were used in combination to diagnostically identify these genes, which play a significant role in biofilms. This finding has highlighted a hallmark target list for P. aeruginosa anti-biofilm potential treatments.

Postpartum depression (PPD) is a type of depression that mothers have following childbirth due to hormonal changes, psychological transition to parenting, and exhaustion. This depression strikes either during/or in the first year following childbirth. It is also a frequently disregarded medical condition that must be treated right away as it might have major repercussions. Machine learning (ML) and artificial intelligence (AI) are tools that healthcare professionals can utilize to anticipate this condition more rapidly and correctly. Consequently, we have demonstrated how to use explainable artificial intelligence (XAI) methods and heterogeneous classifiers to predict postpartum depression in mothers who have recently given birth. The K-Nearest Neighbor (KNN) model and the customized stack model outperformed all other classifiers. KNN model obtained 97% accuracy, 98% recall, and 95% precision and the stack model obtained 97% accuracy, 100% recall, and 94% precision, respectively. A set of frameworks and resources known as explainable artificial intelligence (XAI) facilitates the comprehension and interpretation of predictions made by machine learning algorithms. Four distinct XAI techniques: ELI5, Shapley Additive Values (SHAP), Local Interpretable Model-agnostic Explanations (LIME), and Anchor – have been used to interpret the model predictions. Explainability, interpretability, accountability, and transparency are crucial parameters of XAI, ensuring that machine learning models provide understandable and trustworthy results to users and stakeholders. The goal of this interdisciplinary research is to develop an automated diagnosis framework with tools that can transform therapy for postpartum depression leading to suicide attempts and empower medical professionals to offer mothers individualized, high-quality care.

Anaemia is a disorder marked by low blood levels of haemoglobin (HGB), affecting people of all ages and ethnicities and is a major global public health concern. Anaemia must be diagnosed as soon as possible to enable prompt treatment and intervention, which can reduce complications and enhance patient outcomes. With the ability to improve diagnostic precision and expedite patient care procedures, machine learning (ML) has become a potent instrument in the healthcare industry. Hence, we examine the use of ML approaches to predict haemoglobin-like anaemia in this research article. Based on a heterogeneous dataset of blood markars, we investigate the performance of many machine learning techniques such as Logistic Regression, CatBoost, XgBoost Decision Trees, KNN and others. The algorithms are further ensembled using a customized stacking approach. The ML models' judgments are interpreted using explainable artificial intelligence (XAI) methods. The xgboost and the stacking classifier obtained an accuracy, precision and recall of 99% each. Our research shows how ML models can help with the early diagnosis and treatment of anaemia, which will ultimately lead to better patient outcomes and healthcare results. Overall, the research shows how ML emphasizes the value of interdisciplinary cooperation in solving challenging medical problems.

Diabetes is a fast-developing medical issue that causes most renal and cardiac illnesses. Thus, diabetes management requires regular glucose monitoring. One potential technology is non-invasive glucometer monitoring. This work aims to develop a user-friendly near-infrared sensor-based non-invasive glucose monitoring system, correlating sensor output voltage variations with glucose levels, to provide accurate and convenient glucose monitoring for diabetes management. The objective is to validate the system’s accuracy against existing fingerpick methods and analyze its performance across different age groups and food intake conditions through experimental testing and Clarke grid analysis. In our research, we propose a near-infrared sensor-based non-invasive-type glucose monitoring technique which is a user-friendly system. The experimental setup and prototype system are designed and implemented for measuring the variation of glucose level with respect to a sensor output voltage. Using Beer Lambert’s law, the established results correlated the absorbance property of light with the sample concentration level. Demonstration of testing for different aged people was done under various food intake conditions. The obtained results are tabulated and validated with the existing fingerpick method and achieved an accuracy of 97.8%. Also, Clarke grid analysis has been done and depicted the pattern obtained.

Schizophrenia is a complicated and multidimensional mental condition marked by a wide range of emotional, cognitive, and behavioural symptoms. Although the exact root cause of schizophrenia is unknown, experts believe that a complex interaction of genetic, environmental, neurobiological, neurodevelopmental, and immune system dysfunctional elements are the contributing factors. In healthcare, artificial intelligence (AI) is used for analysing big datasets, enhance patient care, personalize treatment regimens, improve diagnostic accuracy, and expedite administrative duties. Hence, ML has been used to diagnose Schizophrenia in this study. The term ‘explainable artificial intelligence' (XAI) describes the development of AI systems that are able to provide understandable explanations for their choices as well as behaviours. In our research paper, we harnessed the power of five diverse XAI methodologies: LIME (Local Interpretable Model-agnostic Explanations), SHAP (Shapley Additive exPlanations), ELI5 (Explain Like I'm 5), QLattice, and Anchor. According to (XAI), the most significant attributes include age range, sex, the presence of a triradius on the left thumb, the total number of triradii, and the left thenar region's palmar pattern. By enabling early intervention, automatic identification of schizophrenia using XAI can benefit patients, assisting doctors in making precise diagnoses, assisting medical personnel in maximizing resource allocation and care coordination.

Myocardial infarction (MI) is the leading cause of human death globally. It occurs when a blockage in an artery prevents blood and oxygen from reaching the heart muscle, causing tissues in the heart muscle to die. This leads to a necessity to develop a method to diagnose MI’s early, preventing further complications such as irregular heart rhythm, heart failure or even cardiac arrest. This research aims to develop a more accurate machine learning (ML) model to help predict acute myocardial infarction (AMI) with a greater degree of accuracy without invasive procedures using additional explainable artificial intelligence (XAI) techniques which will help medical practitioners to better diagnose AMI more precisely. According to the results, the random forest classifier model gave the highest accuracy of 86%. XAI techniques were used to visualize the data and results, and determined white blood cell (WBC) count to be the most crucial feature in classification, followed by neutrophil (NEU) count, neutrophil-lymphocyte (NEU/LY) ratio, platelet width of distribution (PDW) values and basophil (BA) counts. The developed model can help medical practitioners make a more accurate early diagnosis of AMI using readily available hematological parameters, enabling practitioners to provide superior care to a diverse range of individuals.

According to various studies, different countries have different climate conditions that affect the quantity and quality of crop production. Farmers want to use novel technologies that can help them produce crops in large quantities with good quality. The greenhouse is one of the rapidly growing technologies used for the production of crops. It protects the crops from changes in external weather conditions and, hence, helps to produce good-quality crops throughout the year. This work proposes a deep study of the technologies used in the greenhouse for the monitoring and control of various environmental parameters that affect the quality and production of the crops. This work also analyses the different communication techniques, relays, and sensors used for monitoring and controlling the different greenhouse parameters. Also, give details on sensors and the advantages and disadvantages of different communication technologies so that farmers can easily understand which technology is most suitable for their greenhouse. This study helps the farmers adopt the best-suited techniques in their green houses that are cost-friendly, easy to use, and have a longer life.

Background Low back pain (LBP), the primary cause of disability, is the most common musculoskeletal disorder globally and the primary cause of disability. Magnetic resonance imaging (MRI) studies are inconclusive and less sensitive for identifying and classifying patients with LBP. Hence, this study aimed to investigate the role of artificial intelligence (AI) models in the prediction of LBP using T2 weighted MRI image of the lumbar spine. Methods This was a prospective case-control study. A total of 200 MRI patients (100 cases and controls each) referred for lumbar spine and whole spine screening were included. The scans were performed using 3.0 Tesla MRI (United Imaging Healthcare). T2 weighted images of the lumbar spine were segmented to extract radiomic features. Machine learning (ML) models, such as random forest, decision tree, logistic regression, K-nearest neighbors, adaboost, and deep learning methods (DL), such as ResNet and GoogleNet, were used, and performance measures were calculated. Results Our study showed that Random forest and AdaBoost are the most reliable ML models for predicting LBP. Random forest showed high performance with area under curve (AUC) values from 0.83 to 0.88 across all lumbar vertebrae and L2-L3, L3-L4, and L4-L5 intervertebral discs (IVDs), with AUCs of 0.88 the highest at L5-S1 IVD (0.92). Adaboost demonstrated high performance at the L2-L5 vertebrae with AUC values of 0.82 to 0.90, with the highest AUC (0.97) at the L5-S1 IVD. Among the DL models, GoogleNet outperformed the other models at 30 epochs with an accuracy of 0.85, followed by ResNet 18 (30 epochs) with an accuracy of 0.84. Conclusion The study demonstrated that ML and DL models can effectively predict LBP from MRI T2 weighted image of the lumbar spine. ML and DL models could also enhance the diagnostic accuracy of LBP, potentially leading to better patient management and outcomes.

Background Low back pain (LBP), the primary cause of disability, is the most common musculoskeletal disorder globally and the primary cause of disability. Magnetic resonance imaging (MRI) studies are inconclusive and less sensitive for identifying and classifying patients with LBP. Hence, this study aimed to investigate the role of artificial intelligence (AI) models in the prediction of LBP using T2 weighted MRI image of the lumbar spine. Methods This was a prospective case-control study. A total of 200 MRI patients (100 cases and controls each) referred for lumbar spine and whole spine screening were included. The scans were performed using 3.0 Tesla MRI (United Imaging Healthcare). T2 weighted images of the lumbar spine were segmented to extract radiomic features. Machine learning (ML) models, such as random forest, decision tree, logistic regression, K-nearest neighbors, adaboost, and deep learning methods (DL), such as ResNet and GoogleNet, were used, and performance measures were calculated. Results Our study showed that Random forest and AdaBoost are the most reliable ML models for predicting LBP. Random forest showed high performance with area under curve (AUC) values from 0.83 to 0.88 across all lumbar vertebrae and L2-L3, L3-L4, and L4-L5 intervertebral discs (IVDs), with AUCs of 0.88 the highest at L5-S1 IVD (0.92). Adaboost demonstrated high performance at the L2-L5 vertebrae with AUC values of 0.82 to 0.90, with the highest AUC (0.97) at the L5-S1 IVD. Among the DL models, GoogleNet outperformed the other models at 30 epochs with an accuracy of 0.85, followed by ResNet 18 (30 epochs) with an accuracy of 0.84. Conclusion The study demonstrated that ML and DL models can effectively predict LBP from MRI T2 weighted image of the lumbar spine. ML and DL models could also enhance the diagnostic accuracy of LBP, potentially leading to better patient management and outcomes.