Diagnostic Accuracy of Automated Diabetic Retinopathy Image Assessment Softwares: IDx-DR and Medios Artificial Intelligence.

INTRODUCTION: Numerous studies have demonstrated the use of artificial intelligence (AI) for early detection of referable diabetic retinopathy (RDR). A direct comparison of these multiple automated diabetic retinopathy (DR) image assessment softwares (ARIAs) is, however, challenging. We retrospectively compared the performance of two modern ARIAs, IDx-DR and Medios AI. METHODS: In this retrospective-comparative study, retinal images with sufficient image quality were run on both ARIAs. They were captured in 811 consecutive patients with diabetes visiting diabetic clinics in Poland. For each patient, four non-mydriatic images, 45° field of view, i.e., two sets of one optic disc and one macula-centered image using Topcon NW400 were captured. Images were manually graded for severity of DR as no DR, any DR (mild non-proliferative diabetic retinopathy [NPDR] or more severe disease), RDR (moderate NPDR or more severe disease and/or clinically significant diabetic macular edema [CSDME]), or sight-threatening DR (severe NPDR or more severe disease and/or CSDME) by certified graders. The ARIA output was compared to manual consensus image grading (reference standard). RESULTS: On 807 patients, based on consensus grading, there was no evidence of DR in 543 patients (67%). Any DR was seen in 264 (33%) patients, of which 174 (22%) were RDR and 41 (5%) were sight-threatening DR. The sensitivity of detecting RDR against reference standard grading was 95% (95% CI: 91, 98%) and the specificity was 80% (95% CI: 77, 83%) for Medios AI. They were 99% (95% CI: 96, 100%) and 68% (95% CI: 64, 72%) for IDx-DR, respectively. CONCLUSION: Both the ARIAs achieved satisfactory accuracy, with few false negatives. Although false-positive results generate additional costs and workload, missed cases raise the most concern whenever automated screening is debated.

Validation of a simple-to-use, affordable, portable, wavefront aberrometry-based auto refractometer in the adult population: A prospective study.

BACKGROUND: Refraction is one of the key components of a comprehensive eye examination. Auto refractometers that are reliable and affordable can be beneficial, especially in a low-resource community setting. The study aimed to validate the accuracy of a novel wave-front aberrometry-based auto refractometer, Instaref R20 against the open-field system and subjective refraction in an adult population. METHODS: All the participants underwent a comprehensive eye examination including objective refraction, subjective acceptance, anterior and posterior segment evaluation. Refraction was performed without cycloplegia using WAM5500 open-field auto refractometer (OFAR) and Instaref R20, the study device. Agreement between both methods was evaluated using Bland-Altman analysis. The repeatability of the device based on three measurements in a subgroup of 40 adults was assessed. RESULTS: The refractive error was measured in 132 participants (mean age,30.53 ± 9.36 years, 58.3% female). The paired mean difference of the refraction values of the study device against OFAR was - 0.13D for M, - 0.0002D (J0) and - 0.13D (J45) and against subjective refraction (SR) was - 0.09D (M), 0.06 (J0) and 0.03D (J45). The device agreed within +/- 0.50D of OFAR in 78% of eyes for M, 79% for J0 and 78% for J45. The device agreed within +/- 0.5D of SR values for M (84%), J0 (86%) and J45 (89%). CONCLUSION: This study found a good agreement between the measurements obtained with the portable autorefractor against open-field refractometer and SR values. It has a potential application in population-based community vision screening programs for refractive error correction without the need for highly trained personnel.

Identification of kinases and kinase inhibitors for the differential targeting of Wnt/ß-catenin signaling in gastric cancer subtypes.

The oncogenic signaling pathway Wnt is often activated in many cancers including gastric cancer. Wnt signaling pathway is considered as a potential target for developing new targeted therapeutics. Kinase inhibitors are the promising class of drugs for many diseases including cancers. Toward identifying the potent inhibitors targeting Wnt signaling pathway, a kinase inhibitor library with 82 inhibitors were screened using Wnt pathway reporter assay in gastric cancer cells. Notably, 34 kinase inhibitors were identified to inhibit Wnt mediated reporter activity to the extent of more than 50%. The corresponding kinase genes, which are known targets of these kinase inhibitors, were investigated for their expression in the available mRNA profiles of gastric tumors. A major group of the kinase genes showed higher expression in intestinal subtype gastric tumors. Another group of kinase genes were found expressed in diffuse type gastric tumors. The kinase genes expressed in intestinal type gastric tumors were found associated with varying survival of gastric cancer patients whereas those expressed in diffuse type tumors were found associated with the poor survival. Thus, the kinase genes specifically expressed in intestinal and diffuse type gastric tumors and the kinase inhibitors to target Wnt signaling pathway in gastric cancer subtypes have been identified.

A Two-Pronged Pulmonary Gene Delivery Strategy: A Surface-Modified Fullerene Nanoparticle and a Hypotonic Vehicle.

Inhaled gene therapy poses a unique potential of curing chronic lung diseases, which are currently managed primarily by symptomatic treatments. However, it has been challenging to achieve therapeutically relevant gene transfer efficacy in the lung due to the presence of numerous biological delivery barriers. Here, we introduce a simple approach that overcomes both extracellular and cellular barriers to enhance gene transfer efficacy in the lung in vivo. We endowed tetra(piperazino)fullerene epoxide (TPFE)-based nanoparticles with non-adhesive surface polyethylene glycol (PEG) coatings, thereby enabling the nanoparticles to cross the airway mucus gel layer and avoid phagocytic uptake by alveolar macrophages. In parallel, we utilized a hypotonic vehicle to facilitate endocytic uptake of the PEGylated nanoparticles by lung parenchymal cells via the osmotically driven regulatory volume decrease (RVD) mechanism. We demonstrate that this two-pronged delivery strategy provides safe, wide-spread and high-level transgene expression in the lungs of both healthy mice and mice with chronic lung diseases characterized by reinforced delivery barriers.

Focused Ultrasound Preconditioning for Augmented Nanoparticle Penetration and Efficacy in the Central Nervous System.

Microbubble activation with focused ultrasound (FUS) facilitates the noninvasive and spatially-targeted delivery of systemically administered therapeutics across the blood-brain barrier (BBB). FUS also augments the penetration of nanoscale therapeutics through brain tissue; however, this secondary effect has not been leveraged. Here, 1 MHz FUS sequences that increase the volume of transfected brain tissue after convection-enhanced delivery of gene-vector "brain-penetrating" nanoparticles were first identified. Next, FUS preconditioning is applied prior to trans-BBB nanoparticle delivery, yielding up to a fivefold increase in subsequent transgene expression. Magnetic resonance imaging (MRI) analyses of tissue temperature and Ktrans confirm that augmented transfection occurs through modulation of parenchymal tissue with FUS. FUS preconditioning represents a simple and effective strategy for markedly improving the efficacy of gene vector nanoparticles in the central nervous system.

Sensory feedback independent pre-song vocalizations correlate with time to song initiation.

The song of the adult male zebra finch is a well-studied example of a learned motor sequence. Song bouts begin with a variable number of introductory notes (INs) before actual song production. Previous studies have shown that INs progress from a variable initial state to a stereotyped final state before each song. This progression is thought to represent motor preparation, but the underlying mechanisms remain poorly understood. Here, we assessed the role of sensory feedback in the progression of INs to song. We found that the mean number of INs before song and the progression of INs to song were not affected by removal of two sensory feedback pathways (auditory or proprioceptive). In both feedback-intact and feedback-deprived birds, the presence of calls (other non-song vocalizations), just before the first IN, was correlated with fewer INs before song and an initial state closer to song. Finally, the initial IN state correlated with the time to song initiation. Overall, these results show that INs do not require real-time sensory feedback for progression to song. Rather, our results suggest that changes in IN features and their transition to song are controlled by internal neural processes, possibly involved in getting the brain ready to initiate a learned movement sequence.

Comparative Assessment of Patient Care Expenses among Intensive Care Units of a Tertiary Care Teaching Hospital using Cost Block Method.

INTRODUCTION: Intensive care services of a hospital are found to consume major chunk of hospital resources as well draining the savings of patients. Implementing proper control measures facilitates effective functioning of critical care services. AIM: Identify various costs involved in operating Surgical Intensive Care Unit (SICU) and Respiratory Intensive Care Unit (RICU); also find out the running cost of the same. METHODOLOGY: Retrospective data was collected for 12 months period and prospectively through informal interactions with staff. RESULTS: Construction and estate costs of the respective ICU's were found to be high, followed by laboratory charges. Running cost of RICU was found to be more than SICU. CONCLUSION: Costing of intensive care service is essential for controlled operations and to provide efficient patient care.

Hydrogel-assisted functional reconstitution of human P-glycoprotein (ABCB1) in giant liposomes.

This paper describes the formation of giant proteoliposomes containing P-glycoprotein (P-gp) from a solution of small proteoliposomes that had been deposited and partially dried on a film of agarose. This preparation method generated a significant fraction of giant proteoliposomes that were free of internalized vesicles, making it possible to determine the accessible liposome volume. Measuring the intensity of the fluorescent substrate rhodamine 123 (Rho123) inside and outside these giant proteoliposomes determined the concentration of transported substrates of P-gp. Fitting a kinetic model to the fluorescence data revealed the rate of passive diffusion as well as active transport by reconstituted P-gp in the membrane. This approach determined estimates for the membrane permeability coefficient (Ps) of passive diffusion and rate constants of active transport (kT) by P-gp as a result of different experimental conditions. The Ps value for Rho123 was larger in membranes containing P-gp under all assay conditions than in membranes without P-gp indicating increased leakiness in the presence of reconstituted transmembrane proteins. For P-gp liposomes, the kT value was significantly higher in the presence of ATP than in its absence or in the presence of ATP and the competitive inhibitor verapamil. This difference in kT values verified that P-gp was functionally active after reconstitution and quantified the rate of active transport. Lastly, patch clamp experiments on giant proteoliposomes showed ion channel activity consistent with a chloride ion channel protein that co-purified with P-gp. Together, these results demonstrate several advantages of using giant rather than small proteoliposomes to characterize transport properties of transport proteins and ion channels.

A combination of curcumin with either gramicidin or ouabain selectively kills cells that express the multidrug resistance-linked ABCG2 transporter.

This paper introduces a strategy to kill selectively multidrug-resistant cells that express the ABCG2 transporter (also called breast cancer resistance protein, or BCRP). The approach is based on specific stimulation of ATP hydrolysis by ABCG2 transporters with subtoxic doses of curcumin combined with stimulation of ATP hydrolysis by Na(+),K(+)-ATPase with subtoxic doses of gramicidin A or ouabain. After 72 h of incubation with the drug combinations, the resulting overconsumption of ATP by both pathways inhibits the efflux activity of ABCG2 transporters, leads to depletion of intracellular ATP levels below the viability threshold, and kills resistant cells selectively over cells that lack ABCG2 transporters. This strategy, which was also tested on a clinically relevant human breast adenocarcinoma cell line (MCF-7/FLV1), exploits the overexpression of ABCG2 transporters and induces caspase-dependent apoptotic cell death selectively in resistant cells. This work thus introduces a novel strategy to exploit collateral sensitivity (CS) with a combination of two clinically used compounds that individually do not exert CS. Collectively, this work expands the current knowledge on ABCG2-mediated CS and provides a potential strategy for discovery of CS drugs against drug-resistant cancer cells.

Dual role of the metalloprotease FtsH in biogenesis of the DrrAB drug transporter.

This study provides the first direct evidence for the dual role of the metalloprotease FtsH in membrane protein biogenesis. Using the physiological substrate DrrAB, it is shown that FtsH is not only responsible for proteolysis of unassembled DrrB protein but also plays a much broader role in biogenesis of the DrrAB complex. Previous studies showed that the stable expression of DrrB in the membrane depends on simultaneous expression of DrrA. Here we show that DrrB is proteolyzed by FtsH when it is expressed alone. Moreover, DrrA and DrrB proteins expressed together in a temperature-sensitive ftsH mutant strain of Escherichia coli were found to be nonfunctional due to their incorrect assembly. Simultaneous expression of wild-type FtsH in trans resulted in normal doxorubicin efflux. Strikingly, doxorubicin efflux could be restored in mutant cells irrespective of whether FtsH was expressed simultaneously with DrrAB or expressed after these proteins had already accumulated in an inactive conformation, thus providing crucial evidence for the ability of FtsH to refold the misassembled proteins. Complementation experiments also showed that the catalytic AAA domain of FtsH contains a chaperone-like activity, however, unlike wild-type FtsH, it was unable to restore function. Our results therefore show for the first time that FtsH contains the protease as well as refolding functions, and both the AAA and the proteolytic domains of FtsH are required for each of these activities.

Non-viral delivery of nucleic acid for treatment of rare diseases of the muscle.

Rare muscular disorders (RMDs) are disorders that affect a small percentage of the population. The disorders which are attributed to genetic mutations often manifest in the form of progressive weakness and atrophy of skeletal and heart muscles. RMDs includes disorders such as Duchenne muscular dystrophy (DMD), GNE myopathy, spinal muscular atrophy (SMA), limb girdle muscular dystrophy, and so on. Due to the infrequent occurrence of these disorders, development of therapeutic approaches elicits less attention compared with other more prevalent diseases. However, in recent times, improved understanding of pathogenesis has led to greater advances in developing therapeutic options to treat such diseases. Exon skipping, gene augmentation, and gene editing have taken the spotlight in drug development for rare neuromuscular disorders. The recent innovation in targeting and repairing mutations with the advent of CRISPR technology has in fact opened new possibilities in the development of gene therapy approaches for these disorders. Although these treatments show satisfactory therapeutic effects, the susceptibility to degradation, instability, and toxicity limits their application. So, an appropriate delivery vector is required for the delivery of these cargoes. Viral vectors are considered potential delivery systems for gene therapy; however, the associated concurrent immunogenic response and other limitations have paved the way for the applications of other non-viral systems like lipids, polymers, cellpenetrating peptides (CPPs), and other organic and inorganic materials. This review will focus on non-viral vectors for the delivery of therapeutic cargoes in order to treat muscular dystrophies.

Examining Diagnostic Errors in the Field of Otorhinolaryngology within the Challenging Landscape of Limited-Resource Healthcare.

Diagnostic accuracy is vital in otorhinolaryngology for effective patient care, yet diagnostic mismatches between non-otorhinolaryngology clinicians and ENT specialists can occur. However, studies investigating such mismatches in low-resource healthcare environments are limited. This study aims to analyze diagnostic mismatches in otorhinolaryngology within a low-resource healthcare environment. A publicly available dataset assessing diagnostic outcomes from non-otorhinolaryngology clinicians and ENT specialists was analyzed. The dataset included demographic characteristics, referral diagnoses, and final ENT specialist diagnoses. Descriptive statistics and appropriate statistical tests were employed to assess the prevalence of diagnostic mismatches and associated factors. The analysis comprised 1544 cases. The prevalence of diagnostic mismatches between non-otorhinolaryngology clinicians and ENT specialists was 67.4%. Certain specific ENT diseases demonstrated higher frequencies of diagnostic mismatches. Factors such as mismatch in the diagnosis and compliance of patient were found to influence the occurrence of diagnostic mismatches. This study highlights the presence of diagnostic mismatches in otorhinolaryngology within a low-resource healthcare environment. The prevalence of these mismatches underscores the need for improved diagnostic practices in such settings. Factors contributing to diagnostic mismatches should be further explored to develop strategies for enhancing diagnostic accuracy and reducing diagnostic errors in otorhinolaryngology.

An optimized convolutional neural network architecture for lung cancer detection.

Lung cancer, the treacherous malignancy affecting the respiratory system of a human body, has a devastating impact on the health and well-being of an individual. Due to the lack of automated and noninvasive diagnostic tools, healthcare professionals look forward toward biopsy as a gold standard for diagnosis. However, biopsy could be traumatizing and expensive process. Additionally, the limited availability of dataset and inaccuracy in diagnosis is a major drawback experienced by researchers. The objective of the proposed research is to develop an automated diagnostic tool for screening of lung cancer using optimized hyperparameters such that convolutional neural network (CNN) model generalizes well for universally obtained computerized tomography (CT) slices of lung pathologies. The aforementioned objective is achieved in the following ways: (i) Initially, a preprocessing methodology specific to lung CT scans is formulated to avoid the loss of information due to random image smoothing, and (ii) a sine cosine algorithm optimization algorithm (SCA) is integrated in the CNN model, to optimally select the tuning parameters of CNN. The error rate is used as an objective function, and the SCA algorithm tries to minimize. The proposed method successfully achieved an average classification accuracy of 99% in classification of lung scans in normal, benign, and malignant classes. Further, the generalization ability of the proposed model is tested on unseen dataset, thereby achieving promising results. The quantitative results prove the efficacy of the system to be used by radiologists in a clinical scenario.

Empowering Portable Age-Related Macular Degeneration Screening: Evaluation of a Deep Learning Algorithm for a Smartphone Fundus Camera.

OBJECTIVES: Despite global research on early detection of age-related macular degeneration (AMD), not enough is being done for large-scale screening. Automated analysis of retinal images captured via smartphone presents a potential solution; however, to our knowledge, such an artificial intelligence (AI) system has not been evaluated. The study aimed to assess the performance of an AI algorithm in detecting referable AMD on images captured on a portable fundus camera. DESIGN, SETTING: A retrospective image database from the Age-Related Eye Disease Study (AREDS) and target device was used. PARTICIPANTS: The algorithm was trained on two distinct data sets with macula-centric images: initially on 108,251 images (55% referable AMD) from AREDS and then fine-tuned on 1108 images (33% referable AMD) captured on Asian eyes using the target device. The model was designed to indicate the presence of referable AMD (intermediate and advanced AMD). Following the first training step, the test set consisted of 909 images (49% referable AMD). For the fine-tuning step, the test set consisted of 238 (34% referable AMD) images. The reference standard for the AREDS data set was fundus image grading by the central reading centre, and for the target device, it was consensus image grading by specialists. OUTCOME MEASURES: Area under receiver operating curve (AUC), sensitivity and specificity of algorithm. RESULTS: Before fine-tuning, the deep learning (DL) algorithm exhibited a test set (from AREDS) sensitivity of 93.48% (95% CI: 90.8% to 95.6%), specificity of 82.33% (95% CI: 78.6% to 85.7%) and AUC of 0.965 (95% CI:0.95 to 0.98). After fine-tuning, the DL algorithm displayed a test set (from the target device) sensitivity of 91.25% (95% CI: 82.8% to 96.4%), specificity of 84.18% (95% CI: 77.5% to 89.5%) and AUC 0.947 (95% CI: 0.911 to 0.982). CONCLUSION: The DL algorithm shows promising results in detecting referable AMD from a portable smartphone-based imaging system. This approach can potentially bring effective and affordable AMD screening to underserved areas.

Evaluation of an AI algorithm trained on an ethnically diverse dataset to screen a previously unseen population for diabetic retinopathy.

PURPOSE: This study aimed to determine the generalizability of an artificial intelligence (AI) algorithm trained on an ethnically diverse dataset to screen for referable diabetic retinopathy (RDR) in the Armenian population unseen during AI development. METHODS: This study comprised 550 patients with diabetes mellitus visiting the polyclinics of Armenia over 10 months requiring diabetic retinopathy (DR) screening. The Medios AI-DR algorithm was developed using a robust, diverse, ethnically balanced dataset with no inherent bias and deployed offline on a smartphone-based fundus camera. The algorithm here analyzed the retinal images captured using the target device for the presence of RDR (i.e., moderate non-proliferative diabetic retinopathy (NPDR) and/or clinically significant diabetic macular edema (CSDME) or more severe disease) and sight-threatening DR (STDR, i.e., severe NPDR and/or CSDME or more severe disease). The results compared the AI output to a consensus or majority image grading of three expert graders according to the International Clinical Diabetic Retinopathy severity scale. RESULTS: On 478 subjects included in the analysis, the algorithm achieved a high classification sensitivity of 95.30% (95% CI: 91.9%-98.7%) and a specificity of 83.89% (95% CI: 79.9%-87.9%) for the detection of RDR. The sensitivity for STDR detection was 100%. CONCLUSION: The study proved that Medios AI-DR algorithm yields good accuracy in screening for RDR in the Armenian population. In our literature search, this is the only smartphone-based, offline AI model validated in different populations.

Diagnostic performance of the offline Medios Artificial Intelligence (AI) for glaucoma detection in a rural tele-ophthalmology setting.

PURPOSE: This study assesses the diagnostic efficacy of offline Medios Artificial Intelligence (AI) glaucoma software in a primary eyecare setting, using non-mydriatic fundus images from Remidio's Fundus-on-Phone (FOP NM-10). AI results were compared with tele-ophthalmologists' diagnoses and with a glaucoma specialist's assessment for those participants referred to tertiary eyecare hospital. DESIGN: Prospective, cross-sectional study PARTICIPANTS: 303 participants from 6 satellite vision centers of a tertiary eye hospital METHODS: At the vision center, participants underwent comprehensive eye evaluations, including clinical history, visual acuity measurement, slit lamp examination, intraocular pressure measurement, and fundus photography using the FOP NM-10 camera. Medios AI-Glaucoma software analysed 42-degrees disc-centric fundus images, categorizing them as normal, glaucoma, or suspect. Tele-ophthalmologists who were glaucoma fellows with a minimum of 3 years of ophthalmology and 1 year of glaucoma fellowship training, masked to AI results, remotely diagnosed subjects based on the history and disc appearance. All participants labelled as disc suspects or glaucoma by AI or tele-ophthalmologists underwent further comprehensive glaucoma evaluation at the base hospital, including clinical examination, Humphrey visual field analysis (HFA), and Optical Coherence Tomography (OCT). AI and tele-ophthalmologist diagnoses were then compared with a glaucoma specialist's diagnosis. MAIN OUTCOME MEASURES: Sensitivity and Specificity of Medios AI RESULTS: Out of 303 participants, 299 with at least one eye of sufficient image quality were included in the study. The remaining 4 participants did not have sufficient image quality in both eyes. Medios AI identified 39 participants (13%) with referable glaucoma. The AI exhibited a sensitivity of 0.91 (95% CI: 0.71 - 0.99) and specificity of 0.93 (95% CI: 0.89 - 0.96) in detecting referable glaucoma (definite perimetric glaucoma) when compared to tele-ophthalmologist. The agreement between AI and the glaucoma specialist was 80.3%, surpassing the 55.3.% agreement between the tele-ophthalmologist and the glaucoma specialist amongst those participants who were referred to the base hospital. Both AI and the tele-ophthalmologist relied on fundus photos for diagnoses, while the glaucoma specialist's assessments at the base hospital were aided by additional tools such as HFA and OCT. Furthermore, AI had fewer false positive referrals (2 out of 10) compared to the tele-ophthalmologist (9 out of 10). CONCLUSION: Medios offline AI exhibited promising sensitivity and specificity in detecting referable glaucoma from remote vision centers in southern India when compared with teleophthalmologists. It also demonstrated better agreement with glaucoma specialist's diagnosis for referable glaucoma participants.

Evaluation of an offline, artificial intelligence system for referable glaucoma screening using a smartphone-based fundus camera: a prospective study.

BACKGROUND/OBJECTIVES: An affordable and scalable screening model is critical for undetected glaucoma. The study evaluated the performance of an offline, smartphone-based AI system for the detection of referable glaucoma against two benchmarks: specialist diagnosis following full glaucoma workup and consensus image grading. SUBJECTS/METHODS: This prospective study (tertiary glaucoma centre, India) included 243 subjects with varying severity of glaucoma and control group without glaucoma. Disc-centred images were captured using a validated smartphone-based fundus camera analysed by the AI system and graded by specialists. Diagnostic ability of the AI in detecting referable Glaucoma (Confirmed glaucoma) and no referable Glaucoma (Suspects and No glaucoma) when compared to a final diagnosis (comprehensive glaucoma workup) and majority grading (image grading) by Glaucoma specialists (pre-defined criteria) were evaluated. RESULTS: The AI system demonstrated a sensitivity and specificity of 93.7% (95% CI: 87.6-96.9%) and 85.6% (95% CI:78.6-90.6%), respectively, in the detection of referable glaucoma when compared against final diagnosis following full glaucoma workup. True negative rate in definite non-glaucoma cases was 94.7% (95% CI: 87.2-97.9%). Amongst the false negatives were 4 early and 3 moderate glaucoma. When the same set of images provided to the AI was also provided to the specialists for image grading, specialists detected 60% (67/111) of true glaucoma cases versus a detection rate of 94% (104/111) by the AI. CONCLUSION: The AI tool showed robust performance when compared against a stringent benchmark. It had modest over-referral of normal subjects despite being challenged with fundus images alone. The next step involves a population-level assessment.

The Urgent Need for Healthcare Workforce Upskilling and Ethical Considerations in the Era of AI-Assisted Medicine.

This letter is in response to the article "Enhancing India's Health Care during COVID Era: Role of Artificial Intelligence and Algorithms". While the integration of AI has the potential to improve patient outcomes and reduce the workload of healthcare professionals, there is a need for significant training and upskilling of healthcare providers. There are ethical and privacy concerns related to the use of AI in healthcare, which must be accompanied by rigorous guidelines. One solution to the overburdened healthcare systems in India is the use of new language generation models like ChatGPT to assist healthcare workers in writing discharge summaries. By using these technologies responsibly, we can improve healthcare outcomes and alleviate the burden on overworked healthcare professionals.

Exploring Radiomics for Classification of Supraglottic Tumors: A Pilot Study in a Tertiary Care Center.

Accurate classification of laryngeal cancer is a critical step for diagnosis and appropriate treatment. Radiomics is a rapidly advancing field in medical image processing that uses various algorithms to extract many quantitative features from radiological images. The high dimensional features extracted tend to cause overfitting and increase the complexity of the classification model. Thereby, feature selection plays an integral part in selecting relevant features for the classification problem. In this study, we explore the predictive capabilities of radiomics on Computed Tomography (CT) images with the incidence of laryngeal cancer to predict the histopathological grade and T stage of the tumour. Working with a pilot dataset of 20 images, an experienced radiologist carefully annotated the supraglottic lesions in the three-dimensional plane. Over 280 radiomic features that quantify the shape, intensity and texture were extracted from each image. Machine learning classifiers were built and tested to predict the stage and grade of the malignant tumour based on the calculated radiomic features. To investigate if radiomic features extracted from CT images can be used for the classification of laryngeal tumours. Out of 280 features extracted from every image in the dataset, it was found that 24 features are potential classifiers of laryngeal tumour stage and 12 radiomic features are good classifiers of histopathological grade of the laryngeal tumor. The novelty of this paper lies in the ability to create these classifiers before the surgical biopsy procedure, giving the clinician valuable, timely information.