A cross-sectional comparative study: ChatGPT 3.5 versus diverse levels of medical experts in the diagnosis of ENT diseases

PURPOSE

With recent advances in artificial intelligence (AI), it has become crucial to thoroughly evaluate its applicability in healthcare. This study aimed to assess the accuracy of ChatGPT in diagnosing ear, nose, and throat (ENT) pathology, and comparing its performance to that of medical experts.

METHODS

We conducted a cross-sectional comparative study where 32 ENT cases were presented to ChatGPT 3.5, ENT physicians, ENT residents, family medicine (FM) specialists, second-year medical students (Med2), and third-year medical students (Med3). Each participant provided three differential diagnoses. The study analyzed diagnostic accuracy rates and inter-rater agreement within and between participant groups and ChatGPT.

RESULTS

The accuracy rate of ChatGPT was 70.8%, being not significantly different from ENT physicians or ENT residents. However, a significant difference in correctness rate existed between ChatGPT and FM specialists (49.8%, p < 0.001), and between ChatGPT and medical students (Med2 47.5%, p < 0.001; Med3 47%, p < 0.001). Inter-rater agreement for the differential diagnosis between ChatGPT and each participant group was either poor or fair. In 68.75% of cases, ChatGPT failed to mention the most critical diagnosis.

CONCLUSIONS

ChatGPT demonstrated accuracy comparable to that of ENT physicians and ENT residents in diagnosing ENT pathology, outperforming FM specialists, Med2 and Med3. However, it showed limitations in identifying the most critical diagnosis.

CT Scan in Children Suspected of Foreign Body Aspiration: A Systematic Review and Meta-analysis

OBJECTIVE

The goal of this study is to evaluate the sensitivity and specificity of computed tomography (CT) scans in the diagnosis of foreign body aspiration (FBA) in children, and to determine whether chest CT scans would reduce the need for diagnostic rigid bronchoscopies.

DATA SOURCES

MEDLINE, EMBASE, Scopus, and the Cochrane Central Register of Controlled Trials (CENTRAL) databases were searched for relevant articles and conference proceedings that were published in English through November 1, 2022.

REVIEW METHODS

We included prospective and retrospective studies comparing chest CT scans and rigid bronchoscopy for the diagnosis of FBA in pediatric patients (<16 years old). The pooled estimates of the sensitivity and specificity of the chest CT scan in the diagnosis of FBA were calculated using a fixed- or common-effects analysis and a random-effects analysis that accounts for heterogeneity if present. Forest plots were constructed to combine the evidence identified during the systematic review.

RESULTS

Eighteen articles (4178 patients) were included. The average age of the children was 2.26 (±0.75) years, and 65% (±5.64%) of them were boys. Cough was the most prevalent symptom upon presentation. The pooled analysis showed that the sensitivity of chest CT scan in detecting a foreign body in children was 99% (95% confidence interval, CI [97, 100]; I2  = 72%, τ2  = 0.0065, p < .01). The false negative rate was 1.8% (95% CI [0.3, 2.7]; I2  = 72%, p < .01). The specificity of chest CT scan was 92% (95% CI [83, 98]; I2  = 83%, τ2  = 0.0437, p < .01).

CONCLUSIONS

Chest CT scan is a sensitive and specific test for the diagnosis of FBA in the pediatric population. Its use can help to reduce unnecessary rigid bronchoscopies, especially in patients with a low clinical suspicion of aspiration. It should not be a replacement for the gold standard bronchoscopy, particularly in cases where there is a clear history and symptoms suggestive of aspiration.

Ipratropium Bromide Nasal Spray in Non-Allergic Rhinitis: A Systematic Review and Meta-Analysis

OBJECTIVE

This study aims to compare the effectiveness of intranasal ipratropium bromide (INIB) to a placebo in reducing nasal symptoms, particularly rhinorrhea, and enhancing quality of life in non-allergic rhinitis (NAR) patients.

STUDY DESIGN

Systematic review and meta-analysis.

METHODS

A comprehensive review of the literature was conducted on Medline, Embase, and Cochrane libraries. Randomized controlled trials (RCTs) and non-randomized comparative parallel group trials comparing IB nasal spray to placebo were included.

RESULTS

Five RCTs assessed a total of 472 participants with a diagnosis of NAR. IB nasal spray 0.03% were used across all studies. IB has a better impact on decreasing rhinorrhea than the placebo, with a standardized mean difference (SMD) of 0.93 (95% CI 0.06-1.8). The mean change in rhinorrhea severity was 85% (95% CI 77-92%) and I^2 26% (p = 0.24). IB outperformed the placebo in terms of shortening the symptom's duration/day, as shown by an SMD of 0.35 (95% CI 0.15-0.55). The difference between treatments was noticeable within the first week and remained consistent throughout the treatment. Patients who were administered IB experienced a substantially greater improvement in physical and mental outcomes. Nasal adverse events with IB were generally intermittent and brief.

CONCLUSION

Compared with a placebo, IB nasal spray is both safe and effective in treating the rhinorrhea associated with NAR. IB significantly reduces the severity and duration of rhinorrhea. The treatment was determined to be beneficial by both patients and physicians and resulted in a better quality of life.

LEVEL OF EVIDENCE

1 Laryngoscope, 133:3247-3255, 2023.

Enhancing cancer treatment and understanding through clustering of gene responses to categorical stressors

Cancer cells have a unique metabolic activity in the glycolysis pathway compared to normal cells, which allows them to maintain their growth and proliferation. Therefore, inhibition of glycolytic pathways may be a promising therapeutic approach for cancer treatment. In this novel study, we analyzed the genetic responses of cancer cells to stressors, particularly to drugs that target the glycolysis pathway. Gene expression data for experiments on different cancer cell types were extracted from the Gene Expression Omnibus and the expression fold change was then clustered after dimensionality reduction. We identified four groups of responses: the first and third were most affected by anti-glycolytic drugs, especially those acting on multiple pathways at once, and consisted mainly of squamous and mesenchymal tissues, showing higher mitotic inhibition and apoptosis. The second and fourth groups were relatively unaffected by treatment, comprising mainly gynecologic and hormone-sensitive groups, succumbing least to glycolysis inhibitors. Hexokinase-targeted drugs mainly showed this blunted effect on cancer cells. This study highlights the importance of analyzing the molecular states of cancer cells to identify potential targets for personalized cancer therapies and to improve our understanding of the disease.

Polygenic and Network-Based Studies in Risk Identification and Demystification of cancer

INTRODUCTION

Diseases were initially thought to be the consequence of a single gene mutation. Advances in DNA sequencing tools and our understanding of gene behavior have revealed that complex diseases, such as cancer, are the product of genes cooperating with each other and with their environment in orchestrated communication networks. Seeing that the function of individual genes is still used to analyze cancer, the shift to using functionally interacting groups of genes as a new unit of study holds promise for demystifying cancer.

AREAS COVERED

The literature search focused on three types of cancer, namely breast, lung, and prostate, but arguments from other cancers were also included. The aim was to prove that multigene analyses can accurately predict and prognosticate cancer risk, subtype cancer for more personalized and effective treatments, and discover anti-cancer therapies. Computational intelligence is being harnessed to analyze this type of data and is proving indispensable to scientific progress.

EXPERT OPINION

In the future, comprehensive profiling of all kinds of patient data (e.g., serum molecules, environmental exposures) can be used to build universal networks that should help us elucidate the molecular mechanisms underlying diseases and provide appropriate preventive measures, ensuring lifelong health and longevity.

Microarray analysis of breast cancer gene expression profiling in response to 2-deoxyglucose, metformin, and glucose starvation

Background

Breast cancer (BC) is the most frequently diagnosed cancer in women. Altering glucose metabolism and its effects on cancer progression and treatment resistance is an emerging interest in BC research. For instance, combining chemotherapy with glucose-lowering drugs (2-deoxyglucose (2-DG), metformin (MET)) or glucose starvation (GS) has shown better outcomes than with chemotherapy alone. However, the genes and molecular mechanisms that govern the action of these glucose deprivation conditions have not been fully elucidated. Here, we investigated the differentially expressed genes in MCF-7 and MDA-MB-231 BC cell lines upon treatment with glucose-lowering drugs (2-DG, MET) and GS using microarray analysis to study the difference in biological functions between the glucose challenges and their effect on the vulnerability of BC cells.

Methods

MDA-MB-231 and MCF-7 cells were treated with 20 mM MET or 4 mM 2-DG for 48 h. GS was performed by gradually decreasing the glucose concentration in the culture medium to 0 g/L, in which the cells remained with fetal bovine serum for one week. Expression profiling was carried out using Affymetrix Human Clariom S microarrays. Differentially expressed genes were obtained from the Transcriptome Analysis Console and enriched using DAVID and R packages.

Results

Our results showed that MDA-MB-231 cells were more responsive to glucose deprivation than MCF-7 cells. Endoplasmic reticulum stress response and cell cycle inhibition were detected after all three glucose deprivations in MDA-MB-231 cells and only under the metformin and GS conditions in MCF-7 cells. Induction of apoptosis and inhibition of DNA replication were observed with all three treatments in MDA-MB-231 cells and metformin-treated MCF-7 cells. Upregulation of cellular response to reactive oxygen species and inhibition of DNA repair mechanisms resulted after metformin and GS administration in MDA-MB-231 cell lines and metformin-treated MCF-7 cells. Autophagy was induced after 2-DG treatment in MDA-MB-231 cells and after metformin in MCF-7 cells. Finally, inhibition of DNA methylation were observed only with GS in MDA-MB-231 cells.

Conclusion

The procedure used to process cancer cells and analyze their expression data distinguishes our study from others. GS had the greatest effect on breast cancer cells compared to 2-DG and MET. Combining MET and GS could restrain both cell lines, making them more vulnerable to conventional chemotherapy.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12935-022-02542-w.