RESUMEN

Background The use of computational technology in medicine has allowed for an increase in the accuracy of clinical diagnosis, reducing errors through additional layers of oversight. Artificial intelligence technologies present the potential to further augment and expedite the accuracy, quality, and efficiency at which diagnosis can be made when used as an adjunctive tool. Such techniques, if found to be accurate and reliable in their diagnostic acuity, can be implemented to foster better clinical decision-making, improving patient quality of care while reducing healthcare costs. Methodology This study implemented convolution neural networks to develop a deep learning model capable of differentiating normal chest X-rays from those indicating pneumonia, tuberculosis, cardiomegaly, and COVID-19. There were 3,063 normal chest X-rays, 3,098 pneumonia chest X-rays, 2,920 COVID-19 chest X-rays, 2,214 chest X-rays, and 554 tuberculosis chest X-rays from Kaggle that were used for training and validation. The model was trained to recognize patterns within the chest X-rays to efficiently recognize these diseases within patients to be treated on time. Results The results indicated a success rate of 98.34% incorrect detections, exemplifying a high degree of accuracy. There are limitations to this study. Training models require hundreds to thousands of samples, and due to potential variability in image scanning equipment and techniques from which the images are sourced, the model could have learned to interpret external noise and unintended details which can adversely impact accuracy. Conclusions Further studies that implement more universal database-sourced images with similar image scanning techniques, assess diverse but related medical conditions, and the utilization of repeat trials can help assess the reliability of the model. These results highlight the potential of machine learning algorithms for disease detection with chest X-rays.

RESUMEN

OBJECTIVES & METHODS: CINtec PLUS and cobas HPV tests were compared for triaging patients referred to colposcopy with a history of LSIL cytology in a 2-year prospective study. Cervical specimens were tested once at enrollment, and test positivity rates determined. Test performance was ascertained with cervical intraepithelial neoplasia grade 2 or worse (CIN2+) and CIN3 or worse (CIN3+) serving as clinical endpoints. RESULTS: In all ages, (19-76 years, n= 598), 44.3% tested CINtec PLUS positive vs. 55.4% HPV positive (p< 0.001). To detect CIN2+ (n= 99), CINtec PLUS was 81.8% sensitive vs. 93.9% for HPV testing (p= 0.009); genotype 16/18-specific sensitivity was 46.5%. Specificity was 52.9% vs. 36.6%, respectively (p< 0.001). In all ages, to detect CIN3+ (n= 44), sensitivity was 93.2% for both tests; genotype 16/18-specific sensitivity was 52.3%. Specificity was 48.4% for CINtec PLUS vs. 31.1% for HPV testing (p< 0.001). In patients < 30 years, CINtec was 91.7% sensitive vs 95.8% for HPV testing (p= 0.549). CONCLUSIONS: CINtec PLUS or cobas HPV test could serve as a predictor of CIN3+ with high sensitivity in patients referred to colposcopy with a history of LSIL regardless of age while significantly reducing the number of LSIL referral patients requiring further investigations and follow-up in colposcopy clinics.

Asunto(s)

Infecciones por Papillomavirus , Displasia del Cuello del Útero , Neoplasias del Cuello Uterino , Adulto , Anciano , Canadá , Colposcopía , Inhibidor p16 de la Quinasa Dependiente de Ciclina , Detección Precoz del Cáncer , Femenino , Humanos , Antígeno Ki-67 , Persona de Mediana Edad , Papillomaviridae/genética , Embarazo , Estudios Prospectivos , Derivación y Consulta , Sensibilidad y Especificidad , Neoplasias del Cuello Uterino/diagnóstico , Adulto Joven , Displasia del Cuello del Útero/genética

RESUMEN

BACKGROUND: Gastric schwannomas are uncommon among a broad range of possible diagnoses in the work up of a gastric mass. Regional lymphadenopathy associated with gastric schwannoma is an even less common occurrence and one would otherwise suspect a malignant neoplasm. CASE PRESENTATION: We present two non-consecutive cases from a signle academic center depicting Caucasian females in their 5th and 6th decades of life with gastric schwannoma and adjacent lymphadenopathy. Multiple lymph node excisions were performed without evidence of neoplasia. DISCUSSION: Lymphadanopathy in the presence of a gastric mass typically represents malignant neoplasm. A less than likely presentation of gastric schwannoma with reactive regional lymph nodes poses a challenge to adequate preoperative diagnosis and increases risk for a more aggressive than necessary surgical approach with lymphadenectomy. CONCLUSION: While the correlation between gastric schwannoma and lymphadenopathy is uncertain, this ought to be considered. If diagnosis can be confirmed preoperatively, omission of lymphadenectomy is appropriate.