scholarly journals Use of Artificial Intelligence to Triage Patients with Flu-Like Symptoms Using Imaging in Non-COVID-19 Hospitals during COVID-19 Pandemic: An Ongoing 8-Month Experience

Author(s):  
Atul Kapoor ◽  
Aprajita Kapoor ◽  
Goldaa Mahajan

Abstract Background Evaluation of suspected coronavirus disease-2019 (COVID-19) patient is a diagnostic dilemma as it commonly presents like influenza in early stages. Studies and guidelines have emerged both for and against the use of imaging as a frontline tool to investigate such patients. Reverse transcriptase-polymerase chain reaction (RT-PCR) is suggested as the backbone of diagnosis. We designed and tested a diagnostic algorithm using artificial intelligence (AI) to determine the role of imaging in the evaluation of patients with acute flu-like presentation. Materials and Methods Overall, 3,235 consecutive patients with flu-like presentation were evaluated over a period of 240 days. All patients underwent plain radiographs of chest with computer-aided detection for COVID-19 (CAD4COVID) AI analysis. Based on the threshold scores, they were divided into two groups: group A (score < 50) and group B (score > 50). Group A patients were discharged and put on routine symptomatic treatment and follow-up with RT-PCR, while group B patients underwent high-resolution computed tomography (HRCT) followed by COVID-19 AI analysis and RT-PCR test. These were then triaged into COVID-19 and non-COVID-19 subgroups based on COVID-19 similarity scores by AI, and lung severity scores were also determined. Results Group A had 2,209 (68.3%) patients with CAD4COVID score of <50 while 1,026 (31.7%) patients comprised group B. Also, 825 (25.5%) patients were COVID-19 positive with COVID-19 similarity threshold of >0.85 on AI. RT-PCR was positive in 415 and false-negative in 115 patients while 12 patients died before the test could be done. The sensitivity and specificity of CAD4COVID AI analysis on plain radiographs for detection of any lung abnormality combined with HRCT AI analysis was 97.9% and 99% using the above algorithm. Conclusion Combined use of chest radiographs and plain HRCT with AI-based analysis is useful and an accurate frontline tool to triage patients with acute flu-like symptoms in non-COVID-19 health care facilities.

Author(s):  
Stefano Sartini ◽  
Laura Massobrio ◽  
Ombretta Cutuli ◽  
Paola Campodonico ◽  
Cristina Bernini ◽  
...  

COVID-19 respiratory failure is a life-threatening condition. Oxygenation targets were evaluated in a non-ICU setting. In this retrospective, observational study, we enrolled all patients admitted to the University Hospital of Genoa, Italy, between 1 February and 31 May 2020 with an RT-PCR positive for SARS-CoV-2. PaO2, PaO2/FiO2 and SatO2% were collected and analyzed at time 0 and in case of admission, patients who required or not C-PAP (groups A and B) were categorized. Each measurement was correlated to adverse outcome. A total of 483 patients were enrolled, and 369 were admitted to hospital. Of these, 153 required C-PAP and 266 had an adverse outcome. Patients with PaO2 <60 and >100 had a higher rate of adverse outcome at time 0, in groups A and B (OR 2.52, 3.45, 2.01, respectively). About the PaO2/FiO2 ratio, the OR for < 300 was 3.10 at time 0, 4.01 in group A and 4.79 in group B. Similar odds were found for < 200 in any groups and < 100 except for group B (OR 11.57). SatO2 < 94% showed OR 1.34, 3.52 and 19.12 at time 0, in groups A and B, respectively. PaO2 < 60 and >100, SatO2 < 94% and PaO2/FiO2 ratio < 300 showed at least two- to three-fold correlation to adverse outcome. This may provide simple but clear targets for clinicians facing COVID-19 respiratory failure in a non ICU-setting.


2020 ◽  
Author(s):  
Xiangyun Yin ◽  
Jixiu Zhao ◽  
Jian Jiang ◽  
Hongmin Xi ◽  
Xianghong Li ◽  
...  

Abstract Background:Premature infant is a significant health care burden. White matter damage (WMD) is a leading cause of acute mortality and chronic morbidity in preterm. Xenon (Xe) intervention was given to the 3-day-old neonatal rats with brain white matter injury. By detecting the changes in the expression level of microRNA210 and hypoxia inducible factor 1α (HIF-1α) in brain tissue before and after xenon intervention, we can research the molecular basis and the mechanism of neuroprotective on effect of xenon on brain white matter damage in neonatal rats.Methods:Three-day-old SD rats were randomly divided into sham group(Group A, n=24), lipopolysaccharide(LPS)+hypoxia-ischemia(HI) group (Group B, n=24) and LPS+HI+Xe group ( n=72). The onset of Xe inhalation started at 0,2 and 5 hours in subgroups C,D,and E respectively.We investigated the neurobehavioral deficits by performing TUNEL and hematoxylin and eosin (HE) staining and examining the expression of miR-210and HIF-1α in brain tissues via RT-PCR and western blot. Results: Xe treatment improved the histological alterations and decreased the number of apoptotic cells in group C pups.Compared to group A,Detection of miR-210 level by RT-PCR. the expression level of miR-210 in neonatal rats' periventricular tissue increased significantly at all time points in group B (p<0.05).While the expression level of miR-210 in brain tissues of group B was significantly lower at 48h and 72h than that of group C(p<0.05).Similarly,Detection of HIF-1α protein by Western blot. The level of HIF-1α protein in group B brain tissues was significantly higher than that of group A at each time point (p<0.05), Xe treatment resulted in a marked increase in HIF-1α in C,D, and E subgroups (P < 0.05, compared to group B).Conclusions: These results demonstrate that the expression of HIF-1α and miR-210 increased in periventricular tissues and Xe could relieve the white matter damage by up-regulating the expression of HIF-1α and its target gene miR-210.The Xe therapeutic time window was within 5 hours after intervention, the sooner the better.


1995 ◽  
Vol 13 (11) ◽  
pp. 2784-2788 ◽  
Author(s):  
G P Warren ◽  
L H Einhorn

PURPOSE To assess the ability of gallium scans to determine whether residual masses consist of viable tumor or necrotic fibrous tissue after chemotherapy for seminoma. PATIENTS AND METHODS Thirty-two patients were enrolled and 27 were assessable. Patients receiving first-line or salvage chemotherapy had gallium scans performed during their first and last scheduled course of chemotherapy and results were compared with restaging computed tomographic (CT) scans and subsequent clinical outcome. RESULTS Of 27 assessable patients, 22 received first-line chemotherapy (group A) and five salvage chemotherapy (group B). Eight patients were not gallium-avid before chemotherapy despite obvious clinical and radiographic evidence of metastatic seminoma. Eighteen of 19 gallium-positive patients had a persistent mass postchemotherapy on abdominal CT. Of 16 patients in group A whose tumors were gallium-avid, all 16 had normalized gallium scans after chemotherapy. However, two of these 16 patients recurred in their original disease site. In group B, there were three patients with gallium-avid tumors and all three had normalized scans postchemotherapy. Two patients who were not gallium-avid (one each in group A and B) also developed recurrent disease. Twenty-four of 27 patients are alive with no evidence of active disease at a median follow-up time of 18 months, including 20 with more than 1 year of follow-up data. CONCLUSION Eight of 27 patients had false-negative gallium scans at the time of diagnosis. All nineteen gallium scans that were initially positive reverted to normal after chemotherapy. Two of 19 patients' follow-up gallium scans were false-negative. We therefore feel that gallium scans have minimal value in the prechemotherapy or postchemotherapy evaluation of metastatic seminoma.


Blood ◽  
2005 ◽  
Vol 106 (11) ◽  
pp. 4366-4366
Author(s):  
Nnenna Osuji ◽  
Ilaria Del Giudice ◽  
Tim Dexter ◽  
Estella Matutes ◽  
Vasantha Brito-Babapulle ◽  
...  

Abstract T-cell prolymphocytic leukemia (T-PLL) is rare and presents with widespread disease. Indolent presentations are seen but eventually progress. The disease shows marked chemoresistance and is best treated with the monoclonal anti-CD52 antibody (CAMPATH). Prolymphocytes show a post-thymic phenotype and are CD4+CD8− (65%), CD4−CD8+ (10%) or CD4+CD8+ (25%). This double positive phenotype, raises questions about the putative ontology of T-PLL. Morphological heterogeneity, with typical (75%), small cell (20%) and cerebriform/sezary-like variants (5%) is described. Inversions or reciprocal translocations of chromosome 14 involving breakpoints at q11 (TCR a/d) and q32.1 (TCL1 and TCL1b) are seen (~ 80%). Other common abnormalities involve chromosome 8, translocation (X;14)(q28;q11) and, ATM (11q23). We investigated the clinico-pathological heterogeneity in T-PLL, at the level of the transcriptome and evaluated the ability of gene expression profiling to sub-classify T-PLL. Total RNA was extracted from blood prolymphocytes (>92% purity) of 22 patients. cDNA synthesis followed by biotin-labelled cRNA synthesis was carried out as per Affymetrix protocols. Fragmented cRNA was hybridized to the Human U133 PLUS2 GeneChip array (54K probes). Microarray services were provided by MRC geneservice (UK HGMP Resource Centre). Hierarchical clustering of samples was performed using a filtered gene set (12,456) and >4 different algorithims. Prediction analysis for micoarray (PAM) and significance analysis of microarray (SAM) were used to evaluate class performance, and partition genes using pre-defined labels of immunophenotype, karyotype, response and morphology. Validation was performed by RT-PCR in a subset of genes.Unsupervised analysis robustly and reproducibly partitioned samples into 2 groups; A (n=8) and B (n=14). SAM analysis identified 4487 differentially expressed transcripts (false discovery rates <1%), >40% of which showed >2-fold difference in expression between the groups. There was no statistical difference in age, immunophenotype or karyotype betweeen groups, however, differential response to CAMPATH was seen. PAM analysis refined a sub-group of ~123 genes which most efficiently differentiated these groups. Group A showed significantly higher rates of non-response and progressive disease as compared to group B (n=14, p=0.036). Key differences related to apoptosis and cell-cycle associated gene expression. Down regulation of caspases (CASP1, CASP2,CASP4, CARD8 and CASP8AP2), cyclins (CCNC, CCND2, CCND3, CCNG1, CCNI, CCNT2), bcl-2, HDAC1, HIPK2, IL6R and ATM were frequent in group A with upregulation of genes implicated in NF-kB (TRAF4, SQSTM1) and TNF pathways (LMNA, ARTS-1), as well as transcription factors such as ATF-3. CD52 expression was ~2-fold higher in group B and may explain in part, differential responses to CAMPATH. RT-PCR validated gene expression data for LMNA and ATF-3. Despite the small numbers, algorithim-independent segregation into 2 consistent groups, in conjunction with the magnitude of gene differences, presence of many mutually exclusive divisions, and low prediciton errors, imply that the 2 identified profiles arise from fundamental differences at a regulatory level and thus likely represent a generalisable classification for T-PLL. Differential responses to CAMPATH may be a sub-feature of this grouping.


Author(s):  
Abu Taiub Mohammed Mohiuddin Chowdhury ◽  
Mohammad Shahbaz ◽  
Md Rezaul Karim ◽  
Johirul Islam ◽  
Dan Guo ◽  
...  

Abstract Background The worldwide COVID-19 pandemic was caused by a newly discovered Coronavirus. The treatment methods for COVID-19 are emerging and rapidly evolving. Existing drugs, including Ivermectin and Hydroxychloroquine, offer the hope of effective treatment in early disease. In this study, we investigated and compared outcomes of Ivermectin-Doxycycline vs. Hydroxychloroquine-Azithromycin combination therapy COVID19 patients with mild to moderate disease.Methods Patients with mild to moderate COVID-19 disease, tested positive by RT PCR for SARS-CoV-2 infection at Chakoria Upazilla Health Complex, Cox's Bazar, Bangladesh, were included in this study. Patients were divided randomly into two groups: Ivermectin 200µgm/kg single dose + Doxycycline 100 mg BID for 10days in group A, and Hydroxychloroquine 400 mg 1st day, then200mg BID for 9days + Azithromycin 500 mg daily for 5 days in group B. PCR for SARS-CoV-2 was repeated in all symptomatic patients on the second day onward without symptoms, or, for those who were asymptomatic (throughout the process), on the 5th day after taking medication and repeated every two days onward if the result is positive. Time to negative PCR and time to full symptomatic recovery was measured for each group.Results All subjects in the Ivermectin-Doxycycline group (group A) reached a negative PCR for SARS-CoV-2, at a mean of 8.93days, and all reached symptomatic recovery, at a mean of 5.93days, with 55.10% symptom-free by the 5th day. In the Hydroxychloroquine-Azithromcyin group (group B), 96.36% reached a negative PCR at a mean of 6.99days and were symptoms-free at 9.33days. Group A patients had symptoms that could have been caused by the medication in 31.67% of patients, including lethargy in 14(23.3%), nausea in 11(18.3%), and occasional vertigo in 7(11.66%) of patients. In Group B, 46.43% had symptoms that could have been caused by the medication, including 13(23.21%) mild blurring of vision and headache; 22(39.2%) increased lethargy and dizziness, 10(17.85%) occasional palpitation, and 9(16.07%) nausea and vomiting.Conclusion The Ivermectin-Doxycycline combination showed a trend toward superiority to the Hydroxychloroquine-Azithromycin combination therapy in the case of patients with mild to moderate COVID19 disease, though the difference in time to becoming symptom-free and the difference in time to negative PCR was not statistically significant.


2021 ◽  
Vol 108 (Supplement_7) ◽  
Author(s):  
Khaled Noureldin ◽  
Afsheen Mahmoud ◽  
Ben Panamarenko ◽  
Ahmed Shalaby

Abstract Objectives Assess MDCT accuracy in staging cancers periampullary cancers. Introduction Periampullary malignancies are highly aggressive with poor outcomes. Surgery is the only curative option. It is crucial to define the patients who can advantage from a Whipple’s resection and who can avoid. Methodology and Results RCT investigated randomly 28 patients over 15 months. The patients were sub-divided into 2 groups. Group A, we relied mainly on the MDCT for preoperative staging, while in Group B staging laparoscopy was added before the abdominal exploration. Sensitivity of the MDCT and its accuracy were 100% in defining the signs of irresectability. For borderline staging, the accuracy of the scan was 62.5% and 71%, in groups A and B. The Overall accuracy of MDCT was 75%. It decreased to 68.1% for borderline lesions. The addition of staging laparoscopy to the diagnostic work up, increased the accuracy to 92.5%. The camera test was able to see occult findings which were missed in the images. liver Mets and malignant peritoneal fluid were localized in 18% and 9% respectively. 3 cases in group A and one in group B underwent unnecessary laparotomy. Thus, the false negative incidences were 21% and 7% in group A and B, with overall incidence 14.2%. Conclusion MDCT is highly sensitive and specific with high stage periampullary cancers. These parameters drop in border tumors with reduced accuracy in detecting the degree of vascular abutment and distant-occult findings. Addition of other adjuncts to decrease the rate of un-indicated laparotomy is advised.


1987 ◽  
Author(s):  
A Eldor ◽  
M Rose

A dramatic change in the prognosis of TTP has taken place since the introduction of plasma therapy in 1977. However, plasma therapy does not always result in a complete cure since TTP manifestation may reappear. We describe 38 patients who were treated for TTP in 15 hospitals in Israel and New York City since 1977. 37 patients received plasma (transfusions and exchanges) and 30 survived. 12 patients (37%) developed relapsing TTP. Infections, pregnancy and surgery frequently preceded the initial episodes and the relapses. To evaluate the clinical course of relapsing TTP, a scoring system was developed based on 4 parameters: neurological findings, renal function impairment, platelet count and hemoglobin value at presentation. Each parameter was marked on a scale of 0 to 2: 0= no abnormality, 1= moderate impairment, 2= severe impairment. The severity of each episode was the sum of the 4 scores. The cases were divided into 3 groups: Group A= patients who died during 1st episode; Group B= patients who had only one episode; Group C= patients who relapsed. The following are the average severity scores:The differences between Groups A and B; A and C; B and C; and B and the relapses are significant (p<0.005)(Chi-square test). The differences between Group C first episode* and subsequent relapses are not significant (paired t-test). Hence, relapsing TTP was manifested by a milder clinical course, however two relapses were fatal, demonstrating that this is not a benign disorder. Therapy consisted of plasma, plasmapheresis, steroids, platelet-inhibitor drugs and 11 patients underwent splenectomy. Addition of vincristin seemd to shorten the duration of the TTP episode. No differences were observed in the treatment of Group A, B and C patients. However, during relapses, patients received less therapy probably due to their milder clinical course. Splenectomy did not prevent relapses, but prolonged the remission duration. Based on our data, we recommend that the severity score be used in determining the intensity of treatment.


2021 ◽  
Vol 2021 ◽  
pp. 1-6
Author(s):  
Shan Lu ◽  
Zhiheng Xing ◽  
Shiyu Zhao ◽  
Xianglu Meng ◽  
Juhong Yang ◽  
...  

COVID-19 is a kind of pneumonia with new coronavirus infection, and the risk of death in COVID-19 patients with diabetes is four times higher than that in healthy people. It is unclear whether there is a difference in chest CT images between type 2 diabetes mellitus (T2DM) and non-diabetes mellitus (NDM) COVID-19 patients. The aim of this study was to investigate the differences in chest CT images between T2DM and NDM patients with COVID-19 based on a quantitative method of artificial intelligence. A total of 62 patients with COVID-19 pneumonia were retrospectively enrolled and divided into group A (T2DM COVID-19 pneumonia group, n = 15) and group B (NDM COVID-19 pneumonia group, n = 47). The clinical and laboratory examination information of the two groups was collected. Quantitative features (volume of consolidation shadows and ground glass shadows, proportion of consolidation shadow (or ground glass shadow) to lobe volume, total volume, total proportion, and number) of chest spiral CT images were extracted using Dr. Wise @Pneumonia software. The results showed that among the 26 CT image features, the total volume and proportion of bilateral pulmonary consolidation shadow in group A were larger than those in group B ( P = 0.031 and 0.019, respectively); there was no significant difference in the total volume and proportion of bilateral pulmonary ground glass density shadow between the two groups ( P > 0.05 ). In group A, the blood glucose level was correlated with the volume of consolidation shadow and the proportion of consolidation shadow to right middle lobe volume, and higher than those patients in group B. In conclusion, the inflammatory exudation in the lung of COVID-19 patients with diabetes is more serious than that of patients without diabetes based on the quantitative method of artificial intelligence. Moreover, the blood glucose level is positively correlated with pulmonary inflammatory exudation in COVID-19 patients.


Author(s):  
Xueyan Mei ◽  
Hao-Chih Lee ◽  
Kai-yue Diao ◽  
Mingqian Huang ◽  
Bin Lin ◽  
...  

AbstractFor diagnosis of COVID-19, a SARS-CoV-2 virus-specific reverse transcriptase polymerase chain reaction (RT-PCR) test is routinely used. However, this test can take up to two days to complete, serial testing may be required to rule out the possibility of false negative results, and there is currently a shortage of RT-PCR test kits, underscoring the urgent need for alternative methods for rapid and accurate diagnosis of COVID-19 patients. Chest computed tomography (CT) is a valuable component in the evaluation of patients with suspected SARS-CoV-2 infection. Nevertheless, CT alone may have limited negative predictive value for ruling out SARS-CoV-2 infection, as some patients may have normal radiologic findings at early stages of the disease. In this study, we used artificial intelligence (AI) algorithms to integrate chest CT findings with clinical symptoms, exposure history, and laboratory testing to rapidly diagnose COVID-19 positive patients. Among a total of 905 patients tested by real-time RT-PCR assay and next-generation sequencing RT-PCR, 419 (46.3%) tested positive for SARSCoV-2. In a test set of 279 patients, the AI system achieved an AUC of 0.92 and had equal sensitivity as compared to a senior thoracic radiologist. The AI system also improved the detection of RT-PCR positive COVID-19 patients who presented with normal CT scans, correctly identifying 17 of 25 (68%) patients, whereas radiologists classified all of these patients as COVID-19 negative. When CT scans and associated clinical history are available, the proposed AI system can help to rapidly diagnose COVID-19 patients.


2021 ◽  
Vol 19 (2) ◽  
pp. 169-185
Author(s):  
Ewa Wilczek-Rużyczka ◽  
Aleksandra Gawrońska ◽  
Jolanta Góral-Półrola

The aim of the study was to answer the question as to whether transcranial direct current stimulation (tDCS) is more effective in reducing burnout syndrome in nurses than the commonly used individual psychotherapy. The study included 40 nurses from various health care facilities located in the Lesser Poland and Podkarpackie Voivodeship suffering from burnout syndrome. They were assigned to the experimental group while 20 to the control group. Two different therapy models were used: the experimental group (A) included 20 of the nurses treated with the use of transcranial direct current stimulation (tDCS), four times a week for 8 weeks, in sessions that lasted initially 10, then 15, 20, 25 and finally 30 minutes and the control group (B) included 20 of the nurses treated with individual psychotherapy employed for 8 weeks, once a week for 30 minutes. To evaluate the results we used: screening with a clinical interview, the Mini–Mental State Examination (MMSE), the Beck Depression Inventory and a Polish adaptation of the Italian questionnaire created by Massimo Sentinello (LBQ). Treatment was provided. The transcranial direct current stimulation (tDCS) used in Group A is more effective in reducing many symptoms than is the case with individual psychotherapy. Comparing the intragroup effects, it was found that the tDCS employed in Group A significantly reduced the intensity of depressive symptoms among the surveyed nurses [F (1.38) = 57.62; p <0.001; η2 = 0.603] while the individual psychotherapy used in Group B failed to produce a statistically significant effect [F (1.38) = 1.794; p = 0.188; η2 = 0.045]. These include a reduction of depression, a reduction in chronic psychophysical exhaustion, vegetative problem reduction, and the improvement of nurse-patient relations. Neurotherapy with the use of transcranial direct current stimulation (tDCS) is more effective in reducing burnout syndrome than the commonly used individual psychotherapy. It also helps to return these nurses to full professional activity. The studies presented above recommend the use of new neurotechnologies in therapy as a result of their usefulness and non-invasive character.


Sign in / Sign up

Export Citation Format

Share Document