| 1 | Clinicopathological spectrum of snake bite-induced acute kidney injury from India显示文摘AIM To study the clinico-pathological spectrum of snake bite-induced acute kidney injury(AKI).METHODS A retrospective study of patients admitted at Indira Gandhi Medical College Hospital,Shimla with snake bite-induced AKI from July 2003 to June 2016.Medical records were evaluated for patient's information on demographic,clinical characteristics,complications and outcome.Outcomes of duration of hospital stay,requirement for intensive care unit support,treatment with dialysis,survival and mortality were analyzed.The survival and non survival groups were compared to see the difference in the demographic factors,clinical characteristics,laboratory results,and complications.In patients subjected to kidney biopsy,the findings of histopathological examination of the kidney biopsies were also analyzed.RESULTS One hundred and twenty-one patients were diagnosed with snake bite-induced AKI.Mean age was 42.2 ± 15.1 years and majority(58%) were women.Clinical details were available in 88 patients.The mean duration of arrival at hospital was 3.4 ± 3.7 d with a range of 1 to30 d.Eighty percent had oliguria and 55% had history of having passed red or brown colored urine.Coagulation defect was seen in 89% patients.The hematological and biochemical laboratory abnormalities were:Anemia(80.7%),leukocytosis(75%),thrombocytopenia(47.7%),hyperkalemia(25%),severe metabolic acidosis(39.8%),hepatic dysfunction(40.9%),hemolysis(85.2%) and rhabdomyolysis(68.2%).Main complications were:Gastrointestinal bleed(12.5%),seizure/encephalopathy(10.2%),hypertension,pneumonia/acute respiratory distress syndrome(ARDS) and disseminated intravascular coagulation(9.1% each),hypotension and multi organ failure(MOF)(4.5% each).Eighty-two percent patients required renal replacement therapy.One hundred and ten(90.9%) patient survived and 11(9.1%) patients died.As compared to the survival group,the white blood cell count(P = 0.023) and bilirubin levels(P = 0.006) were significant higher and albumin levels were significantly lower(0.005) in patients who died.The proportion of patients with pneumonia/ARDS(P = 0.001),seizure/encephalopathy(P = 0.005),MOF(P = 0.05) and need for intensive care unit support(0.001) was significantly higher and duration of hospital stay was significantly shorter(P = 0.012) in patients who died.Kidney biopsy was done in total of 22 patients.Predominant lesion on kidney biopsy was acute tubular necrosis(ATN) in 20(91%) cases.In 11 cases had severe ATN and in other nine(41%) cases kidney biopsy showed features of ATN associated with mild to moderate acute interstitial nephritis(AIN).One patient only had moderate AIN and one had patchy renal cortical necrosis(RCN).CONCLUSION AKI due to snake bite is severe and a high proportion requires renal replacement therapy.On renal histology ATN and AIN are common,RCN is rare. | Sanjay Vikrant Ajay Jaryal Anupam Parashar | 2017 | World Journal of Nephrology2017，6，3： | 2 |
| 2 | Autism Spectrum Disorder Prediction by an Explainable Deep Learning Approach显示文摘Autism Spectrum Disorder (ASD) is a developmental disorderwhose symptoms become noticeable in early years of the age though it canbe present in any age group. ASD is a mental disorder which affects the communicational, social and non-verbal behaviors. It cannot be cured completelybut can be reduced if detected early. An early diagnosis is hampered by thevariation and severity of ASD symptoms as well as having symptoms commonly seen in other mental disorders as well. Nowadays, with the emergenceof deep learning approaches in various fields, medical experts can be assistedin early diagnosis of ASD. It is very difficult for a practitioner to identifyand concentrate on the major feature’s leading to the accurate prediction ofthe ASD and this arises the need for having an automated approach. Also,presence of different symptoms of ASD traits amongst toddlers directs tothe creation of a large feature dataset. In this study, we propose a hybridapproach comprising of both, deep learning and Explainable Artificial Intelligence (XAI) to find the most contributing features for the early and preciseprediction of ASD. The proposed framework gives more accurate predictionalong with the recommendations of predicted results which will be a vital aidclinically for better and early prediction of ASD traits amongst toddlers. | Anupam Garg Anshu Parashar Dipto Barman Sahil Jain Divya Singhal Mehedi Masud Mohamed Abouhawwash | 2022 | Computers, Materials & Continua2022，，4： | 1 |
您所在的机构暂未开通此部分的功能，请联系管理员