Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 6 de 6
Filter
Add filters








Language
Year range
1.
Healthcare Informatics Research ; : 284-294, 2020.
Article in English | WPRIM | ID: wpr-834232

ABSTRACT

Objectives@#Machine learning has been widely used to predict diseases, and it is used to derive impressive knowledge in the healthcare domain. Our objective was to predict in-hospital mortality from hospital-acquired infections in trauma patients on an unbalanced dataset. @*Methods@#Our study was a cross-sectional analysis on trauma patients with hospital-acquired infections who were admitted to Shiraz Trauma Hospital from March 20, 2017, to March 21, 2018. The study data was obtained from the surveillance hospital infection database. The data included sex, age, mechanism of injury, body region injured, severity score, type of intervention, infection day after admission, and microorganism causes of infections. We developed our mortality prediction model by random under-sampling, random over-sampling, clustering (k-mean)-C5.0, SMOTE-C5.0, ADASYN-C5.5, SMOTE-SVM, ADASYN-SVM, SMOTE-ANN, and ADASYN-ANN among hospital-acquired infections in trauma patients. All mortality predictions were conducted by IBM SPSS Modeler 18. @*Results@#We studied 549 individuals with hospital-acquired infections in a trauma hospital in Shiraz during 2017 and 2018. Prediction accuracy before balancing of the dataset was 86.16%. In contrast, the prediction accuracy for the balanced dataset achieved by random under-sampling, random over-sampling, clustering (k-mean)-C5.0, SMOTE-C5.0, ADASYN-C5.5, and SMOTE-SVM was 70.69%, 94.74%, 93.02%, 93.66%, 90.93%, and 100%, respectively. @*Conclusions@#Our findings demonstrate that cleaning an unbalanced dataset increases the accuracy of the classification model. Also, predicting mortality by a clustered under-sampling approach was more precise in comparison to random under-sampling and random over-sampling methods.

2.
PAFMJ-Pakistan Armed Forces Medical Journal. 2018; 68 (2): 221-224
in English | IMEMR | ID: emr-198886

ABSTRACT

Objective: The objective of this study was to compare the mean per operative and post operative blood loss using harmonic scalpel and monopolar electrocautry in modified radical mastectomy. Study Design: Randomized controlled trial. Place and Duration of Study: Department of surgery PNS Shifa Karachi, from 25[th] Oct 2011 to 24[th] Apr 2012


Material and Methods: A total of 64 patients, undergoing Modified Radical Mastectomy [MRM] were randomly divided into two groups of 32 patients each, using random numbers table. Dissection in group A was done using Harmonic Scalpel [HS]. Group B underwent Monopolar Electrocautry [ME] for dissection and hemostasis. Mean per and post operative blood loss was calculated in milliliters


Results: Mean per operative and post operative blood loss using harmonic scalpel [group-A] was 121.19 +/- 5.63 ml while 603.35 +/- 8.04 ml loss was recorded in monopolar electrocautry group [group B]. A p-value was calculated as <0.001 which shows a significant difference between both the groups


Conclusion: The mean per and post operative blood loss using harmonic scalpel is significantly less than using monopolar electrocautry in modified radical mastectomy

3.
Saudi Journal of Gastroenterology [The]. 2010; 16 (4): 260-263
in English | IMEMR | ID: emr-139389

ABSTRACT

It has been shown previously that in primary care settings in UK abnormal liver enzymes are not adequately investigated and followed up; hence potentially treatable chronic liver diseases remain undiagnosed. No such published data is available with regard to secondary care settings. The aims of this audit were, to determine if the current practice in our hospital with regards to investigation, management and follow-up of patients with elevated liver enzymes is in accordance with American Gastroenterology Association [AGA] guidelines and to analyze the effect of age and elevated parameters of liver blood tests on mortality in patients with bacterial sepsis. A total of 4816 patients were admitted to our acute medical receiving unit during a period of 6 months, of which 378 were with elevated liver enzymes. The common conditions that resulted in elevated liver enzymes were sepsis [123] and alcohol-related liver diseases [120]. All patients with elevated parameters of liver function tests [LFTs] were fully investigated, managed and followed up in accordance with AGA guidelines. In addition, in patients with bacterial sepsis, old age was associated with increased mortality, while development of jaundice in elderly patients with bacterial sepsis was associated with increased survival

4.
Malaysian Journal of Medical Sciences ; : 49-53, 2009.
Article in English | WPRIM | ID: wpr-627769

ABSTRACT

Sacroilliac joint diasthesis from high energy trauma is always complicated with chronic pain and long term morbidity. Open anterior stabilisation with plate allow direct reduction and stabilisation with biomechanically advantages. Here we report on four cases of pelvic injury with sacroiliac joint disruption treated with anterior plate stabilisation through a surgical approach similar to that used for anterior ring fractures.

5.
Annals of Saudi Medicine. 2008; 28 (3): 188-191
in English | IMEMR | ID: emr-85737

ABSTRACT

We compared endometrial sampling by pipelle endometrial curette with Conventional dilatation and curettage [D and C] in patients with abnormal uterine bleeding. Endometrial sampling with pipelle curette was performed on 100 patients followed by formal D and C. Samples were labeled as A and B, respectively, and sent to a histopathologist who was blinded as to the method of sampling. The histopathology reports of both samples were compared, taking D and C as the gold standard. An adequate sample was obtained in 98% of cases by pipelle and in 100% of cases by D and C. Pipelle had a sensitivity, specificity, positive predictive value and negative predictive value of 100% for diagnosing endometrial carcinoma, hyperplasia and secretory endometrium. Pipelle also had high diagnostic sensitivity, specificity and negative predictive value [100%, 98% and 100%, respectively] for hyperplasia with atypia, and low sensitivity [57%] and positive predictive value [57%], but high specificity [97%] and negative predictive value [97%] for endometritis. Similarly, for proliferative endometrium, the pipelle technique had values of 94% and 93% for sensitivity and specificity, respectively. Both samples labeled as inadequate for histology by pipelle were polyps on the D and C report. Difficult endotracheal intubation was encountered in two cases of D and C. No other complications of the procedure were observed. The pipelle is a safe device for getting an adequate endometrial sample for histology, with a high sensitivity and specificity for detection of hyperplasia and malignancy


Subject(s)
Humans , Female , Endometrium/pathology , Dilatation and Curettage
6.
PJMR-Pakistan Journal of Medical Research. 1997; 36 (3): 108-112
in English | IMEMR | ID: emr-46568

ABSTRACT

The survey was conducted during April 1990 to December 1991, to determine the prevalent species of anopheles and culex mosquitoes in the urban and rural areas of Rawalpindi and Islamabad. A total of 12592 mosquitoes were of captured. Of which 87.2% were identified as different species of culex and 12.8% anopheles species. A total of 12 anopheles and 8 culex species were identified. Maximum number of mosquitoes were captured in the month of November [18.2%], when the maximum temperature, relative humidity and rainfall was 24°C, 95%, 7.4mm respectively. An. culicifacies was found as the most abundant specy [47%] among anopheles species and C.vagans [53%] among culex species. About 2/3rd [64.8%] mosquitoes of the total number were captured from urban areas and 1/3rd [35.2%] from rural areas. The relative abundance of genus anopheline was found at rural area [12.2%] and to genus culicine at urban areas [64.2%]. Mosquitoes of both urban and rural areas preferred to rest at cattle sheds [65%] than bed rooms [35%]


Subject(s)
Insecta , Rural Health
SELECTION OF CITATIONS
SEARCH DETAIL