An Intelligent Patient Admission Model of Day Surgery Using Heterogeneous Data with Semi-Supervised Learning: A Case Study of Laparoscopic Cholecystectomy (Preprint)

2021 ◽  
Author(s):  
Wenchang Li ◽  
Lisha Jiang ◽  
Hongwei Shi ◽  
Hongsheng Ma

BACKGROUND Day surgery has many advantages including shortening hospital stay, decreasing the risk of hospital-associated infections, and increasing cost efficiency over traditional surgery, it has gained a great reputation and popularity in recent years. However, the patients’ admission criteria of day surgery at present were mainly based on expert experience, which was a lack of scientific evidence. OBJECTIVE Our study is to investigate the day surgery patient’s admission criteria and build an intelligent machine learning model of day surgery patients who underwent laparoscopic cholecystectomy, to ensure patients’ safety and medical quality, providing reference and inspiration for other day surgery admission decisions. METHODS We analyzed the clinical data of day surgery patients who underwent laparoscopic cholecystectomy at West China Hospital from Jan 1st 2009 to Dec 31st 2021 and developed a semi-supervised artificial intelligence algorithm, SDSPA algorithm, which is built by self-training and uses both structured data like patient characteristics and unstructured clinical diagnosis to assist surgeons to make quick admission decisions. RESULTS After comparing several classifiers with self-training in our experiment, the performance of LightGBM with unstructured text processed by BERT were the best, obtaining an accuracy of 0.85 and an f1-score of 0.83, as well as reaching 0.97 on the precision score, which is an important indicator related to patients’ safety. CONCLUSIONS The application of our SDSPA algorithm can make the patient admission of day surgery more intelligent, and maximize the utilization of medical resources while ensuring patients’ safety.

Author(s):  
Ryan Dillon ◽  
Jennifer Uyei ◽  
Rajpal Singh ◽  
Eilish McCann

Aim: To determine the suitability of network meta-analysis (NMA) using antibacterial treatment evidence in complicated urinary tract infection. Materials & methods: We conducted a systematic literature review to identify published clinical trial data for complicated urinary tract infection treatments. We performed a feasibility assessment to determine whether the available evidence would support the creation of a robust NMA, considering key assumptions of homogeneity, similarity and consistency. Results: Twenty-five trials met eligibility criteria. Risk of bias was low, and individual studies met their primary end point(s). Assumptions central to the conduct of a robust NMA were not met. Heterogeneity was ubiquitous, including baseline pathogen, treatment and patient characteristics. Conclusion: Limited and heterogeneous data identified make the use of NMA to compare novel antibacterial agents impractical and likely unreliable.


2008 ◽  
Vol 6 ◽  
pp. S86-S88 ◽  
Author(s):  
S.M. Tenconi ◽  
L. Boni ◽  
E.M. Colombo ◽  
G. Dionigi ◽  
F. Rovera ◽  
...  

2005 ◽  
Vol 12 ◽  
pp. S3-S3
Author(s):  
R MONZANI ◽  
F CARRERA ◽  
S BONA

2008 ◽  
Vol 74 (9) ◽  
pp. 832-833
Author(s):  
Madhavi Meka ◽  
Santosh Potdar ◽  
Peter Benotti ◽  
J. Edward Hartle ◽  
Christopher Senkowski

There is no uniform data regarding prophylactic cholecystectomy in patients undergoing renal transplantation with gallbladder disease. Data analyses suggest that posttransplant patients on cyclosporine have a higher incidence of gallbladder calcifications compared with nonimmunosuppressed patients. Laparoscopic cholecystectomy is a relatively safe procedure in modern-day surgery. Taking these facts into consideration, we attempted to compare risks and complications associated with gallbladder disease and eventual cholecystectomy in pretransplant versus post-transplant patients. Between June 1999 and December 2005, 210 renal transplants were performed at our institution. One hundred four patients who had transplants before April 2003 were not screened for gallbladder disease and nine of these patients developed gallbladder disease. These patients form our control group. One hundred six patients who had transplants after April 2003 had pretransplant screening for gallbladder disease and 11 patients were identified with gallbladder disease. These patients form our study group. Nine patients who developed gallbladder disease after renal transplant underwent laparoscopic cholecystectomy with three resulting morbidities (33%), two graft losses (22%), and one mortality (11%). There was one mortality (11%) in this group. One patient in the study group died of acute gallstone pancreatitis. Of the 11 patients who were found to have gallbladder disease on screening, nine patients underwent laparoscopic cholecystectomy with one morbidity and no mortality or graft loss. Given the relative rarity of the critical events in this study (morbidity, mortality, and graft loss), the definitive statistical value of prescreening for gallbladder disease cannot be established. However, our results are suggestive of clinical value and thus we tentatively recommend ultrasound screening for gallbladder disease for all pretransplant patients and laparoscopic cholecystectomy for those identified to have gallbladder disease.


2019 ◽  
Vol 2019 ◽  
pp. 1-12 ◽  
Author(s):  
Markus Rupp ◽  
Stefanie Kern ◽  
Thaqif El Khassawna ◽  
Abdullah Ismat ◽  
Deeksha Malhan ◽  
...  

Introduction. Nonunions are a challenge for orthopedic surgeons. In hypertrophic nonunions, improvement of mechanical stability usually is the satisfactory treatment, whereas in atrophic nonunions improvement of the biological environment is most important. However, scientific evidence revealed that “avital” nonunions are not avascular and fibrous tissue contains cells with osteogenic potential. To find out if systemic factors suppress this intrinsic potential in atrophic nonunions, this study compares characteristics of hypertrophic with atrophic nonunion patients. Methods. We analyzed medical records of 162 surgically treated patients suffering from aseptic long bone nonunions. Atrophic and hypertrophic nonunions were distinguished by absence or presence of callus and calcification in the fracture gap. Mechanical implant loosening and patient characteristics such as age, gender, and body mass index were assessed. Fracture classification according to AO/OTA, open and closed fractures, and osteosynthesis were recorded. In addition, comorbidities and allergies between both groups were compared. Results. A higher number of hypertrophic nonunion patients were male with often allergies. Hypertrophic nonunion occurred more often after intramedullary nailing compared to atrophic nonunions. Atrophic nonunion patients being nonallergic were significantly older than nonallergic patients suffering from hypertrophic nonunions. In both atrophic and hypertrophic nonunion patients, age was lower in patients with accompanying injuries compared with age of patients with isolated fractures. Conclusion. Systemic factors influence development of nonunion types. In nonallergic patients, atrophic nonunions occur more often in the elderly. This manuscript is a first step to identify different factors which might influence the nature of nonunion. To enable nonunion treatment which is tailored to individual patient characteristics, further prospective studies with more sophisticated research methods are necessary.


2010 ◽  
Vol 92 (4) ◽  
pp. 307-310 ◽  
Author(s):  
Sue K Down ◽  
Marko Nicolic ◽  
Hibba Abdulkarim ◽  
Nick Skelton ◽  
Adrian H Harris ◽  
...  

INTRODUCTION Re-admission rate following laparoscopic cholecystectomy is currently defined as within 30 days of the initial operation. This may underestimate the true incidence and financial cost of postoperative morbidity. This study aimed to analyse re-admissions within 90 days of elective and emergency laparoscopic cholecystectomy at a district general hospital, and to compare outcomes to larger teaching centres. PATIENTS AND METHODS We undertook a retrospective analysis of all patients re-admitted within 90 days of laparoscopic cholecystectomy during an 18-month period (June 2006 to December 2007). Patient characteristics, details of the primary operation, and reasons for re-admission were identified, and a comparison of re-admissions following elective versus emergency procedures was performed. RESULTS A total of 326 laparoscopic cholecystectomies were performed during the 18-month period (246 elective, 80 emergency). No operations required conversion to an open procedure. Twenty-five patients were re-admitted within 90 days of their operation, of whom only 14 had complications directly related to their surgery (overall re-admission rate 4.3%). There was no statistical difference in re-admission rate or cause of re-admission between elective and emergency procedures. However, the mean time to re-admission following elective procedures was significantly longer (36 days; P = 0.0003). CONCLUSIONS Re-admission rates at our district general hospital are comparable to those reported by larger teaching centres. Current 30-day re-admission data may significantly underestimate morbidity rates and socio-economic cost following elective laparoscopic cholecystectomy.


Author(s):  
Pietro Alessandro Vaccario ◽  
Alícia Carolina Rodrigues Rocha ◽  
Ledismar José da Silva

AbstractBacterial meningitis remains a public health problem. One of the complications of this group of diseases is cerebral ischemia, an important indicator of severity and an independent predictor of poor prognosis. It is already known that, in many cases, pathological aggressiveness is the result of brain abnormalities in individuals with mental illnesses. The indication of neurosurgeries for psychiatric disorders (NPDs) relies on numerous studies based on scientific evidence that correlate psychiatric illnesses with the limbic system and the pathophysiology of emotions. The development of sophisticated stereotactic target localization techniques, brain atlases, and imaging methods made stereotaxis possible, a procedure that increased the precision of neurosurgery and reduced brain damage. Nowadays, multiple targets can be treated during NPD, according to the particular characteristics of the patient. Moreover, the combination of lesions leads to more significant improvements compared with isolated procedures. The present study aimed to report the rare case of a patient with a history of bacterial meningitis who developed stroke and chronic pathological aggressiveness refractory to clinical treatment and underwent ablation using the multitarget stereotactic technique.


1996 ◽  
Vol 24 (2) ◽  
pp. 231-236 ◽  
Author(s):  
R. J. Singleton ◽  
G. E. Rudkin ◽  
G. A. Osborne ◽  
D. S. Watkin ◽  
J. A. R. Williams

Outcome is presented for 40 consecutive laparoscopic cholecystectomies performed in a public teaching hospital day surgery unit. The unanticipated hospital admission rate on the day of surgery was 17.5% (seven patients) and the majority of these (12.5%; five patients) were due to surgery-related considerations. Two other admissions were due to nausea and vomiting. One patient was admitted to hospital on the second postoperative day with nausea and vomiting. Procedure duration for the day cases averaged 98 minutes (SD25; range 60–167). Recovery room times before discharge averaged 272 minutes (SD 58; range 125–365). Each day surgery patient averaged 3.3 postoperative home visits from community nurses. Most patients (94%) mobilized at home by the second postoperative day and 85% resumed normal activities of daily living by two weeks. At follow-up, 25 patients (76%) stated they were happy to spend the first night at home, but seven (21%) would have preferred to remain in hospital for the first postoperative night. Laparoscopic cholecystectomy can be performed successfully as a day–case procedure, but long operating and recovery room times and potentially high admission rates suggest that these factors should be considered in cost equations for day-case management of this procedure.


Sign in / Sign up

Export Citation Format

Share Document