Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 3 de 3
Filter
Add more filters










Database
Language
Publication year range
1.
Int J Med Inform ; 167: 104878, 2022 11.
Article in English | MEDLINE | ID: mdl-36194993

ABSTRACT

INTRODUCTION: Necrotizing Soft Tissue Infections (NSTI) are severe infections with high mortality affecting a heterogeneous patient population. There is a need for a clinical decision support system which predicts outcomes and provides treatment recommendations early in the disease course. METHODS: To identify relevant clinical needs, interviews with eight medical professionals (surgeons, intensivists, general practitioner, emergency department physician) were conducted. This resulted in 24 unique questions. Mortality was selected as first endpoint to develop a machine learning (Random Forest) based prediction model. For this purpose, data from the prospective, international INFECT cohort (N = 409) was used. RESULTS: Applying a feature selection procedure based on an unsupervised algorithm (Boruta) to the  > 1000 variables available in INFECT, including baseline, and both NSTI specific and NSTI non-specific clinical data yielded sixteen predictive parameters available on or prior to the first day on the intensive care unit (ICU). Using these sixteen variables 30-day mortality could be accurately predicted (AUC = 0.91, 95% CI 0.88-0.96). Except for age, all variables were related to sepsis (e.g. lactate, urine production, systole). No NSTI-specific variables were identified. Predictions significantly outperformed the SOFA score(p < 0.001, AUC = 0.77, 95% CI 0.69-0.84) and exceeded but did not significantly differ from the SAPS II score (p = 0.07, AUC = 0.88, 95% CI 0.83-0.92). The developed model proved to be stable with AUC  > 0.8 in case of high rates of missing data (50% missing) or when only using very early (<1 h) available variables. CONCLUSIONS: This study shows that mortality can be accurately predicted using a machine learning model. It lays the foundation for a more extensive, multi-endpoint clinical decision support system in which ultimately other outcomes and clinical questions (risk for septic shock, AKI, causative microbe) will be included.


Subject(s)
Soft Tissue Infections , Cohort Studies , Humans , Intensive Care Units , Lactates , Prospective Studies , Soft Tissue Infections/epidemiology , Soft Tissue Infections/therapy
2.
World J Surg ; 46(5): 1051-1058, 2022 05.
Article in English | MEDLINE | ID: mdl-35187588

ABSTRACT

BACKGROUND: Necrotizing soft tissue infections (NSTI) affect long-term quality of life in survivors. Different approaches to debridement may influence quality of life. The aim of this study was to assess the current practice of the debridement of NSTI in the Netherlands. METHODS: An animated, interactive online survey was distributed among general surgeons and plastic surgeons in the Netherlands. Two NSTI-cases were presented, followed by questions regarding the preferred surgical approach. Case one described a woman with a swollen, red leg, with signs of sepsis and without visible necrosis. Case two described an immunocompromised man with septic shock syndrome and extensive necrosis. RESULTS: In total 232 responses were included (143 general surgeons, 89 plastic surgeons). In case one, 32% chose to preserve all skin, while 17% chose to resect all skin above the affected fascia, including normal-looking skin. In case two, all participants resected necrotic skin, and most (88%) also blue discolored skin. While 32% did not resect more than blue discolored and necrotic skin, 35% also resected red-colored skin, and 21% all skin overlying the affected fascia, including normal colored skin. Respondents working in a hospital with a burn center tended to preserve more skin, whereas plastic surgeons chose more often for skin resection compared to general surgeons. CONCLUSIONS: By using a novel approach to a survey, the authors demonstrate the existence of extensive practice variety regarding the approach to debridement of NSTI among Dutch general and plastic surgeons. Consensus is needed, followed by targeted education of surgeons.


Subject(s)
Shock, Septic , Soft Tissue Infections , Debridement , Female , Humans , Male , Quality of Life , Soft Tissue Infections/surgery , Surveys and Questionnaires
3.
J Pediatr Surg ; 49(7): 1153-5, 2014 Jul.
Article in English | MEDLINE | ID: mdl-24952806

ABSTRACT

BACKGROUND: In patients with a non-palpable testis (NPT) on physical examination, the testis is assumed either to be situated intra-abdominally or to be hypoplastic or absent. Diagnostic laparoscopy in these boys is considered the preferable first step. In this study the diagnostic value of pre-operative ultrasound for NPT is assessed in comparison with laparoscopy. METHODS: All boys aged under the age of 17 years who were diagnosed with an NPT by a pediatric surgeon from 2000 till 2012 were evaluated. All patients of whom clinical, ultrasonographic, and operative findings were available were included. RESULTS: Ninety-six boys with 117 NPTs were included. With ultrasound 67 testes were detected in the inguinal canal, which was confirmed peroperatively for 61 testes. Of the 15 testes with an intra-abdominal position on ultrasound, 10 were found intra-abdominally during surgery. The positive predictive value of the ultrasonography is 91% for inguinally located testes and 67% for intra-abdominally located testes. CONCLUSION: Ultrasonography has a high positive predictive value for inguinally located testes. When ultrasound locates a testis in an inguinal location, a primary inguinal exploration can be considered, preventing an unnecessary diagnostic laparoscopy.


Subject(s)
Cryptorchidism/diagnostic imaging , Preoperative Care , Testis/diagnostic imaging , Adolescent , Child , Child, Preschool , Cryptorchidism/surgery , Humans , Infant , Infant, Newborn , Laparoscopy , Male , Predictive Value of Tests , Testis/abnormalities , Testis/surgery , Ultrasonography
SELECTION OF CITATIONS
SEARCH DETAIL
...