Identifying necrotizing soft tissue infection using infectious fluid analysis and clinical parameters based on machine learning algorithms.

Background: Determining the presence of necrotizing soft tissue infection (NSTI) poses a significant hurdle. As of late, there has been a notable increase in the application of artificial intelligence (AI) machine learning techniques in identifying diseases, a shift that can be attributed to their exceptional efficiency, unbiased nature, and high precision. Methods: Information was gathered from a cohort of 13 patients suffering from NSTI, alongside 12 patients with cellulitis. The construction of NSTI diagnostic machine learning models utilized four different algorithms, specifically random forest, k-nearest neighbors (KNN), support vector machine (SVM), and logistic regression. These models were constructed based on 28 distinctive attributes identified through statistical examination. Following this, the diagnostic efficiency of each algorithms was evaluated. A novel random forest model, streamlined for clinical use, was later developed by focusing on 6 attributes that had the most pronounced influence on the accuracy of our initial random forest model. Results: The following data was noted regarding the sensitivity and specificity of the four NSTI diagnostic models:logistic regression displayed 78.2 % and 83.7 %, KNN presented 79.1 % and 87.1 %, SVM showed 83.5 % and 86.3 %, and random forest exhibited 89.6 % and 92.9 %, respectively. In comparison, lactate levels in fluid demonstrated 100 % sensitivity and 76.9 % specificity at an optimal cut-off point of 69.6 mg/dL. Among all four machine learning models, random forest outperformed the others and also showed better results than fluid lactate. A newly constructed random forest model, created using 6 of the 13 identified features, displayed promising results in diagnosing NSTI, having a sensitivity and specificity of 90.2 % and 92.2 %, respectively. Conclusions: Developing a diagnostic model for NSTI employing the random forest algorithm has resulted in a diagnostic technique that is more efficient, cost-effective, and expedient. This approach could provide healthcare practitioners with the tools to identify and manage NSTI with greater efficacy.

Urine-Specific Gravity-Based Hydration Prevents Stroke in Evolution in Patients with Acute Ischemic Stroke.

BACKGROUND: Early neurological deterioration after ischemic stroke (stroke-in-evolution [SIE]) is associated with poorer outcomes. Previous studies have demonstrated a link between hydration status and the development of SIE. In this study, we tested the hypothesis that rehydration therapy, administered on the basis of urine-specific gravity (USG) findings, might reduce the development of SIE. METHODS: We conducted a single-arm prospective study of patients with acute ischemic stroke with historical controls. For the study group, a USG higher than 1.010 was taken as an indication for rehydration. Control group patients were rehydrated without referring to USG. An increase in National Institutes of Health Stroke Scale (NIHSS) score of 4 or higher within 3 days was defined as having SIE. RESULTS: A total of 445 patients were analyzed, 167 in the study group and 278 in the control group. The proportion of patients who developed SIE was numerically, but not significantly, lower in the study group (5.9%; 10 of 167) compared with the control group (11.5%; 32 of 278). Among patients with a USG higher than 1.010 at admission, the SIE rate was significantly reduced in the study group compared with the control group (6.1% versus 16.0%; P = .021), while the rate of SIE was similar in those with a USG of 1.010 or lower at admission. Multivariate logistic regression analysis confirmed that USG-based hydration was an independent factor associated with reducing SIE. CONCLUSIONS: USG might be a convenient and useful method for guiding fluid therapy in patients with acute ischemic stroke. USG-based hydration reduced the incidence of SIE among patients with a USG higher than 1.010 at admission.

The influence of dehydration on the prognosis of acute ischemic stroke for patients treated with tissue plasminogen activator.

BACKGROUND: Many studies have determined that dehydration is an independent predictor of outcome after ischemic stroke (IS); however, none have determined if the use of thrombolytic therapy modifies the negative impact of poor hydration. To inform the stroke registry established at our institution, we conducted a retrospective study to determine if dehydration remains a negative prognostic factor after IS patients treated with tissue plasminogen activator (tPA). METHODS: Between 2007 and 2012, we recruited 382 subjects; 346 had data available and were divided into 2 groups on the basis of their blood urea nitrogen/creatinine (BUN/Cr) ratio. Dehydrated subjects had a BUN/Cr ratio ≥ 15; hydrated subjects had a BUN/Cr < 15. The primary outcome was impairment at discharge as graded by the Barthel Index (BI) and the modified Rankin Scale (mRS). RESULTS: The dehydration group had a greater mean age; more women; lower mean levels of hemoglobin, triglycerides, and sodium; and higher mean potassium and glucose levels. A favorable outcome as assessed by the mRS (≤2) was significantly less frequent among dehydrated subjects, but a favorable outcome by the BI (≥60) was not. Logistic regression and multivariate models confirmed that dehydration is an independent predictor of poor outcome by both the mRS and the BI; however, it was not predictive when patients were stratified by Trial of Org 10,172 in Acute Stroke Treatment subtype. CONCLUSIONS: Our findings indicate that use of thrombolytic therapy does not eliminate the need to closely monitor hydration status in patients with IS.

Favorable outcome of blood urea nitrogen/creatinine-based hydration therapy 3 months after acute ischemic stroke.

BACKGROUND: Dehydration is associated with acute ischemic stroke. However, the relationship between hydration therapy given during acute ischemic stroke and clinical outcomes remains unclear. AIMS: We determined whether hydration therapy in patients with a blood urea nitrogen/creatinine (BUN/Cr) ratio of at least 15 improved clinical outcome. METHODS: We conducted a nonblinded, phase II, single-arm, prospective study of patients with acute ischemic stroke and BUN/Cr ratio of at least 15 with historical controls. The hydration group received intravenous bolus (300-500 mL) saline followed by maintenance saline infusion (40-80 mL/h for the first 72 hours), whereas the control group received maintenance saline infusion (40-60 mL/h for the first 24 hours and 0-60 mL/h for 24-72 hours after stroke). The study end point was the percentage of patients with a favorable outcome defined as modified Rankin scale score of 2 or lower at 3 months after stroke. RESULTS: A total of 237 patients were enrolled (hydration, n = 134; control, n = 103). The mean volume of saline infused within the first 72 hours was significantly larger (P < .001), and the rate of favorable outcome at 3 months after stroke was significantly higher (P = .016) in the hydration group than in the controls. Further analysis revealed that the difference was significant in the lacunar stroke subtype (P = .020) but not in the nonlacunar subtype. CONCLUSIONS: Blood urea nitrogen/Cr ratio-based saline hydration therapy in patients with acute ischemic stroke significantly increased the rate of favorable clinical outcome with functional independence at 3 months after stroke.