Background::Acute pulmonary embolism (APE) is a fatal cardiovascular disease, yet missed diagnosis and misdiagnosis often occur due to non-specific symptoms and signs. A simple, objective technique will help clinicians make a quick and precise diagnosis. In population studies, machine learning (ML) plays a critical role in characterizing cardiovascular risks, predicting outcomes, and identifying biomarkers. This work sought to develop an ML model for helping APE diagnosis and compare it against current clinical probability assessment models.Methods::This is a single-center retrospective study. Patients with suspected APE were continuously enrolled and randomly divided into two groups including training and testing sets. A total of 8 ML models, including random forest (RF), Na?ve Bayes, decision tree, K-nearest neighbors, logistic regression, multi-layer perceptron, support vector machine, and gradient boosting decision tree were developed based on the training set to diagnose APE. Thereafter, the model with the best diagnostic performance was selected and evaluated against the current clinical assessment strategies, including the Wells score, revised Geneva score, and Years algorithm. Eventually, the ML model was internally validated to assess the diagnostic performance using receiver operating characteristic (ROC) analysis.Results::The ML models were constructed using eight clinical features, including D-dimer, cardiac troponin T (cTNT), arterial oxygen saturation, heart rate, chest pain, lower limb pain, hemoptysis, and chronic heart failure. Among eight ML models, the RF model achieved the best performance with the highest area under the curve (AUC) (AUC = 0.774). Compared to the current clinical assessment strategies, the RF model outperformed the Wells score ( P = 0.030) and was not inferior to any other clinical probability assessment strategy. The AUC of the RF model for diagnosing APE onset in internal validation set was 0.726. Conclusions::Based on RF algorithm, a novel prediction model was finally constructed for APE diagnosis. When compared to the current clinical assessment strategies, the RF model achieved better diagnostic efficacy and accuracy. Therefore, the ML algorithm can be a useful tool in assisting with the diagnosis of APE.

Objective To explore the perioperative outcomes and safety of enhanced recovery after surgery (ERAS) in laparoscopic radical cystectomy (LRC).Methods We retrospectively evaluated outcome of 10 LRC patients on ERAS protocol from May 2017 to October 2017,and 39 LRC patients on conventional recovery after surgery(CRAS) protocol from July 2015 to November 2016.There were (60.9 ±11.4) years and (63.7 ± 12.1) years in ERAS group and CRAS group respectively(P =0.514);(25.5 ±2.7) kg/m2 and (24.4 ± 3.6) kg/m2 with body mass index (P =0.375).Both of the median of charlson comorbidity index (P =0.931) and American Society of Anesthesiologists score (P =0.254) were 2 There was no statistical significance between the two groups for type of urinary diversion and preoperative laboratory studies (P ＞ 0.05).Patients' perioperative outcomes,early (30-day) complications and postoperative readmission rate were compared.Results The ERAS group had less intraoperative crystalloid infusion [(950.0 ± 474.3) ml vs.(1 797.4 ± 448.1) ml,P ＜ 0.001],faster removed gastric tube (0 d vs.4 d,P ＜0.001),and shorter passing flatus time [(1.6 ± 0.8) d vs.(2.9 ± 1.4) d,P =0.006] than the CRAS group;however,no difference was found in terms of intraoperative colliod infusion [(1 110.0 ± 331.5)ml vs.(1 117.9 ± 397.9) ml,P =0.954].No patients from either group required conversion to open surgery.There was no significant difference between the two groups for operative time (P =0.311),estimated blood loss (P =0.073),drain days (P =0.681),postoperative hospital stay (P =0.509),overall blood transfusion (P =1.000),intensive care unit stay (P =1.000) and tumor characteristics (pathological stage,histology,nodes removed,positive nodes,lymph node-positive patients,positive surgical margins).The 30-day postoperative complications were documented in 5 (50％)and 23 (59％)patients in groups ERAS and CRAS (P =0.878),respectively.And the most common complication were minor complications (Clavien-Dindo grade 1 and 2) in both groups (100.0％ vs.86.9％,P =0.729).The 30-day readmission rate was 20.0％ (2 patients) in ERAS group and 10.3％ (4 patients) in CRAS group with no statistical significance(P =0.588).Conclusions Our ERAS protocol expedited bowel function recovery after RC and urinary diversion without increasing in 30-day complications compared with CRAS.The key of implement ERAS pathway is to explore and develop their own protocol conformed to their medical treatment enviroment.

Filamentous microalga Tribonema sp. has the advantages of highly resistance to zooplankton-predation, easy harvesting, and high cellular lipid content, in particular large amounts of palmitoleic acid (PA) and eicosapentaenoic acid (EPA). Therefore, Tribonema sp. is considered as a promising biomass feedstock to produce biodiesel and high-value products. In this work, we studied the effect of different concentrations of nitrogen (NaNO₃: 255-3 060 mg/L), phosphorus (K₂HPO₄: 4-240 mg/L), iron ((NH₄)₃FeC₁₂H₁₀O₁₄: 0.6-12 mg/L) and magnesium (MgSO₄: 7.5-450 mg/L) on the biomass, lipid content, and fatty acid composition of Tribonema sp. FACHB-1786, aiming at enhancing cell lipid productivity. The growth of Tribonema sp. had a positive correlation with the concentration of magnesium, and the maximum biomass of Tribonema sp. (under the condition of 450 mg/L MgSO₄) was 8.09 g/L, much greater than those reported in previous studies using the same and other Tribonema species under autotrophic conditions. Different nitrogen concentrations exerted no significant effect on algal growth (P > 0.05), but a higher nitrogen concentration resulted in a greater amount of lipid in the cells. The maximum volumetric productivities of total lipids (319. 6 mg/(L·d)), palmitoleic acid (135.7 mg/(L·d)), and eicosapentaenoic acid (24.2 mg/(L·d)) of Tribonema sp. were obtained when the concentrations of NaNO₃, K₂HPO₄, (NH₄)₃FeC₁₂H₁₀O₁₄, and MgSO₄ were 765 mg/L, 80 mg/L, 6 mg/L, and 75 mg/L, respectively. This study will provide a reference for substrate optimization for Tribonema sp. growth and lipid production.
Biofuels ; Biomass ; Lipids ; Microalgae ; Nitrogen ; Stramenopiles

Humans ; Hospital Mortality ; Pulmonary Embolism ; Comorbidity ; Registries ; Neoplasms/complications*