A regimen based on the combination of trimethoprim/sulfamethoxazole with caspofungin and corticosteroids as a first-line therapy for patients with severe non-HIV-related pneumocystis jirovecii pneumonia: a retrospective study in a tertiary hospital.

BACKGROUND: Pneumocystis jirovecii pneumonia (PJP) is a life-threatening and severe disease in immunocompromised hosts. A synergistic regimen based on the combination of sulfamethoxazole-trimethoprim (SMX-TMP) with caspofungin and glucocorticosteroids (GCSs) may be a potential first-line therapy for PJP. Therefore, it is important to explore the efficacy and safety of this synergistic therapy for treating non-HIV-related PJP patients. METHODS: We retrospectively analysed the data of 38 patients with non-HIV-related PJP at the First Affiliated Hospital of Xi'an Jiaotong University. Patients were divided into two groups: the synergistic therapy group (ST group, n = 20) and the monotherapy group (MT group, n = 18). All patients were from the ICU and were diagnosed with severe PJP. In the ST group, all patients were treated with SMX-TMP (TMP 15-20 mg/kg per day) combined with caspofungin (70 mg as the loading dose and 50 mg/day as the maintenance dose) and a GCS (methylprednisolone 40-80 mg/day). Patients in the MT group were treated only with SMX-TMP (TMP 15-20 mg/kg per day). The clinical response, adverse events and mortality were compared between the two groups. RESULTS: The percentage of patients with a positive clinical response in the ST group was significantly greater than that in the MT group (100.00% vs. 66.70%, P = 0.005). The incidence of adverse events in the MT group was greater than that in the ST group (50.00% vs. 15.00%, P = 0.022). Furthermore, the dose of TMP and duration of fever in the ST group were markedly lower than those in the MT group (15.71 mg/kg/day vs. 18.35 mg/kg/day (P = 0.001) and 7.00 days vs. 11.50 days (P = 0.029), respectively). However, there were no significant differences in all-cause mortality or duration of hospital stay between the MT group and the ST group. CONCLUSIONS: Compared with SMZ/TMP monotherapy, synergistic therapy (SMZ-TMP combined with caspofungin and a GCS) for the treatment of non-HIV-related PJP can increase the clinical response rate, decrease the incidence of adverse events and shorten the duration of fever. These results indicate that synergistic therapy is effective and safe for treating severe non-HIV-related PJP.

Automated Detection of Epiretinal Membranes in OCT Images Using Deep Learning.

INTRODUCTION: Development and validation of a deep learning algorithm to automatedly identify and locate ERM regions in OCT images. METHODS: OCT images of 468 eyes were retrospectively collected from a total of 404 ERM patients. One expert manually annotated the ERM regions for all images. A total of 422 images (90%) and the rest 46 images (10%) were used as the training dataset and validation dataset for deep learning algorithm training and validation, respectively. One senior and one junior clinician read the images. The diagnostic results were compared. RESULTS: The algorithm accurately segmented and located the ERM regions in OCT images. The image-level accuracy was 95.65%, and the ERM region-level accuracy was 90.14%, respectively. In comparison experiments, the accuracies of the junior clinician improved from 85.00% and 61.29% without the assistance of the algorithm to 100.00% and 90.32% with the assistance of the algorithm. The corresponding results of the senior clinician were 96.15%, 95.00% without the assistance of the algorithm, and 96.15%, 97.50% with the assistance of the algorithm. CONCLUSIONS: The developed deep learning algorithm can accurately segmenting ERM regions in OCT images. This deep learning approach may help clinicians in clinical diagnosis with better accuracy and efficiency.

Deep Learning Promotes the Screening of Natural Products with Potential Microtubule Inhibition Activity.

Natural microtubule inhibitors, such as paclitaxel and ixabepilone, are key sources of novel medications, which have a considerable influence on anti-tumor chemotherapy. Natural product chemists have been encouraged to create novel methodologies for screening the new generation of microtubule inhibitors from the enormous natural product library. There have been major advancements in the use of artificial intelligence in medication discovery recently. Deep learning algorithms, in particular, have shown promise in terms of swiftly screening effective leads from huge compound libraries and producing novel compounds with desirable features. We used a deep neural network to search for potent ß-microtubule inhibitors in natural goods. Eleutherobin, bruceine D (BD), and phorbol 12-myristate 13-acetate (PMA) are three highly effective natural compounds that have been found as ß-microtubule inhibitors. In conclusion, this paper describes the use of deep learning to screen for effective ß-microtubule inhibitors. This research also demonstrates the promising possibility of employing deep learning to develop drugs from natural products for a wider range of disorders.

MiR-501-5p alleviates cardiac dysfunction in septic patients through targeting NR4A3 to prevent its binding with Bcl-2.

Sepsis-induced myocardial dysfunction is a common complication in septic patients. To date, a limited number of biomarkers that could predict cardiomyocyte apoptosis have been explored. In this study, we successfully established a cecal ligation and puncture (CLP)-induced septic model, and it was found that miR-501-5p expression was down-regulated in peripheral blood samples of septic patients with cardiac dysfunction, lipopolysaccharide (LPS)-induced cardiomyocytes, and the myocardium and peripheral blood in the septic model. Moreover, it was revealed that miR-501-5p overexpression could increase left ventricular diastolic pressure (LVDP), fractional shortening (FS), ejection fraction (EF), and maximum rate of the rise of left ventricular pressure (+dp/dt) in vivo, while it decreased the levels of myocardial injury-related indicators. In addition, LPS induction accelerated apoptosis and elevated the inflammation in HL-1 and HCM cells, which could be reversed by miR-501-5p overexpression. Mechanistically, we considered nuclear receptor subfamily 4 group A member 3 (NR4A3) as the target of miR-501-5p, and it was found that miR-501-5p prevented the binding between NR4A3 and Bcl-2. It was found that miR-501-5p exerted an inhibitory effect on cardiomyocyte apoptosis and inflammation in a NR4A3-dependent manner. Overall, our results may provide evidence for consideration of miR-501-5p in the therapy of sepsis.

Identification of Barrett's esophagus in endoscopic images using deep learning.

BACKGROUND: Development of a deep learning method to identify Barrett's esophagus (BE) scopes in endoscopic images. METHODS: 443 endoscopic images from 187 patients of BE were included in this study. The gastroesophageal junction (GEJ) and squamous-columnar junction (SCJ) of BE were manually annotated in endoscopic images by experts. Fully convolutional neural networks (FCN) were developed to automatically identify the BE scopes in endoscopic images. The networks were trained and evaluated in two separate image sets. The performance of segmentation was evaluated by intersection over union (IOU). RESULTS: The deep learning method was proved to be satisfying in the automated identification of BE in endoscopic images. The values of the IOU were 0.56 (GEJ) and 0.82 (SCJ), respectively. CONCLUSIONS: Deep learning algorithm is promising with accuracies of concordance with manual human assessment in segmentation of the BE scope in endoscopic images. This automated recognition method helps clinicians to locate and recognize the scopes of BE in endoscopic examinations.

A Deep Learning-Based Framework for Accurate Evaluation of Corneal Treatment Zone After Orthokeratology.

Purpose: Given the robust effectiveness of inhibiting myopia progression, orthokeratology has gained increasing popularity worldwide. However, identifying the boundary and the center of reshaped corneal area (i.e., treatment zone) is the main challenging task in evaluating the performance of orthokeratology. Here we present automated deep learning algorithms to solve the challenges. Methods: A total of 6328 corneal topographical maps, including 2996 axial subtractive maps and 3332 tangential subtractive maps, were collected from 2044 myopic patients who received orthokeratology. The boundary and the center of the treatment zones were annotated by experts as ground truths using axial subtractive maps and tangential subtractive maps, respectively. The algorithms based on neural network structures of fully convolutional networks (FCNs) and convolutional neural networks (CNNs) were developed to automatically identify the boundary and the center of the treatment zone, respectively. Results: The algorithm of FCNs identified the treatment zone boundaries with an accuracy intersection over union (IoU) of 0.90 ± 0.06 (mean ± SD; range, 0.60-0.97). The algorithm of CNNs also identified the treatment zone centers with an average deviation of 0.22 ± 0.22 mm (range, 0.01-1.66 mm). Conclusions: These results show that a deep learning-based solution is able to provide an automatic and accurate tool to accomplish the two main challenges of orthokeratology. Translational Relevance: Deep learning in orthokeratology can shorten the time while maintaining accurate results in clinical practice, which enables clinicians to help more patients daily.

Prognostic value of the combined variability of mean platelet volume and neutrophil percentage for short-term clinical outcomes of sepsis patients.

INTRODUCTION: In this single center retrospective cohort study, 784 patients with sepsis were enrolled and followed up for at least 30 days. The selected endpoint was an all-cause mortality event. METHOD: The relationship between MPV-CV + NEU%-CV and all-cause mortality (in-hospital and 30-day) was analyzed by categorizing the patients into four groups according to MPV-CV and NEU%-CV values. For in-hospital mortality, a significantly higher risk of mortality was observed in patients with an MPV-CV ≥ 15.00% + NEU%-CV ≥ 16.00% than in patients of the other groups (P < 0.001). After adjustment for age, sex, body mass index (BMI), infection site, Acute Physiology and Chronic Health Evaluation (APACHE) II score, Sequential Organ Failure Assessment (SOFA) score, use of vasoactive drugs, mechanical ventilation and renal replacement therapy (RRT), hematocrit, albumin, procalcitonin (PCT), and lactate, logistic regression analysis revealed that an MPV-CV ≥ 15.00% + NEU%-CV ≥ 16.00% was an independent predictive factor for in-hospital mortality [adjusted model: odds ratio (OR) = 4.48, 95% CI = 2.92-6.88, P = 0.001]. RESULTS: After adjustment for age, sex, BMI, infection site, APACHE II score, SOFA score, hematocrit, albumin, PCT, lactate, and the use of vasoactive drugs, mechanical ventilation, and RRT, Cox proportional-hazards regression model revealed that an MPV-CV ≥ 15.00% + NEU%-CV ≥ 16.00% was an independent predictive factor for 30-day mortality [adjusted model 1: hazard ratio (HR) = 7.69, 95% CI = 4.15-14.24, P < 0.001; adjusted model 2: HR = 4.07, 95% CI = 2.50-6.62, P < 0.001]. CONCLUSION: The combination of MPV-CV and NEU%-CV provides a good prognostic value and is a strong independent predictor of short-term clinical outcomes in patients with sepsis. An MPV-CV ≥ 15.00% + NEU%-CV ≥ 16.00% is significantly associated with adverse short-term clinical outcomes.Trial registration number is XJTU2AF2016LSY-04, the registration date is December 2018.

Voriconazole therapeutic drug monitoring in critically ill patients improves efficacy and safety of antifungal therapy.

Since voriconazole plasma trough concentration (VPC) is related to its efficacy and adverse events, therapeutic drug monitoring (TDM) is recommended to perform. However, there is no report about the data of voriconazole TDM in critically ill patients in China. This retrospective study was performed to determine whether voriconazole TDM was associated with treatment response and/or voriconazole adverse events in critically ill patients, and to identify the potential risk factors associated with VPC. A total of 216 critically ill patients were included. Patients were divided into two groups: those underwent voriconazole TDM (TDM group, n = 125) or did not undergo TDM (non-TDM group, n = 91). The clinical response and adverse events were recorded and compared. Furthermore, in TDM group, multivariate logistic regression analysis was performed to identify the possible risk factors resulting in the variability in initial VPC. The complete response in the TDM group was significantly higher than that in the non-TDM group (P = .012). The incidence of adverse events strongly associated with voriconazole in the non-TDM group was significantly higher than that in the TDM group (19.8% vs 9.6%; P = .033). The factors, including age (OR 0.934, 95% CI: 0.906-0.964), male (OR 5.929, 95% CI: 1.524-23.062), serum albumin level (OR 1.122, 95% CI: 1.020-1.234), diarrhoea (OR 4.953, 95% CI: 1.495-16.411) and non-intravenous administration (OR 4.763, 95% CI: 1.576-14.39), exerted the greatest effects on subtherapeutic VPC (VPC < 1.5 mg/L) in multivariate analysis. Intravenous administration (OR 7.657, 95% CI: 1.957-29.968) was a significant predictor of supratherapeutic VPC (VPC > 4.0 mg/L). TDM can result in a favourable clinical efficacy and a lower incidence of adverse events strongly associated with voriconazole in critically ill patients. Subtherapeutic VPC was closely related to younger age, male, hyperalbuminaemia, diarrhoea and non-intravenous administration, and intravenous administration was a significant predictor of supratherapeutic VPC.

Optimal teicoplanin loading regimen to rapidly achieve target trough plasma concentration in critically ill patients.

Teicoplanin is used for the treatment of Methicillin-resistant Staphylococcus aureus infection. It has been demonstrated that conventional loading regimen was insufficient for teicoplanin to achieve target trough plasma concentration (Cmin  > 10 mg/L). Therefore, a Chinese expert group recommended an optimal loading dose regimen of teicoplanin to treat severe Gram-positive infection. However, there was no report about the teicoplanin concentration, and the safety and efficacy of teicoplanin therapy in Chinese patients since the consensus was published. The objective of this study was to compare the teicoplanin Cmin and clinical response in critically ill Chinese patients after the administration of conventional or optimal loading regimen, and to reveal the potential factors that may affect teicoplanin Cmin in addition to loading regimen. Fifty-five patients were retrospectively divided into two groups based on teicoplanin loading regimen: (a) CD group (conventional loading dose group, n = 18, loading dose was 400 mg); (b) OD group (optimal loading dose group, n = 37, loading dose was 800 mg). Initially, three loading doses were administered every 12 hours, while the fourth loading dose was injected 24 hours after the third dose. The maintenance dose was 400 mg (CD group) or 800 mg (OD group), respectively. The mean teicoplanin Cmin on day 2 and day 4 in the OD group was significantly higher than those in the CD group, which were 14.75 ± 5.93 mg/L vs 8.26 ± 4.87 mg/L (P < .001) and 14.90 ± 5.20 mg/L vs 9.13 ± 4.75 mg/L (P = .019), respectively. The percentages of patients in the OD group achieving the target teicoplanin Cmin on day 2 and day 4 were also significantly higher than those in the CD group, which were 83.7% vs 33.3% (P < .001) and 82.4% vs 28.6% (P = .0013), respectively. Furthermore, multivariate linear regression analysis showed that body-weight exerted significant effect on teicoplanin Cmin in the OD group. The percentage of favourable clinical response in the OD group was significantly higher than that in the CD group (83.8% vs 55.6%, P = .025). There was no difference between teicoplanin adverse effects in the two groups. The study demonstrated that the optimal loading dose regimen of teicoplanin can rapidly reach target Cmin , and result in a good clinical efficacy and low adverse effect in critically ill Chinese patients.