Search

OBJECTIVE. The purpose of this study was to develop an effective nomogram and artificial neural network (ANN) model for predicting recurrent hemoptysis after bronchial artery embolization (BAE). MATERIALS AND METHODS. The institutional ethics review boards of the two participating hospitals approved this study. Patients with hemoptysis who were treated with BAE were allocated to either the training cohort (Hospital A) or the validation cohort (Hospital B). The predictors of recurrent hemoptysis were identified by univariable and multivariable analyses in the training cohort. A nomogram and ANN model were then developed, and the accuracy was validated by the Harrell C statistic and ROC curves in both the training and validation cohorts. RESULTS. A total of 242 patients (training cohort, 141; validation cohort, 101) were enrolled in this study. The univariable and multivariable analyses revealed that age of 60 years old or older (hazard ratio [HR], 3.921; 95% CI, 1.267-12.127; p = 0.018), lung cancer (HR, 18.057; 95% CI, 4.124-79.068; p 0.16) according to the nomogram.

Introduction Accurate prediction of patient prognosis can be especially useful for the selection of best treatment protocols. Machine Learning can serve this purpose by making predictions based upon generalizable clinical patterns embedded within learning datasets. We designed a study to support the feature selection for the 2-year prognostic period and compared the performance of several Machine Learning prediction algorithms for accurate 2-year prognosis estimation in advanced-stage high grade serous ovarian cancer (HGSOC) patients. Methods The prognosis estimation was formulated as a binary classification problem. Dataset was split into training and test cohorts with repeated random sampling until there was no significant difference (p = 0.20) between the two cohorts. A ten-fold cross-validation was applied. Various state-of-the-art supervised classifiers were used. For feature selection, in addition to the exhaustive search for the best combination of features, we used the-chi square test of independence and the MRMR method. Results Two hundred nine patients were identified. The model's mean prediction accuracy reached 73%. We demonstrated that Support-Vector-Machine and Ensemble Subspace Discriminant algorithms outperformed Logistic Regression in accuracy indices. The probability of achieving a cancer-free state was maximised with a combination of primary cytoreduction, good performance status and maximal surgical effort (AUC 0.63). Standard chemotherapy, performance status, tumour load and residual disease were consistently predictive of the mid-term overall survival (AUC 0.63–0.66). The model recall and precision were greater than 80%. Conclusion Machine Learning appears to be promising for accurate prognosis estimation. Appropriate feature selection is required when building an HGSOC model for 2-year prognosis prediction. We provide evidence as to what combination of prognosticators leads to the largest impact on the HGSOC 2-year prognosis.

Introduction/Background* The prognosis of advanced stage high grade serous ovarian cancer patients (HGSOC) is multifactorial, and could be accurately predicted by using Machine Learning (ML) algorithms. We designed a study to support the feature selection of selected clinical variables to define their relative survival impact on two-year prognosis prediction in HGSOC patients, who received surgical treatment. Methodology This was a retrospective analysis of 209 FIGO stage III-IV HGSOC women, who were scheduled for cytoreductive surgery in SJUH, Leeds between Jan 2015 to Dec 2018 with curative or life-prolonging intent. The two-year prognosis estimation was formulated as a binary classification problem. Dataset was split into training (80%) and test (20%) cohorts with repeated random sampling until there was no significant difference (p=0.20) between the two cohorts. A ten-fold cross-validation was applied. Various state-of-the-art supervised ML classifiers were tested, including Support-Vector-Machines (SVMs), K-Nearest Neighbors (KNNs), Ensemble Classifiers, and Naive Bayes, based on a set of performance metrics. These results were directly compared to conventional Logistic Regression (LR). For feature selection, multivariate feature ranking using the MRMR method was carried out. Result(s)* Two hundred nine patients were identified. The model’s mean prediction accuracy reached 73%. We demonstrated that SVM and Ensemble Discriminant algorithms outperformed Logistic Regression in accuracy indices. The probability of achieving a cancer-free state was maximized with a combination of primary cytoreduction, good performance status, and maximal surgical effort (AUC 0.63). Standard chemotherapy, performance status, tumor load, and residual disease were consistently predictive of the two-year overall survival (AUC 0.63-0.66) (figure 1). The model recall and precision were greater than 80%. Conclusion* Appropriate feature selection is required when building a HGSOC model for two-year prognosis prediction. For HGSOC prognosis, one should consider not only the patient’s disease burden but also their overall medical status and ability to undergo extensive surgery, resulting in survival benefits alongside with standard chemotherapy.

Introduction/Background* In advanced stage high grade serous ovarian cancer (HGSOC), the introduction of maximal surgical effort without compromising peri-operative management and subsequent recovery to achieve complete cytoreduction, requires Critical Care Unit (CCU) availability. This paradigm shift prompts the development of tools to accurately predict CCU admission following cytoreductive surgery. Modern data mining technology, such as Machine Learning (ML) could be helpful in accurately predicting CCU admissions to improve standards of care. We developed a framework to improve the accuracy of predicting CCU admission in HGSOC patients by use of ML algorithms (figure 1). Methodology A cohort of 291 advanced stage HGSOC patients, who underwent surgical cytoreduction from Jan 2014 to Dec 2019, was selected from the ovarian database. They were randomly assigned to training (60%) and test (40%) sub-cohorts. Forward selection and backward stepwise regression were employed to screen independent pre- and intra-operative variables. Linear (LDA), Quadratic (QDA), and non-linear distance (ANN and KNN) ML models were employed to derive predictive information. These methods were tested against conventional linear regression (LR). Model performance was evaluated by prediction accuracy, sensitivity, specificity, and F1 scores. Result(s)* We identified 56/291(19.2%) CCU admissions. For the outcome of CCU admission, the prediction accuracies were higher for LDA (0.90) and QDA (0.93) compared with LR (0.84) when all the variables were included in the in-built model. Feature selection identified pre-treatment albumin, surgical complexity score, estimated blood loss, operative time, and bowel resection with stoma formation as the most significant prediction features. With feature selection, the prediction accuracies were higher for LDA (0.89) and KNN (0.86) compared with LR (0.82). Admission to CCU was associated with increased length of stay (P = 0.000), and decreased number of postoperative complications (P = 0.001). Conclusion* Herein, ML algorithms accurately predicted HGSOC patients, who required CCU admission following their cytoreductive surgery. Linear discriminant analysis was consistently more predictive than LR for CCU admission, irrespective of the number of features included in the analysis. Limited, potentially modifiable, mostly intra-operative factors contributing to CCU admission were identified and suggest areas for targeted interventions.

To identify the predictors for recovery of pyogenic liver abscess (PLA) patients treated with percutaneous catheter drainage (PCD) and antibiotics, and then develop an effective nomogram to predict the recovery time. The retrospective study included consecutive PLA patients treated with PCD and antibiotics. We defined the overall recovery time (ORT) as the time from the PCD procedure to the time of clinical success or failure. Based on the ORT, its predictors were identified with univariate and multivariate analyses. Then, a nomogram was developed to predict the ORT, and was internally validated by using Harrell’s c statistic. A total of 116 patients and 142 PCD procedures with a median ORT of 15.0±10.6 days were included. Gas-formation (GF; HR: 0.486 [95% CI 0.312–0.757]; P = 0.001), diabetes mellitus (DM; HR: 0.455 [95% CI 0.303–0.682]; P

Background: Adult granulosa cell tumor (AGCT) of the ovary generally has a good prognosis. Recurrences tend to be late and confined to the abdominopelvis. Bone metastases are extremely rare. We report an extremely rare case of AGCT with synchronous multiple bone metastases and discuss diagnostic procedures and management. Case description: A 35-year-old woman presented with abdominal bloating. On the day of surgery, acting on the complaint of right shoulder pain, an X-ray revealed a permeative lesion involving the neck of humerus, suggestive of a metastatic pathologic fracture. The patient underwent a full staging debulking surgery. Further imaging demonstrated multiple bone metastases. Histology confirmed an AGCT of the ovary. Diagnosis was established by a core bone biopsy from the left femur showing cells consistent with those seen with granulosa cell tumor. The patient received adjuvant chemotherapy with concurrent zoledronic acid as targeted therapy for her bone metastases. Endocrine systemic maintenance treatment was given. The patient rapidly deteriorated and died from her disease at 20 months from the initial diagnosis. Conclusion: Unpredictable biological behavior and clinical manifestations raise a high degree of suspicion for accurate AGCT diagnosis. Management of bone metastases often warrants input from the multidisciplinary team, and treatment may involve chemotherapy, palliative radiotherapy, or orthopaedic interventions.

Bioprinting of unmodified soft extracellular matrix into complex 3D structures has remained challenging to fabricate. Herein, we established a novel process for the printing of low-viscosity hydrogel by using a unique support technique to retain the structural integrity of the support structure. We demonstrated that this process of printing could be used for different types of hydrogel, ranging from fast crosslinking gelatin methacrylate to slow crosslinking collagen type I. In addition, we evaluated the biocompatibility of the process by observing the effects of the cytotoxicity of L929 and the functionality of the human umbilical vein endothelium primary cells after printing. The results show that the bioprinted construct provided excellent biocompatibility as well as supported cell growth and differentiation. Thus, this is a novel technique that can be potentially used to enhance the resolution of the extrusion-based bioprinter.

Pneumatic extrusion-based bioprinting is a recent and interesting technology that is very useful for biomedical applications. However, many process parameters in the bioprinter need to be fully understood in order to print at an adequate resolution. In this paper, a simple yet accurate mathematical model to predict the printed width of a continuous hydrogel line is proposed, in which the resolution is expressed as a function of nozzle size, pressure, and printing speed. A thermo-responsive hydrogel, pluronic F127, is used to validate the model predictions. This model could provide a platform for future correlation studies on pneumatic extrusion-based bioprinting as well as for developing new bioink formulations.

Fabrication techniques for cardiac tissue engineering have been evolving around scaffold-based and scaf-fold-free approaches. Conventional fabrication approaches lack control over scalability and homogeneous cell distribu-tion. Bioprinting provides a technological platform for controlled deposition of biomaterials, cells, and biological fac-tors in an organized fashion. Bioprinting is capable of alternating heterogeneous cell printing, printing anatomical rele-vant structure and microchannels resembling vasculature network. These are essential features of an engineered cardiac tissue. Bioprinting can potentially build engineered cardiac construct that resembles native tissue across macro to na-noscale.

Bioprinting is a layer-by-layer additive fabrication technique for making three-dimensional (3D) tissue and organ constructs using biological products. The capability to fabricate 3D tubular structure in free-form or vertical configuration is the first step towards the possibility of organ printing in three dimensions. In this study, alginate-based tubular structures of varying viscosity were printed vertically using multi-nozzle extrusion-based technique. Manufacturing challenges associated with the vertical printing configurations are also discussed here. We have also proposed measurable parameters to quantify the quality of printing for systematic investigation in bioprinting. This study lays a foundation for the successful fabrication of viable 3D tubular constructs.