Biologically inspired intelligent decision making: a commentary on the use of artificial neural networks in bioinformatics

Exploring the efficacy of artificial neural networks in predicting lung cancer recurrence: a retrospective study based on patient records

Background

Lung cancer remains a significant public health concern, accounting for a considerable number of cancer-related deaths worldwide. Neural networks have emerged as a promising tool that can aid in the diagnosis and treatment of various cancers. Consequently, there has been a growing interest in exploring the potential of artificial intelligence (AI) methods in medicine. The present study aimed to evaluate the effectiveness of a neural network in predicting lung cancer recurrence.

Methods

The study employed retrospective data from 2,296 medical records of patients diagnosed with lung cancer and admitted to the Warmińsko-Mazurskie Center for Lung Diseases in Olsztyn, Poland. The statistical software STATISTICA 7.1, equipped with the Neural Networks module (StatSoft Inc., Tulsa, USA), was utilized to analyze the data. The neural network model was trained using patient information regarding gender, treatment, smoking status, family history, and symptoms of cancer.

Results

The study employed a multilayer perceptron neural network with a two-phase learning process. The network demonstrated high predictive ability, as indicated by the percentage of correct classifications, which amounted to 87.5%, 89.1%, and 89.9% for the training, validation, and test sets, respectively.

Conclusions

The findings of this study support the potential usefulness of a neural network-based predictive model in assessing the risk of lung cancer recurrence. Further research is warranted to validate these findings and to explore AI's broader implications in cancer diagnosis and treatment.

Prediction of transport proteins from sequence information with the deep learning approach

Transport proteins (TPs) are vital to the growth and life of all living things, especially in fields of microbial pathogenesis and drug resistance of tumor cells. Accurately identifying potential TPs remains an important challenge for the advancement of functional genomics. This study aimed to develop a tool for predicting TPs using the deep learning approach. Here, we proposed DeepTP, a convolutional neural network model that uses parallel subnetworks to extract features from protein sequences and uses fully connected layers for TP classification. To train and evaluate the performance of the developed model, datasets were collected from the UniProtKB/Swiss-Prot database. The test results revealed that the proposed model could successfully identify TPs with the AUCROC, accuracy, F-value, and Matthews correlation coefficient of 0.9719, 0.9513, 0.8982, and 0.8679, respectively. By further comparison, DeepTP achieved better performance than other commonly used methods. Analysis of the gradients of prediction score concerning input suggested that DeepTP makes predictions by recognizing the functional domains of TPs. We anticipate that DeepTP will serve as a useful tool for predicting TPs in large-scale genome projects, which will facilitate the discovery of novel TPs.

Machine learning predicts clinically significant health related quality of life improvement after sensorimotor rehabilitation interventions in chronic stroke

Health related quality of life (HRQOL) reflects individuals perceived of wellness in health domains and is often deteriorated after stroke. Precise prediction of HRQOL changes after rehabilitation interventions is critical for optimizing stroke rehabilitation efficiency and efficacy. Machine learning (ML) has become a promising outcome prediction approach because of its high accuracy and easiness to use. Incorporating ML models into rehabilitation practice may facilitate efficient and accurate clinical decision making. Therefore, this study aimed to determine if ML algorithms could accurately predict clinically significant HRQOL improvements after stroke sensorimotor rehabilitation interventions and identify important predictors. Five ML algorithms including the random forest (RF), k-nearest neighbors (KNN), artificial neural network, support vector machine and logistic regression were used. Datasets from 132 people with chronic stroke were included. The Stroke Impact Scale was used for assessing multi-dimensional and global self-perceived HRQOL. Potential predictors included personal characteristics and baseline cognitive/motor/sensory/functional/HRQOL attributes. Data were divided into training and test sets. Tenfold cross-validation procedure with the training data set was used for developing models. The test set was used for determining model performance. Results revealed that RF was effective at predicting multidimensional HRQOL (accuracy: 85%; area under the receiver operating characteristic curve, AUC-ROC: 0.86) and global perceived recovery (accuracy: 80%; AUC-ROC: 0.75), and KNN was effective at predicting global perceived recovery (accuracy: 82.5%; AUC-ROC: 0.76). Age/gender, baseline HRQOL, wrist/hand muscle function, arm movement efficiency and sensory function were identified as crucial predictors. Our study indicated that RF and KNN outperformed the other three models on predicting HRQOL recovery after sensorimotor rehabilitation in stroke patients and could be considered for future clinical application.

Artificial Intelligence-Driven Prediction Modeling and Decision Making in Spine Surgery Using Hybrid Machine Learning Models

Healthcare systems worldwide generate vast amounts of data from many different sources. Although of high complexity for a human being, it is essential to determine the patterns and minor variations in the genomic, radiological, laboratory, or clinical data that reliably differentiate phenotypes or allow high predictive accuracy in health-related tasks. Convolutional neural networks (CNN) are increasingly applied to image data for various tasks. Its use for non-imaging data becomes feasible through different modern machine learning techniques, converting non-imaging data into images before inputting them into the CNN model. Considering also that healthcare providers do not solely use one data modality for their decisions, this approach opens the door for multi-input/mixed data models which use a combination of patient information, such as genomic, radiological, and clinical data, to train a hybrid deep learning model. Thus, this reflects the main characteristic of artificial intelligence: simulating natural human behavior. The present review focuses on key advances in machine and deep learning, allowing for multi-perspective pattern recognition across the entire information set of patients in spine surgery. This is the first review of artificial intelligence focusing on hybrid models for deep learning applications in spine surgery, to the best of our knowledge. This is especially interesting as future tools are unlikely to use solely one data modality. The techniques discussed could become important in establishing a new approach to decision-making in spine surgery based on three fundamental pillars: (1) patient-specific, (2) artificial intelligence-driven, (3) integrating multimodal data. The findings reveal promising research that already took place to develop multi-input mixed-data hybrid decision-supporting models. Their implementation in spine surgery may hence be only a matter of time.

Accuracy of Ultrasound Diagnosis of Thyroid Nodules Based on Artificial Intelligence-Assisted Diagnostic Technology: A Systematic Review and Meta-Analysis

BACKGROUND

Ultrasonography (US) is the most common method of identifying thyroid nodules, but US images require an experienced surgeon for identification. Many artificial intelligence (AI) techniques such as computer-aided diagnostic systems (CAD), deep learning (DL), and machine learning (ML) have been used to assist in the diagnosis of thyroid nodules, but whether AI techniques can improve the diagnostic accuracy of thyroid nodules still needs to be explored.

OBJECTIVE

To clarify the accuracy of AI-based thyroid nodule US images for differentiating benign and malignant thyroid nodules.

METHODS

A search strategy of "subject terms + key words" was used to search PubMed, Cochrane Library, Embase, Web of Science, China Biology Medicine (CBM), and China National Knowledge Infrastructure (CNKI) for studies on AI-assisted diagnosis of thyroid nodules based on US images. The summarized receiver operating characteristic (SROC) curve and the pooled sensitivity and specificity were used to assess the performance of the diagnostic tests. The quality assessment of diagnostics accuracy studies-2 (QUADAS-2) tool was used to assess the methodological quality of the included studies. The Review Manager 5.3 and Stata 15 were used to process the data. Subgroup analysis was based on the integrity of data collection.

RESULTS

A total of 25 studies with 17,429 US images of thyroid nodules were included. AI-assisted diagnostic techniques had better diagnostic efficacy in the diagnosis of benign and malignant thyroid nodules: sensitivity 0.88 (95% CI: (0.85-0.90)), specificity 0.81 (95% CI: 0.74-0.86), diagnostic odds ratio (DOR) 30 (95% CI: 19-46). The SROC curve indicated that the area under the curve (AUC) was 0.92 (95% CI: 0.89-0.94). Threshold effect analysis showed a Spearman correlation coefficient: 0.17 < 0.5, suggesting no threshold effect for the included studies. After a meta-regression analysis of 4 different subgroups, the results showed a statistically significant effect of mean age ≥50 years on heterogeneity. Compared with studies with an average age of ≥50 years, AI-assisted diagnostic techniques had higher diagnostic performance in studies with an average age of <50 years (0.89 (95% CI: 0.87-0.92) vs. 0.80 (95% CI: 0.73-0.88)), (0.83 (95% CI: 0.77-0.88) vs. 0.73 (95% CI: 0.60-0.87)).

CONCLUSIONS

AI-assisted diagnostic techniques had good diagnostic efficacy for thyroid nodules. For the diagnosis of <50 year olds, AI-assisted diagnostic technology was more effective in diagnosis.

Dynamic changes of intestinal flora in patients with irritable bowel syndrome combined with anxiety and depression after oral administration of enterobacteria capsules

This study investigated the clinical characteristics and dynamic changes of intestinal bacterial community to evaluate the curative effect of fecal microbiota transplantation (FMT) on irritable bowel syndrome with predominant diarrhea (IBS-D) comorbid with anxiety and depression. Total two treatments were designed in randomize-controlled trial includes oral FMT capsules with 1 week (A1), 8 weeks (A2), and 12 weeks (A3), as well as oral empty capsules with 1 week (B1), 8 weeks (B2), and 12 weeks (B3) as control for comparison. The positive therapeutic effects occurred in FMT colonized patient with IBS-D comorbid psychological disorder, demonstrated at alleviated IBS-D severity (IBS-SSS score from 291.11 reduced to 144.44), altered stool type (from 6 changed to 4), reduced anxiety and depression scores (from 18.33 to 8.39 and from 22.33 to 17.78) after FMT-treated 12 weeks. The FMT therapy improved bacterial alpha diversity and the majority bacterial community predominant by Bacteroidetes and Firmicutes, and the relative abundance (RA) was higher after FMT-treated 12 weeks (50.61% and 45.52%) than control (47.62% and 38.96%). In short, FMT therapy has great potential for IBS-D patients combined with anxiety and depression by alleviated clinical symptoms and restore the intestinal micro-ecology.

An Artificial Neural Network Prediction Model for Posttraumatic Epilepsy: Retrospective Cohort Study

Background

Posttraumatic epilepsy (PTE) is a common sequela after traumatic brain injury (TBI), and identifying high-risk patients with PTE is necessary for their better treatment. Although artificial neural network (ANN) prediction models have been reported and are superior to traditional models, the ANN prediction model for PTE is lacking.

Objective

We aim to train and validate an ANN model to anticipate the risks of PTE.

Methods

The training cohort was TBI patients registered at West China Hospital. We used a 5-fold cross-validation approach to train and test the ANN model to avoid overfitting; 21 independent variables were used as input neurons in the ANN models, using a back-propagation algorithm to minimize the loss function. Finally, we obtained sensitivity, specificity, and accuracy of each ANN model from the 5 rounds of cross-validation and compared the accuracy with a nomogram prediction model built in our previous work based on the same population. In addition, we evaluated the performance of the model using patients registered at Chengdu Shang Jin Nan Fu Hospital (testing cohort 1) and Sichuan Provincial People’s Hospital (testing cohort 2) between January 1, 2013, and March 1, 2015.

Results

For the training cohort, we enrolled 1301 TBI patients from January 1, 2011, to December 31, 2017. The prevalence of PTE was 12.8% (166/1301, 95% CI 10.9%-14.6%). Of the TBI patients registered in testing cohort 1, PTE prevalence was 10.5% (44/421, 95% CI 7.5%-13.4%). Of the TBI patients registered in testing cohort 2, PTE prevalence was 6.1% (25/413, 95% CI 3.7%-8.4%). The results of the ANN model show that, the area under the receiver operating characteristic curve in the training cohort was 0.907 (95% CI 0.889-0.924), testing cohort 1 was 0.867 (95% CI 0.842-0.893), and testing cohort 2 was 0.859 (95% CI 0.826-0.890). Second, the average accuracy of the training cohort was 0.557 (95% CI 0.510-0.620), with 0.470 (95% CI 0.414-0.526) in testing cohort 1 and 0.344 (95% CI 0.287-0.401) in testing cohort 2. In addition, sensitivity, specificity, positive predictive values and negative predictors in the training cohort (testing cohort 1 and testing cohort 2) were 0.80 (0.83 and 0.80), 0.86 (0.80 and 0.84), 91% (85% and 78%), and 86% (80% and 83%), respectively. When calibrating this ANN model, Brier scored 0.121 in testing cohort 1 and 0.127 in testing cohort 2. Compared with the nomogram model, the ANN prediction model had a higher accuracy (P=.01).

Conclusions

This study shows that the ANN model can predict the risk of PTE and is superior to the risk estimated based on traditional statistical methods. However, the calibration of the model is a bit poor, and we need to calibrate it on a large sample size set and further improve the model.

Sequential Pattern Mining to Predict Medical In-Hospital Mortality from Administrative Data: Application to Acute Coronary Syndrome

Prediction of a medical outcome based on a trajectory of care has generated a lot of interest in medical research. In sequence prediction modeling, models based on machine learning (ML) techniques have proven their efficiency compared to other models. In addition, reducing model complexity is a challenge. Solutions have been proposed by introducing pattern mining techniques. Based on these results, we developed a new method to extract sets of relevant event sequences for medical events' prediction, applied to predict the risk of in-hospital mortality in acute coronary syndrome (ACS). From the French Hospital Discharge Database, we mined sequential patterns. They were further integrated into several predictive models using a text string distance to measure the similarity between patients' patterns of care. We computed combinations of similarity measurements and ML models commonly used. A Support Vector Machine model coupled with edit-based distance appeared as the most effective model. We obtained good results in terms of discrimination with the receiver operating characteristic curve scores ranging from 0.71 to 0.99 with a good overall accuracy. We demonstrated the interest of sequential patterns for event prediction. This could be a first step to a decision-support tool for the prevention of in-hospital death by ACS.

Artificial Intelligence for Personalized Medicine in Thyroid Cancer: Current Status and Future Perspectives

Thyroid cancers (TC) have increasingly been detected following advances in diagnostic methods. Risk stratification guided by refined information becomes a crucial step toward the goal of personalized medicine. The diagnosis of TC mainly relies on imaging analysis, but visual examination may not reveal much information and not enable comprehensive analysis. Artificial intelligence (AI) is a technology used to extract and quantify key image information by simulating complex human functions. This latent, precise information contributes to stratify TC on the distinct risk and drives tailored management to transit from the surface (population-based) to a point (individual-based). In this review, we started with several challenges regarding personalized care in TC, for example, inconsistent rating ability of ultrasound physicians, uncertainty in cytopathological diagnosis, difficulty in discriminating follicular neoplasms, and inaccurate prognostication. We then analyzed and summarized the advances of AI to extract and analyze morphological, textural, and molecular features to reveal the ground truth of TC. Consequently, their combination with AI technology will make individual medical strategies possible.

Dental Caries Prediction Based on a Survey of the Oral Health Epidemiology among the Geriatric Residents of Liaoning, China

Background

Dental caries is one of the most common chronic diseases observed in elderly patients. The development of preventive strategies for dental caries in elderly individuals is vital.

Objective

The objective of the present study was to construct a generalized regression neural network (GRNN) prediction model for the risk assessment of dental caries among the geriatric residents of Liaoning, China.

Methods

A stratified equal-capacity random sampling method was used to randomly select 1144 elderly (65-74 years) residents (gender ratio 1 : 1) of Liaoning, China. Data for the oral assessment, including caries characteristics, and questionnaire survey from each participant were collected. Multivariate logistic regression analysis was then performed to identify the independent predictors. GRNN was applied to establish a prediction model for dental caries. The accuracy of the unconditional logistic regression and the GRNN early warning model was compared.

Results

A total of 1144 patients fulfilled the requirements and completed the questionnaires. The caries rate was 68.5%, and the main associated factors were toothache history, residence area, smoking, and drinking. We randomly divided the data for the 1144 participants into a training set (915 cases) and a test set (229 cases). The optimal smoothing factor was 0.7, and the area under the receiver operating characteristic curve for the GRNN model was 0.626 (95% confidence interval, 0.544 to 0.708), with a P value of 0.002. In terms of consistency, sensitivity, and specificity, the GRNN model was better than the traditional unconditional multivariate logistic regression model.

Conclusion

Geriatric (65-74 years) residents of Liaoning, China, have a high rate of dental caries. Residents with a history of toothache and smoking habits are more susceptible to the disease. The GRNN early warning model is an accurate and meaningful tool for screening, early diagnosis, and treatment planning for geriatric individuals with a high risk of caries.

Predicting clinically significant motor function improvement after contemporary task-oriented interventions using machine learning approaches

BACKGROUND

Accurate prediction of motor recovery after stroke is critical for treatment decisions and planning. Machine learning has been proposed to be a promising technique for outcome prediction because of its high accuracy and ability to process large volumes of data. It has been used to predict acute stroke recovery; however, whether machine learning would be effective for predicting rehabilitation outcomes in chronic stroke patients for common contemporary task-oriented interventions remains largely unexplored. This study aimed to determine the accuracy and performance of machine learning to predict clinically significant motor function improvements after contemporary task-oriented intervention in chronic stroke patients and identify important predictors for building machine learning prediction models.

METHODS

This study was a secondary analysis of data using two common machine learning approaches, which were the k-nearest neighbor (KNN) and artificial neural network (ANN). Chronic stroke patients (N = 239) that received 30 h of task-oriented training including the constraint-induced movement therapy, bilateral arm training, robot-assisted therapy and mirror therapy were included. The Fugl-Meyer assessment scale (FMA) was the main outcome. Potential predictors include age, gender, side of lesion, time since stroke, baseline functional status, motor function and quality of life. We divided the data set into a training set and a test set and used the cross-validation procedure to construct machine learning models based on the training set. After the models were built, we used the test data set to evaluate the accuracy and prediction performance of the models.

RESULTS

Three important predictors were identified, which were time since stroke, baseline functional independence measure (FIM) and baseline FMA scores. Models for predicting motor function improvements were accurate. The prediction accuracy of the KNN model was 85.42% and area under the receiver operating characteristic curve (AUC-ROC) was 0.89. The prediction accuracy of the ANN model was 81.25% and the AUC-ROC was 0.77.

CONCLUSIONS

Incorporating machine learning into clinical outcome prediction using three key predictors including time since stroke, baseline functional and motor ability may help clinicians/therapists to identify patients that are most likely to benefit from contemporary task-oriented interventions. The KNN and ANN models may be potentially useful for predicting clinically significant motor recovery in chronic stroke.

Cyclin-Dependent Kinase 18 Controls Trafficking of Aquaporin-2 and Its Abundance through Ubiquitin Ligase STUB1, Which Functions as an AKAP

Arginine-vasopressin (AVP) facilitates water reabsorption in renal collecting duct principal cells through regulation of the water channel aquaporin-2 (AQP2). The hormone binds to vasopressin V2 receptors (V2R) on the surface of the cells and stimulates cAMP synthesis. The cAMP activates protein kinase A (PKA), which initiates signaling that causes an accumulation of AQP2 in the plasma membrane of the cells facilitating water reabsorption from primary urine and fine-tuning of body water homeostasis. AVP-mediated PKA activation also causes an increase in the AQP2 protein abundance through a mechanism that involves dephosphorylation of AQP2 at serine 261 and a decrease in its poly-ubiquitination. However, the signaling downstream of PKA that controls the localization and abundance of AQP2 is incompletely understood. We carried out an siRNA screen targeting 719 kinase-related genes, representing the majority of the kinases of the human genome and analyzed the effect of the knockdown on AQP2 by high-content imaging and biochemical approaches. The screening identified 13 hits whose knockdown inhibited the AQP2 accumulation in the plasma membrane. Amongst the candidates was the so far hardly characterized cyclin-dependent kinase 18 (CDK18). Our further analysis revealed a hitherto unrecognized signalosome comprising CDK18, an E3 ubiquitin ligase, STUB1 (CHIP), PKA and AQP2 that controls the localization and abundance of AQP2. CDK18 controls AQP2 through phosphorylation at serine 261 and STUB1-mediated ubiquitination. STUB1 functions as an A-kinase anchoring protein (AKAP) tethering PKA to the protein complex and bridging AQP2 and CDK18. The modulation of the protein complex may lead to novel concepts for the treatment of disorders which are caused or are associated with dysregulated AQP2 and for which a satisfactory treatment is not available, e.g., hyponatremia, liver cirrhosis, diabetes insipidus, ADPKD or heart failure.

Identifying Cancer Targets Based on Machine Learning Methods via Chou's 5-steps Rule and General Pseudo Components

In recent years, the successful implementation of human genome project has made people realize that genetic, environmental and lifestyle factors should be combined together to study cancer due to the complexity and various forms of the disease. The increasing availability and growth rate of 'big data' derived from various omics, opens a new window for study and therapy of cancer. In this paper, we will introduce the application of machine learning methods in handling cancer big data including the use of artificial neural networks, support vector machines, ensemble learning and naïve Bayes classifiers.

Mortality prediction in patients with isolated moderate and severe traumatic brain injury using machine learning models

BACKGROUND

The purpose of this study was to build a model of machine learning (ML) for the prediction of mortality in patients with isolated moderate and severe traumatic brain injury (TBI).

METHODS

Hospitalized adult patients registered in the Trauma Registry System between January 2009 and December 2015 were enrolled in this study. Only patients with an Abbreviated Injury Scale (AIS) score ≥ 3 points related to head injuries were included in this study. A total of 1734 (1564 survival and 170 non-survival) and 325 (293 survival and 32 non-survival) patients were included in the training and test sets, respectively.

RESULTS

Using demographics and injury characteristics, as well as patient laboratory data, predictive tools (e.g., logistic regression [LR], support vector machine [SVM], decision tree [DT], naive Bayes [NB], and artificial neural networks [ANN]) were used to determine the mortality of individual patients. The predictive performance was evaluated by accuracy, sensitivity, and specificity, as well as by area under the curve (AUC) measures of receiver operator characteristic curves. In the training set, all five ML models had a specificity of more than 90% and all ML models (except the NB) achieved an accuracy of more than 90%. Among them, the ANN had the highest sensitivity (80.59%) in mortality prediction. Regarding performance, the ANN had the highest AUC (0.968), followed by the LR (0.942), SVM (0.935), NB (0.908), and DT (0.872). In the test set, the ANN had the highest sensitivity (84.38%) in mortality prediction, followed by the SVM (65.63%), LR (59.38%), NB (59.38%), and DT (43.75%).

CONCLUSIONS

The ANN model provided the best prediction of mortality for patients with isolated moderate and severe TBI.

Artificial neural network approach to predict surgical site infection after free-flap reconstruction in patients receiving surgery for head and neck cancer

Background

The aim of this study was to develop an effective surgical site infection (SSI) prediction model in patients receiving free-flap reconstruction after surgery for head and neck cancer using artificial neural network (ANN), and to compare its predictive power with that of conventional logistic regression (LR).

Materials and methods

There were 1,836 patients with 1,854 free-flap reconstructions and 438 postoperative SSIs in the dataset for analysis. They were randomly assigned tin ratio of 7:3 into a training set and a test set. Based on comprehensive characteristics of patients and diseases in the absence or presence of operative data, prediction of SSI was performed at two time points (pre-operatively and post-operatively) with a feed-forward ANN and the LR models. In addition to the calculated accuracy, sensitivity, and specificity, the predictive performance of ANN and LR were assessed based on area under the curve (AUC) measures of receiver operator characteristic curves and Brier score.

Results

ANN had a significantly higher AUC (0.892) of post-operative prediction and AUC (0.808) of pre-operative prediction than LR (both P<0.0001). In addition, there was significant higher AUC of post-operative prediction than pre-operative prediction by ANN (p<0.0001). With the highest AUC and the lowest Brier score (0.090), the post-operative prediction by ANN had the highest overall predictive performance.

Conclusion

The post-operative prediction by ANN had the highest overall performance in predicting SSI after free-flap reconstruction in patients receiving surgery for head and neck cancer.

Motor Skills as Moderators of Core Symptoms in Autism Spectrum Disorders: Preliminary Data From an Exploratory Analysis With Artificial Neural Networks

Motor disturbances have been widely observed in children with autism spectrum disorder (ASD), and motor problems are currently reported as associated features supporting the diagnosis of ASD in the current Diagnostic and Statistical Manual of Mental Disorders (DSM-5). Studies on this issue reported disturbances in different motor domains, including both gross and fine motor areas as well as coordination, postural control, and standing balance. However, they failed to clearly state whether motor impairments are related to demographical and developmental features of ASD. Both the different methodological approaches assessing motor skills and the heterogeneity in clinical features of participants analyzed have been implicated as contributors to variance in findings. However, the non-linearity of the relationships between variables may account for the inability of the traditional analysis to grasp the core problem suggesting that the "single symptom approach analysis" should be overcome. Artificial neural networks (ANNs) are computational adaptive systems inspired by the functioning processes of the human brain particularly adapted to solving non-linear problems. This study aimed to apply the ANNs to reveal the entire spectrum of the relationship between motor skills and clinical variables. Thirty-two male children with ASD [mean age: 48.5 months (SD: 8.8); age range: 30-60 months] were recruited in a tertiary care university hospital. A multidisciplinary comprehensive diagnostic evaluation was associated with a standardized assessment battery for motor skills, the Peabody Developmental Motor Scale-Second Edition. Exploratory analyses were performed through the ANNs. The findings revealed that poor motor skills were a common clinical feature of preschoolers with ASD, relating both to the high level of repetitive behaviors and to the low level of expressive language. Moreover, unobvious trends among motor, cognitive and social skills have been detected. In conclusion, motor abnormalities in preschoolers with ASD were widespread, and the degree of impairment may inform clinicians about the severity of ASD core symptoms. Understanding motor disturbances in children with ASD may be relevant to clarify neurobiological basis and ultimately to guide the development of tailored treatments.

Novel Screening Tool for Stroke Using Artificial Neural Network

Background and Purpose—

The timely diagnosis of stroke at the initial examination is extremely important given the disease morbidity and narrow time window for intervention. The goal of this study was to develop a supervised learning method to recognize acute cerebral ischemia (ACI) and differentiate that from stroke mimics in an emergency setting.

Methods—

Consecutive patients presenting to the emergency department with stroke-like symptoms, within 4.5 hours of symptoms onset, in 2 tertiary care stroke centers were randomized for inclusion in the model. We developed an artificial neural network (ANN) model. The learning algorithm was based on backpropagation. To validate the model, we used a 10-fold cross-validation method.

Results—

A total of 260 patients (equal number of stroke mimics and ACIs) were enrolled for the development and validation of our ANN model. Our analysis indicated that the average sensitivity and specificity of ANN for the diagnosis of ACI based on the 10-fold cross-validation analysis was 80.0% (95% confidence interval, 71.8–86.3) and 86.2% (95% confidence interval, 78.7–91.4), respectively. The median precision of ANN for the diagnosis of ACI was 92% (95% confidence interval, 88.7–95.3).

Conclusions—

Our results show that ANN can be an effective tool for the recognition of ACI and differentiation of ACI from stroke mimics at the initial examination.

Nodular Thyroid Disease and Thyroid Cancer in the Era of Precision Medicine

The management of thyroid nodules, one of the main clinical challenges in endocrine clinical practice, is usually straightforward. Although the most important concern is ruling out malignancy, there are grey areas where uncertainty is frequently present: the nodules labelled as indeterminate by cytology and the extent of therapy when thyroid cancer is diagnosed pathologically. There is evidence that the current available precision medicine tools (from all the "-omics" to molecular analysis, fine-tuning imaging or artificial intelligence) may help to fill present gaps in the future. We present here a commentary on some of the current challenges faced by endocrinologists in the field of thyroid nodules and cancer, and illustrate how precision medicine may improve their diagnostic and therapeutic capabilities in the future.

Artificial Neural Network for Total Laboratory Automation to Improve the Management of Sample Dilution

Diluting a sample to obtain a measure within the analytical range is a common task in clinical laboratories. However, for urgent samples, it can cause delays in test reporting, which can put patients' safety at risk. The aim of this work is to show a simple artificial neural network that can be used to make it unnecessary to predilute a sample using the information available through the laboratory information system. Particularly, the Multilayer Perceptron neural network built on a data set of 16,106 cardiac troponin I test records produced a correct inference rate of 100% for samples not requiring predilution and 86.2% for those requiring predilution. With respect to the inference reliability, the most relevant inputs were the presence of a cardiac event or surgery and the result of the previous assay. Therefore, such an artificial neural network can be easily implemented into a total automation framework to sensibly reduce the turnaround time of critical orders delayed by the operation required to retrieve, dilute, and retest the sample.

Sequence homolog-based molecular engineering for shifting the enzymatic pH optimum

Cell-free synthetic biology system organizes multiple enzymes (parts) from different sources to implement unnatural catalytic functions. Highly adaption between the catalytic parts is crucial for building up efficient artificial biosynthetic systems. Protein engineering is a powerful technology to tailor various enzymatic properties including catalytic efficiency, substrate specificity, temperature adaptation and even achieve new catalytic functions. However, altering enzymatic pH optimum still remains a challenging task. In this study, we proposed a novel sequence homolog-based protein engineering strategy for shifting the enzymatic pH optimum based on statistical analyses of sequence-function relationship data of enzyme family. By two statistical procedures, artificial neural networks (ANNs) and least absolute shrinkage and selection operator (Lasso), five amino acids in GH11 xylanase family were identified to be related to the evolution of enzymatic pH optimum. Site-directed mutagenesis of a thermophilic xylanase from Caldicellulosiruptor bescii revealed that four out of five mutations could alter the enzymatic pH optima toward acidic condition without compromising the catalytic activity and thermostability. Combination of the positive mutants resulted in the best mutant M31 that decreased its pH optimum for 1.5 units and showed increased catalytic activity at pH < 5.0 compared to the wild-type enzyme. Structure analysis revealed that all the mutations are distant from the active center, which may be difficult to be identified by conventional rational design strategy. Interestingly, the four mutation sites are clustered at a certain region of the enzyme, suggesting a potential "hot zone" for regulating the pH optima of xylanases. This study provides an efficient method of modulating enzymatic pH optima based on statistical sequence analyses, which can facilitate the design and optimization of suitable catalytic parts for the construction of complicated cell-free synthetic biology systems.

Prediction of Clinical Deterioration in Hospitalized Adult Patients with Hematologic Malignancies Using a Neural Network Model

Introduction

Clinical deterioration (ICU transfer and cardiac arrest) occurs during approximately 5–10% of hospital admissions. Existing prediction models have a high false positive rate, leading to multiple false alarms and alarm fatigue. We used routine vital signs and laboratory values obtained from the electronic medical record (EMR) along with a machine learning algorithm called a neural network to develop a prediction model that would increase the predictive accuracy and decrease false alarm rates.

Design

Retrospective cohort study.

Setting

The hematologic malignancy unit in an academic medical center in the United States.

Patient Population

Adult patients admitted to the hematologic malignancy unit from 2009 to 2010.

Intervention

None.

Measurements and Main Results

Vital signs and laboratory values were obtained from the electronic medical record system and then used as predictors (features). A neural network was used to build a model to predict clinical deterioration events (ICU transfer and cardiac arrest). The performance of the neural network model was compared to the VitalPac Early Warning Score (ViEWS). Five hundred sixty five consecutive total admissions were available with 43 admissions resulting in clinical deterioration. Using simulation, the neural network outperformed the ViEWS model with a positive predictive value of 82% compared to 24%, respectively.

Conclusion

We developed and tested a neural network-based prediction model for clinical deterioration in patients hospitalized in the hematologic malignancy unit. Our neural network model outperformed an existing model, substantially increasing the positive predictive value, allowing the clinician to be confident in the alarm raised. This system can be readily implemented in a real-time fashion in existing EMR systems.

The importance of physicochemical characteristics and nonlinear classifiers in determining HIV-1 protease specificity

This paper reviews recent research relating to the application of bioinformatics approaches to determining HIV-1 protease specificity, outlines outstanding issues, and presents a new approach to addressing these issues. Leading machine learning theory for the problem currently suggests that the direct encoding of the physicochemical properties of the amino acid substrates is not required for optimal performance. A number of amino acid encoding approaches which incorporate potentially relevant physicochemical properties of the substrate are identified, and are evaluated using a nonlinear task decomposition based neuroevolution algorithm. The results are evaluated, and compared against a recent benchmark set on a nonlinear classifier using only amino acid sequence and identity information. Ensembles of these nonlinear classifiers using the physicochemical properties of the substrate are demonstrated to consistently outperform the recently published state-of-the-art linear support vector machine based approach in out-of-sample evaluations.

The optimization of Marasmius androsaceus submerged fermentation conditions in five-liter fermentor

Using desirability function, four indexes including mycelium dry weight, intracellular polysaccharide, adenosine and mannitol yield were uniformed into one expected value (Da) which further served as the assessment criteria. In our present study, Plackett-Burman design was applied to evaluate the effects of eight variables including initial pH, rotating speed, culture temperature, inoculum size, ventilation volume, culture time, inoculum age and loading volume on Da value during Marasmius androsaceus submerged fermentation via a five-liter fermentor. Culture time, initial pH and rotating speed were found to influence Da value significantly and were further optimized by Box-Behnken design. Results obtained from Box-Behnken design were analyzed by both response surface regression (Design-Expert.V8.0.6.1 software) and artificial neural network combining the genetic algorithm method (Matlab2012a software). After comparison, the optimum M. androsaceus submerged fermentation conditions via a five-liter fermentor were obtained as follows: initial pH of 6.14, rotating speed of 289.3 rpm, culture time of 6.285 days, culture temperature of 26 °C, inoculum size of 5%, ventilation volume of 200 L/h, inoculum age of 4 days, and loading volume of 3.5 L/5 L. The predicted Da value of the optimum model was 0.4884 and the average experimental Da value was 0.4760. The model possesses well fitness and predictive ability.

Under the microscope: From pathogens to probiotics and back

The review centers on the human gastrointestinal tract; focusing first on the bacterial stress responses needed to overcome the physiochemical defenses of the host, specifically how these stress survival strategies can be used as targets for alternative infection control strategies. The concluding section focuses on recent developments in molecular diagnostics; centring on the shifting paradigm from culture to molecular based diagnostics.

Predicting outcomes in patients with perforated gastroduodenal ulcers: artificial neural network modelling indicates a highly complex disease

Purpose

Mortality prediction models for patients with perforated peptic ulcer (PPU) have not yielded consistent or highly accurate results. Given the complex nature of this disease, which has many non-linear associations with outcomes, we explored artificial neural networks (ANNs) to predict the complex interactions between the risk factors of PPU and death among patients with this condition.

Methods

ANN modelling using a standard feed-forward, back-propagation neural network with three layers (i.e., an input layer, a hidden layer and an output layer) was used to predict the 30-day mortality of consecutive patients from a population-based cohort undergoing surgery for PPU. A receiver-operating characteristic (ROC) analysis was used to assess model accuracy.

Results

Of the 172 patients, 168 had their data included in the model; the data of 117 (70 %) were used for the training set, and the data of 51 (39 %) were used for the test set. The accuracy, as evaluated by area under the ROC curve (AUC), was best for an inclusive, multifactorial ANN model (AUC 0.90, 95 % CIs 0.85–0.95; p < 0.001). This model outperformed standard predictive scores, including Boey and PULP. The importance of each variable decreased as the number of factors included in the ANN model increased.

Conclusions

The prediction of death was most accurate when using an ANN model with several univariate influences on the outcome. This finding demonstrates that PPU is a highly complex disease for which clinical prognoses are likely difficult. The incorporation of computerised learning systems might enhance clinical judgments to improve decision making and outcome prediction.