The application of naive Bayes model averaging to predict Alzheimer's disease from genome-wide data

Objective

Predicting patient outcomes from genome-wide measurements holds significant promise for improving clinical care. The large number of measurements (eg, single nucleotide polymorphisms (SNPs)), however, makes this task computationally challenging. This paper evaluates the performance of an algorithm that predicts patient outcomes from genome-wide data by efficiently model averaging over an exponential number of naive Bayes (NB) models.

Design

This model-averaged naive Bayes (MANB) method was applied to predict late onset Alzheimer''s disease in 1411 individuals who each had 312 318 SNP measurements available as genome-wide predictive features. Its performance was compared to that of a naive Bayes algorithm without feature selection (NB) and with feature selection (FSNB).

Measurement

Performance of each algorithm was measured in terms of area under the ROC curve (AUC), calibration, and run time.

Results

The training time of MANB (16.1 s) was fast like NB (15.6 s), while FSNB (1684.2 s) was considerably slower. Each of the three algorithms required less than 0.1 s to predict the outcome of a test case. MANB had an AUC of 0.72, which is significantly better than the AUC of 0.59 by NB (p<0.00001), but not significantly different from the AUC of 0.71 by FSNB. MANB was better calibrated than NB, and FSNB was even better in calibration. A limitation was that only one dataset and two comparison algorithms were included in this study.

Conclusion

MANB performed comparatively well in predicting a clinical outcome from a high-dimensional genome-wide dataset. These results provide support for including MANB in the methods used to predict outcomes from large, genome-wide datasets.     

Toward personalizing treatment for depression: predicting diagnosis and severity

Objective

Depression is a prevalent disorder difficult to diagnose and treat. In particular, depressed patients exhibit largely unpredictable responses to treatment. Toward the goal of personalizing treatment for depression, we develop and evaluate computational models that use electronic health record (EHR) data for predicting the diagnosis and severity of depression, and response to treatment.

Materials and methods

We develop regression-based models for predicting depression, its severity, and response to treatment from EHR data, using structured diagnosis and medication codes as well as free-text clinical reports. We used two datasets: 35 000 patients (5000 depressed) from the Palo Alto Medical Foundation and 5651 patients treated for depression from the Group Health Research Institute.

Results

Our models are able to predict a future diagnosis of depression up to 12 months in advance (area under the receiver operating characteristic curve (AUC) 0.70–0.80). We can differentiate patients with severe baseline depression from those with minimal or mild baseline depression (AUC 0.72). Baseline depression severity was the strongest predictor of treatment response for medication and psychotherapy.

Conclusions

It is possible to use EHR data to predict a diagnosis of depression up to 12 months in advance and to differentiate between extreme baseline levels of depression. The models use commonly available data on diagnosis, medication, and clinical progress notes, making them easily portable. The ability to automatically determine severity can facilitate assembly of large patient cohorts with similar severity from multiple sites, which may enable elucidation of the moderators of treatment response in the future.     

An improved model for predicting postoperative nausea and vomiting in ambulatory surgery patients using physician-modifiable risk factors

Objective

Postoperative nausea and vomiting (PONV) is a frequent complication in patients undergoing ambulatory surgery, with an incidence of 20%–65%. A predictive model can be utilized for decision support and feedback for practitioner practice improvement. The goal of this study was to develop a better model to predict the patient''s risk for PONV by incorporating both non-modifiable patient characteristics and modifiable practitioner-specific anesthetic practices.

Materials and methods

Data on 2505 ambulatory surgery cases were prospectively collected at an academic center. Sixteen patient-related, surgical, and anesthetic predictors were used to develop a logistic regression model. The experimental model (EM) was compared against the original Apfel model (OAM), refitted Apfel model (RAM), simplified Apfel risk score (SARS), and refitted Sinclair model (RSM) by examining the discriminating power calculated using area under the curve (AUC) and by examining calibration curves.

Results

The EM contained 11 input variables. The AUC was 0.738 for the EM, 0.620 for the OAM, 0.629 for the RAM, 0.626 for the SARS, and 0.711 for the RSM. Pair-wise discrimination comparison of models showed statistically significant differences (p<0.05) in AUC between the EM and all other models, OAM and RSM, RAM and RSM, and SARS and RSM.

Discussion

All models except the OAM appeared to have good calibration for our institution''s ambulatory surgery data. Ours is the first model to break down risk by anesthetic technique and incorporate risk reduction due to PONV prophylaxis.

Conclusion

The EM showed statistically significant improved discrimination over existing models and good calibration. However, the EM should be validated at another institution.     

Hepatoprotective activity of Hepax-A polyherbal formulation

Objective

To evaluate the hepatoprotective potential of Hepax, a polyherbal formulation, against three experimentally induced hepatotoxicity models in rats.

Methods

Hepatoprotective activity of Hepax was studied against three experimentally induced hepatotoxicity models, namely, carbon tetrachloride (CCl₄), paracetamol and thiocetamide induced hepatotoxicity in rats.

Results

Administration of hepatotoxins (CCl₄, paracetamol and thiocetamide) showed significant morphological, biochemical and histological deteriorations in the liver of experimental animals. Pretreatment with Hepax had significant protection against hepatic damage by maintaining the morphological parameters (liver weight and liver weight to organ weight ratio) within normal range and normalizing the elevated levels of biochemical parameters (SGPT, SGOT, ALP and total bilirubin), which were evidently showed in histopathological study.

Conclusions

The Hepax has highly significant hepatoprotective effect at 100 and 200 mg/kg, p.o. on the liver of all the three experimental animal models.     

Machine learning-based coreference resolution of concepts in clinical documents

Objective

Coreference resolution of concepts, although a very active area in the natural language processing community, has not yet been widely applied to clinical documents. Accordingly, the 2011 i2b2 competition focusing on this area is a timely and useful challenge. The objective of this research was to collate coreferent chains of concepts from a corpus of clinical documents. These concepts are in the categories of person, problems, treatments, and tests.

Design

A machine learning approach based on graphical models was employed to cluster coreferent concepts. Features selected were divided into domain independent and domain specific sets. Training was done with the i2b2 provided training set of 489 documents with 6949 chains. Testing was done on 322 documents.

Results

The learning engine, using the un-weighted average of three different measurement schemes, resulted in an F measure of 0.8423 where no domain specific features were included and 0.8483 where the feature set included both domain independent and domain specific features.

Conclusion

Our machine learning approach is a promising solution for recognizing coreferent concepts, which in turn is useful for practical applications such as the assembly of problem and medication lists from clinical documents.     

Active learning for clinical text classification: is it better than random sampling?

Objective

This study explores active learning algorithms as a way to reduce the requirements for large training sets in medical text classification tasks.

Design

Three existing active learning algorithms (distance-based (DIST), diversity-based (DIV), and a combination of both (CMB)) were used to classify text from five datasets. The performance of these algorithms was compared to that of passive learning on the five datasets. We then conducted a novel investigation of the interaction between dataset characteristics and the performance results.

Measurements

Classification accuracy and area under receiver operating characteristics (ROC) curves for each algorithm at different sample sizes were generated. The performance of active learning algorithms was compared with that of passive learning using a weighted mean of paired differences. To determine why the performance varies on different datasets, we measured the diversity and uncertainty of each dataset using relative entropy and correlated the results with the performance differences.

Results

The DIST and CMB algorithms performed better than passive learning. With a statistical significance level set at 0.05, DIST outperformed passive learning in all five datasets, while CMB was found to be better than passive learning in four datasets. We found strong correlations between the dataset diversity and the DIV performance, as well as the dataset uncertainty and the performance of the DIST algorithm.

Conclusion

For medical text classification, appropriate active learning algorithms can yield performance comparable to that of passive learning with considerably smaller training sets. In particular, our results suggest that DIV performs better on data with higher diversity and DIST on data with lower uncertainty.     

Cognitive work analysis to evaluate the problem of patient falls in an inpatient setting

Objective

To identify factors in the nursing work domain that contribute to the problem of inpatient falls, aside from patient risk, using cognitive work analysis.

Design

A mix of qualitative and quantitative methods were used to identify work constraints imposed on nurses, which may underlie patient falls.

Measurements

Data collection was done on a neurology unit staffed by 27 registered nurses and utilized field observations, focus groups, time–motion studies and written surveys (AHRQ Hospital Survey on Patient Culture, NASA-TLX, and custom Nursing Knowledge of Fall Prevention Subscale).

Results

Four major constraints were identified that inhibit nurses'' ability to prevent patient falls. All constraints relate to work processes and the physical work environment, opposed to safety culture or nursing knowledge, as currently emphasized. The constraints were: cognitive ‘head data’, temporal workload, inconsistencies in written and verbal transfer of patient data, and limitations in the physical environment. To deal with these constraints, the nurses tend to employ four workarounds: written and mental chunking schemas, bed alarms, informal querying of the previous care nurse, and informal video and audio surveillance. These workarounds reflect systemic design flaws and may only be minimally effective in decreasing risk to patients.

Conclusion

Cognitive engineering techniques helped identify seemingly hidden constraints in the work domain that impact the problem of patient falls. System redesign strategies aimed at improving work processes and environmental limitations hold promise for decreasing the incidence of falls in inpatient nursing units.     

Comparing Medline citations using modified N-grams

Objective

We aim to identify duplicate pairs of Medline citations, particularly when the documents are not identical but contain similar information.

Materials and methods

Duplicate pairs of citations are identified by comparing word n-grams in pairs of documents. N-grams are modified using two approaches which take account of the fact that the document may have been altered. These are: (1) deletion, an item in the n-gram is removed; and (2) substitution, an item in the n-gram is substituted with a similar term obtained from the Unified Medical Language System  Metathesaurus. N-grams are also weighted using a score derived from a language model. Evaluation is carried out using a set of 520 Medline citation pairs, including a set of 260 manually verified duplicate pairs obtained from the Deja Vu database.

Results

The approach accurately detects duplicate Medline document pairs with an F₁ measure score of 0.99. Allowing for word deletions and substitution improves performance. The best results are obtained by combining scores for n-grams of length 1–5 words.

Discussion

Results show that the detection of duplicate Medline citations can be improved by modifying n-grams and that high performance can also be obtained using only unigrams (F₁=0.959), particularly when allowing for substitutions of alternative phrases.     

Use of a support vector machine for categorizing free-text notes: assessment of accuracy across two institutions

Background

Electronic health record (EHR) users must regularly review large amounts of data in order to make informed clinical decisions, and such review is time-consuming and often overwhelming. Technologies like automated summarization tools, EHR search engines and natural language processing have been shown to help clinicians manage this information.

Objective

To develop a support vector machine (SVM)-based system for identifying EHR progress notes pertaining to diabetes, and to validate it at two institutions.

Materials and methods

We retrieved 2000 EHR progress notes from patients with diabetes at the Brigham and Women''s Hospital (1000 for training and 1000 for testing) and another 1000 notes from the University of Texas Physicians (for validation). We manually annotated all notes and trained a SVM using a bag of words approach. We then used the SVM on the testing and validation sets and evaluated its performance with the area under the curve (AUC) and F statistics.

Results

The model accurately identified diabetes-related notes in both the Brigham and Women''s Hospital testing set (AUC=0.956, F=0.934) and the external University of Texas Faculty Physicians validation set (AUC=0.947, F=0.935).

Discussion

Overall, the model we developed was quite accurate. Furthermore, it generalized, without loss of accuracy, to another institution with a different EHR and a distinct patient and provider population.

Conclusions

It is possible to use a SVM-based classifier to identify EHR progress notes pertaining to diabetes, and the model generalizes well.     

Clinical research data warehouse governance for distributed research networks in the USA: a systematic review of the literature

Objective

To review the published, peer-reviewed literature on clinical research data warehouse governance in distributed research networks (DRNs).

Materials and methods

Medline, PubMed, EMBASE, CINAHL, and INSPEC were searched for relevant documents published through July 31, 2013 using a systematic approach. Only documents relating to DRNs in the USA were included. Documents were analyzed using a classification framework consisting of 10 facets to identify themes.

Results

6641 documents were retrieved. After screening for duplicates and relevance, 38 were included in the final review. A peer-reviewed literature on data warehouse governance is emerging, but is still sparse. Peer-reviewed publications on UK research network governance were more prevalent, although not reviewed for this analysis. All 10 classification facets were used, with some documents falling into two or more classifications. No document addressed costs associated with governance.

Discussion

Even though DRNs are emerging as vehicles for research and public health surveillance, understanding of DRN data governance policies and procedures is limited. This is expected to change as more DRN projects disseminate their governance approaches as publicly available toolkits and peer-reviewed publications.

Conclusions

While peer-reviewed, US-based DRN data warehouse governance publications have increased, DRN developers and administrators are encouraged to publish information about these programs.     

Antioxidant and cytotoxic activity of Acanthus ilicifolius flower

Objective

To investigate the antioxidant and cytotoxic activity of the flower of Acanthus ilicifolius (A. ilicifolius).

Methods

Antioxidant activity was determined as antiradical efficiency with diphenyl picrylhydrazil (DPPH) method and cytotoxic assay was undertaken using brine shrimp lethal toxicity test.

Results

A. ilicifolius flower contained terpenoid, phenolic compounds, and alkaloid. The methanol extract of A. ilicifolius flower showed the highest antiradical efficiency (AE=1.41×10⁻³) against DPPH radicals and the highest cytotoxicity (LC₅₀=22 µg/mL) against brine shrimp nauplii.

Conclusions

It is suggested that active compounds of A. ilicifolius flower solved in methanol play a role to inhibit free radical activity and kill Artemia salina nauplii. The substances can be considered as potential antioxidant and cytotoxic agents as well as imminent candidate for cancer therapy.     

Hesperidin as a preventive resistance agent in MCF-7 breast cancer cells line resistance to doxorubicin

Objective

To evaluate of hesperidin to overcome resistance of doxorubicin in MCF-7 resistant doxorubicin cells (MCF-7/Dox) in cytotoxicity apoptosis and P-glycoprotein (Pgp) expression in combination with doxorubicin.

Methods

The cytotoxic properties, 50% inhibition concentration (IC₅₀) and its combination with doxorubicin in MCF-7 cell lines resistant to doxorubicin (MCF-7/Dox) cells were determined using MTT assay. Apoptosis induction was examined by double staining assay using ethidium bromide-acridine orange. Immunocytochemistry assay was performed to determine the level and localization of Pgp.

Results

Single treatment of hesperidin showed cytotoxic activity on MCF-7/Dox cells with IC₅₀ value of 11 µmol/L. Thus, combination treatment from hesperidin and doxorubicin showed addictive and antagonist effect (CI>1.0). Hesperidin did not increase the apoptotic induction, but decreased the Pgp expressions level when combined with doxorubicin in low concentration.

Conclusions

Hesperidin has cytotoxic effect on MCF-7/Dox cells with IC₅₀ of 11 µmol/L. Hesperidin did not increased the apoptotic induction combined with doxorubicin. Co-chemotherapy application of doxorubicin and hesperidin on MCF-7/Dox cells showed synergism effect through inhibition of Pgp expression.     

The impact of an electronic health record on nurse sensitive patient outcomes: an interrupted time series analysis

Objectives

To evaluate the impact of electronic health record (EHR) implementation on nursing care processes and outcomes.

Design

Interrupted time series analysis, 2003–2009.

Setting

A large US not-for-profit integrated health care organization.

Participants

29 hospitals in Northern and Southern California.

Intervention

An integrated EHR including computerized physician order entry, nursing documentation, risk assessment tools, and documentation tools.

Main outcome measures

Percentage of patients with completed risk assessments for hospital acquired pressure ulcers (HAPUs) and falls (process measures) and rates of HAPU and falls (outcome measures).

Results

EHR implementation was significantly associated with an increase in documentation rates for HAPU risk (coefficient 2.21, 95% CI 0.67 to 3.75); the increase for fall risk was not statistically significant (0.36; −3.58 to 4.30). EHR implementation was associated with a 13% decrease in HAPU rates (coefficient −0.76, 95% CI −1.37 to −0.16) but no decrease in fall rates (−0.091; −0.29 to 0.11). Irrespective of EHR implementation, HAPU rates decreased significantly over time (−0.16; −0.20 to −0.13), while fall rates did not (0.0052; −0.01 to 0.02). Hospital region was a significant predictor of variation for both HAPU (0.72; 0.30 to 1.14) and fall rates (0.57; 0.41 to 0.72).

Conclusions

The introduction of an integrated EHR was associated with a reduction in the number of HAPUs but not in patient fall rates. Other factors, such as changes over time and hospital region, were also associated with variation in outcomes. The findings suggest that EHR impact on nursing care processes and outcomes is dependent on a number of factors that should be further explored.     

Isolation of a small molecule with anti-MRSA activity from a mangrove symbiont Streptomyces sp. PVRK-1 and its biomedical studies in Zebrafish embryos

Objective

The aim of the present study was to isolate the anti-MRSA (Methicillin Resistant Staphylococcus aureus) molecule from the Mangrove symbiont Streptomyces and its biomedical studies in Zebrafish embryos.

Methods

MRSA was isolated from the pus samples of Colachal hospitals and confirmed by amplification of mecA gene. Anti-MRSA molecule producing strain was identified by 16s rRNA gene sequencing. Anti-MRSA compound production was optimized by Solid State Fermentation (SSF) and the purification of the active molecule was carried out by TLC and RP-HPLC. The inhibitory concentration and LC₅₀ were calculated using Statistical software SPSS. The Biomedical studies including the cardiac assay and organ toxicity assessment were carried out in Zebrafish.

Results

The bioactive anti-MRSA small molecule A₂ was purified by TLC with Rf value of 0.37 with 1.389 retention time at RP-HPLC. The Inhibitory Concentration of the purified molecule A₂ was 30 µg/mL but, the inhibitory concentration of the MRSA in the infected embryo was 32-34 µg/mL for TLC purified molecule A₂ with LC₅₀ mean value was 61.504 µg/mL. Zebrafish toxicity was assessed in 48-60 µg/mL by observing the physiological deformities and the heart beat rates (HBR) of embryos for anti MRSA molecule showed the mean of 41.33-41.67 HBR/15 seconds for 40 µg/mL and control was 42.33-42.67 for 15 seconds which significantly showed that the anti-MRSA molecule A₂ did not affected the HBR.

Conclusions

Anti-MRSA molecule from Streptomyces sp PVRK-1 was isolated and biomedical studies in Zebrafish model assessed that the molecule was non toxic at the minimal inhibitory concentration of MRSA.     

Quantifying clinical narrative redundancy in an electronic health record

Objective

Although electronic notes have advantages compared to handwritten notes, they take longer to write and promote information redundancy in electronic health records (EHRs). We sought to quantify redundancy in clinical documentation by studying collections of physician notes in an EHR.

Design and methods

We implemented a retrospective design to gather all electronic admission, progress, resident signout and discharge summary notes written during 100 randomly selected patient admissions within a 6 month period. We modified and applied a Levenshtein edit-distance algorithm to align and compare the documents written for each of the 100 admissions. We then identified and measured the amount of text duplicated from previous notes. Finally, we manually reviewed the content that was conserved between note types in a subsample of notes.

Measurements

We measured the amount of new information in a document, which was calculated as the number of words that did not match with previous documents divided by the length, in words, of the document. Results are reported as the percentage of information in a document that had been duplicated from previously written documents.

Results

Signout and progress notes proved to be particularly redundant, with an average of 78% and 54% information duplicated from previous documents respectively. There was also significant information duplication between document types (eg, from an admission note to a progress note).

Conclusion

The study established the feasibility of exploring redundancy in the narrative record with a known sequence alignment algorithm used frequently in the field of bioinformatics. The findings provide a foundation for studying the usefulness and risks of redundancy in the EHR.     

Optimal Training Sets for Bayesian Prediction of MeSH? Assignment

Objectives

The aim of this study was to improve naïve Bayes prediction of Medical Subject Headings (MeSH) assignment to documents using optimal training sets found by an active learning inspired method.

Design

The authors selected 20 MeSH terms whose occurrences cover a range of frequencies. For each MeSH term, they found an optimal training set, a subset of the whole training set. An optimal training set consists of all documents including a given MeSH term (C ₁ class) and those documents not including a given MeSH term (C ₋₁ class) that are closest to the C ₁ class. These small sets were used to predict MeSH assignments in the MEDLINE^® database.

Measurements

Average precision was used to compare MeSH assignment using the naïve Bayes learner trained on the whole training set, optimal sets, and random sets. The authors compared 95% lower confidence limits of average precisions of naïve Bayes with upper bounds for average precisions of a K-nearest neighbor (KNN) classifier.

Results

For all 20 MeSH assignments, the optimal training sets produced nearly 200% improvement over use of the whole training sets. In 17 of those MeSH assignments, naïve Bayes using optimal training sets was statistically better than a KNN. In 15 of those, optimal training sets performed better than optimized feature selection. Overall naïve Bayes averaged 14% better than a KNN for all 20 MeSH assignments. Using these optimal sets with another classifier, C-modified least squares (CMLS), produced an additional 6% improvement over naïve Bayes.

Conclusion

Using a smaller optimal training set greatly improved learning with naïve Bayes. The performance is superior to a KNN. The small training set can be used with other sophisticated learning methods, such as CMLS, where using the whole training set would not be feasible.     

Biofabrication of Ag nanoparticles using Moringa oleifera leaf extract and their antimicrobial activity

Objective

To formulate a simple rapid procedure for bioreduction of silver nanoparticles using aqueous leaves extract of Moringa oleifera (M. oleifera).

Methods

10 mL of leaf extract was mixed to 90 mL of 1 mM aqueous of AgNO₃ and was heated at 60 - 80 °C for 20 min. A change from brown to reddish color was observed. Characterization using UV-Vis spectrophotometry, Transmission Electron Microscopy (TEM) was performed.

Results

TEM showed the formation of silver nanoparticles with an average size of 57 nm.

Conclusions

M. oleifera demonstrates strong potential for synthesis of silver nanoparticles by rapid reduction of silver ions (Ag⁺ to Ag⁰). Biological methods are good competents for the chemical procedures, which are eco-friendly and convenient.     

BoB,a best-of-breed automated text de-identification system for VHA clinical documents

Objective

De-identification allows faster and more collaborative clinical research while protecting patient confidentiality. Clinical narrative de-identification is a tedious process that can be alleviated by automated natural language processing methods. The goal of this research is the development of an automated text de-identification system for Veterans Health Administration (VHA) clinical documents.

Materials and methods

We devised a novel stepwise hybrid approach designed to improve the current strategies used for text de-identification. The proposed system is based on a previous study on the best de-identification methods for VHA documents. This best-of-breed automated clinical text de-identification system (aka BoB) tackles the problem as two separate tasks: (1) maximize patient confidentiality by redacting as much protected health information (PHI) as possible; and (2) leave de-identified documents in a usable state preserving as much clinical information as possible.

Results

We evaluated BoB with a manually annotated corpus of a variety of VHA clinical notes, as well as with the 2006 i2b2 de-identification challenge corpus. We present evaluations at the instance- and token-level, with detailed results for BoB''s main components. Moreover, an existing text de-identification system was also included in our evaluation.

Discussion

BoB''s design efficiently takes advantage of the methods implemented in its pipeline, resulting in high sensitivity values (especially for sensitive PHI categories) and a limited number of false positives.

Conclusions

Our system successfully addressed VHA clinical document de-identification, and its hybrid stepwise design demonstrates robustness and efficiency, prioritizing patient confidentiality while leaving most clinical information intact.