PPAD: a deep learning architecture to predict progression of Alzheimer's disease.

MOTIVATION: Alzheimer's disease (AD) is a neurodegenerative disease that affects millions of people worldwide. Mild cognitive impairment (MCI) is an intermediary stage between cognitively normal state and AD. Not all people who have MCI convert to AD. The diagnosis of AD is made after significant symptoms of dementia such as short-term memory loss are already present. Since AD is currently an irreversible disease, diagnosis at the onset of the disease brings a huge burden on patients, their caregivers, and the healthcare sector. Thus, there is a crucial need to develop methods for the early prediction AD for patients who have MCI. Recurrent neural networks (RNN) have been successfully used to handle electronic health records (EHR) for predicting conversion from MCI to AD. However, RNN ignores irregular time intervals between successive events which occurs common in electronic health record data. In this study, we propose two deep learning architectures based on RNN, namely Predicting Progression of Alzheimer's Disease (PPAD) and PPAD-Autoencoder. PPAD and PPAD-Autoencoder are designed for early predicting conversion from MCI to AD at the next visit and multiple visits ahead for patients, respectively. To minimize the effect of the irregular time intervals between visits, we propose using age in each visit as an indicator of time change between successive visits. RESULTS: Our experimental results conducted on Alzheimer's Disease Neuroimaging Initiative and National Alzheimer's Coordinating Center datasets showed that our proposed models outperformed all baseline models for most prediction scenarios in terms of F2 and sensitivity. We also observed that the age feature was one of top features and was able to address irregular time interval problem. AVAILABILITY AND IMPLEMENTATION: https://github.com/bozdaglab/PPAD.

Description of Dissolved Organic Matter Transformational Networks at the Molecular Level.

Dissolved Organic Matter (DOM) is an important component of the global carbon cycle. Unscrambling the structural footprint of DOM is key to understand its biogeochemical transformations at the mechanistic level. Although numerous studies have improved our knowledge of DOM chemical makeup, its three-dimensional picture remains largely unrevealed. In this work, we compare four solid phase extracted (SPE) DOM samples from three different freshwater ecosystems using high resolution mobility and ultrahigh-resolution Fourier transform ion cyclotron resonance tandem mass spectrometry (FT-ICR MS/MS). Structural families were identified based on neutral losses at the level of nominal mass using continuous accumulation of selected ions-collision induced dissociation (CASI-CID)FT-ICR MS/MS. Comparison of the structural families indicated dissimilarities in the structural footprint of this sample set. The structural family representation using Cytoscape software revealed characteristic clustering patterns among the DOM samples, thus confirming clear differences at the structural level (Only 10% is common across the four samples.). The analysis at the level of neutral loss-based functionalities suggests that hydration and carboxylation are ubiquitous transformational processes across the three ecosystems. In contrast, transformation mechanisms involving methoxy moieties may be constrained in estuarine systems due to extensive upstream lignin biodegradation. The inclusion of the isomeric content (mobility measurements at the level of chemical formula) in the structural family description suggests that additional transformation pathways and/or source variations are possible and account for the dissimilarities observed. While the structural character of more and diverse types of DOM samples needs to be assessed and added to this database, the results presented here demonstrate that Graph-DOM is a powerful tool capable of providing novel information on the DOM chemical footprint, based on structural interconnections of precursor molecules generated by fragmentation pathways and collisional cross sections.

Unsupervised Structural Classification of Dissolved Organic Matter Based on Fragmentation Pathways.

Dissolved organic matter (DOM) is considered an essential component of the Earth's ecological and biogeochemical processes. Structural information of DOM components at the molecular level remains one of the most extraordinary analytical challenges. Advances in determination of chemical formulas from the molecular studies of DOM have provided limited indications on structural signatures and potential reaction pathways. In this work, we extend the structural characterization of a wetland DOM sample using precursor and fragment molecular ions obtained by a sequential electrospray ionization-Fourier transform-ion cyclotron resonance tandem mass spectrometry (ESI-FT-ICR CASI-CID MS/MS) approach. The DOM chemical complexity resulted in near 900 precursors (P) and 24 000 fragment (F) molecular ions over a small m/z 261-477 range. The DOM structural content was dissected into families of structurally connected precursors based on neutral mass loss patterns (Pn-1 + F1:n + C) across the two-dimensional (2D) MS/MS space. This workflow identified over 1900 structural families of DOM compounds based on a precursor and neutral loss (H2O, CH4O, and CO2). The inspection of structural families showed a high degree of isomeric content (numerous identical fragmentation pathways), not discriminable with sole precursor ion analysis. The connectivity map of structural families allows for the visualization of potential biogeochemical processes that DOM undergoes throughout its lifetime. This study illustrates that integrating effective computational tools on a comprehensive high-resolution mass fragmentation strategy further enables the DOM structural characterization.

Communication principles and practices for making shared decisions about renal replacement therapy: a review of the literature.

PURPOSE OF REVIEW: To provide an overview of the skill set required for communication and person-centered decision making for renal replacement therapy (RRT) choices, especially conservative kidney management (CKM). RECENT FINDINGS: Research on communication and decision-making skills for shared RRT decision making is still in infancy. We adapt literature from other fields such as primary care and oncology for effective RRT decision making. SUMMARY: We review seven key skills: (1) Announcing the need for decision making (2) Agenda Setting (3) Educating patients about RRT options (4) Discussing prognoses (5) Eliciting patient preferences (6) Responding to emotions and showing empathy, and (7) Investing in the end. We also provide example sentences to frame the conversations around RRT choices including CKM.

Frequency and Severity of Moral Distress in Nephrology Fellows: A National Survey.

INTRODUCTION: Moral distress is a negative affective response to a situation in which one is compelled to act in a way that conflicts with one's values. Little is known about the workplace scenarios that elicit moral distress in nephrology fellows. METHODS: We sent a moral distress survey to 148 nephrology fellowship directors with a request to forward it to their fellows. Using a 5-point (0-4) scale, fellows rated both the frequency (never to very frequently) and severity (not at all disturbing to very disturbing) of commonly encountered workplace scenarios. Ratings of ≥3 were used to define "frequent" and "moderate-to-severe" moral distress. RESULTS: The survey was forwarded by 64 fellowship directors to 386 fellows, 142 of whom (37%) responded. Their mean age was 33 ± 3.6 years and 43% were female. The scenarios that most commonly elicited moderate to severe moral distress were initiating dialysis in situations that the fellow considered futile (77%), continuing dialysis in a hopelessly ill patient (81%) and carrying a high patient census (75%), and observing other providers giving overly optimistic descriptions of the benefits of dialysis (64%). Approximately 27% had considered quitting fellowship during training, including 9% at the time of survey completion. CONCLUSION: A substantial majority of nephrology trainees experienced moral distress of moderate to severe intensity, mainly related to the futile treatment of hopelessly ill patients. Efforts to reduce moral distress in trainees are required.

Outcomes of palliative care consultation in patients with ESRD who received cardiopulmonary resuscitation.

BACKGROUND: The majority of dialysis patients receive aggressive burdensome treatment near the end of life. Currently, we lack interventions to improve end-of-life care (EoLC) for these patients. We examined the association of palliative care consultation with improving EoLC for critically ill patients with end-stage renal disease (ESRD) who received cardiopulmonary resuscitation (CPR). MATERIALS AND METHODS: In this retrospective study, we included patients with ESRD admitted to a large academic center who received CPR either prior to or during their hospital stay. Over 8 years, 17 out of 403 patients received palliative care consultation during their hospital stay; consultations were not standardized in their content. Main outcomes of interest to operationalize better EoLC were: (1) change in code status from full code to do not resuscitate (DNR) and (2) withdrawal from intensive care. RESULTS: Of the patients studied, 60.5% were African-American and 43.2% were female. Demographic differences between those with palliative care consultation and those with usual care were not statistically significant. Palliative care consultation was associated with higher odds of change in code status to DNR (odds ratio 8.10, 95% confidence interval 2.19 - 29.94) and withdrawal from intensive care (odds ratio 8.82, 95% confidence interval 2.69 - 28.91) in patients with ESRD who had received CPR. Palliative care consultation was not associated with any change in in-hospital mortality. CONCLUSION: Palliative care consultation needs to be considered for hospitalized ESRD patients with limited expected prognoses as it may reduce aggressive and burdensome therapies at the end of life. Furthermore, primary palliative care skills such as communication and decision-making should be taught to nephrologists to improve EoLC for dialysis patients.

NGS-Integrator: An efficient tool for combining multiple NGS data tracks using minimum Bayes' factors.

BACKGROUND: Next-generation sequencing (NGS) is widely used for genome-wide identification and quantification of DNA elements involved in the regulation of gene transcription. Studies that generate multiple high-throughput NGS datasets require data integration methods for two general tasks: 1) generation of genome-wide data tracks representing an aggregate of multiple replicates of the same experiment; and 2) combination of tracks from different experimental types that provide complementary information regarding the location of genomic features such as enhancers. RESULTS: NGS-Integrator is a Java-based command line application, facilitating efficient integration of multiple genome-wide NGS datasets. NGS-Integrator first transforms all input data tracks using the complement of the minimum Bayes' factor so that all values are expressed in the range [0,1] representing the probability of a true signal given the background noise. Then, NGS-Integrator calculates the joint probability for every genomic position to create an integrated track. We provide examples using real NGS data generated in our laboratory and from the mouse ENCODE database. CONCLUSIONS: Our results show that NGS-Integrator is both time- and memory-efficient. Our examples show that NGS-Integrator can integrate information to facilitate downstream analyses that identify functional regulatory domains along the genome.

Matters of Life and Death: Why Do Older Patients Choose Conservative Management?

BACKGROUND: Although many older patients with end-stage renal disease and limited prognoses prefer conservative management (CM), it is not widely offered in the United States. Moreover, there is a dearth of US-based literature reporting clinical experience with shared decision making regarding CM of advanced chronic kidney disease (CKD). METHODS: We describe the clinical experience of 13 patients who opted for CM at the University of Rochester Medical Center's CKD clinic during 2016-2017. Main outcomes include: (1) reason for choosing CM, (2) completion of advance directives, (3) location of death, and (4) utilization of hospice service. Patients' reasons for choosing CM were categorized into 4 broad categories based on a review of their electronic medical records. A retrospective chart review conducted by 2 reviewers determined the status of advance care planning, hospice referral, and place of death. RESULTS: The mean age of these patients was 81.8 years (SD 7.3). Their reasons for choosing CM included: poor prognoses; a wish to maintain their quality of life; their desire for a dignified life closure; and the intention to protect family members from having to see them suffer, based on their own memory of having witnessed a relative on dialysis previously. A total of 8 patients died: all received hospice services, 6 died at home, one at a nursing home, and one at a hospital. Advance care planning was completed in 100% of the cases. Symptoms were managed in collaboration with primary care physicians. CONCLUSION: Patients' decisions to choose CM were influenced by their values and previous experience with dialysis, in addition to comorbidities and limited prognoses. Promoting the choice of CM in the United States will require training of clinicians in primary palliative care competencies, including communication and decision-making skills, as well as basic symptom management proficiencies.

Patients' perspectives on dialysis decision-making and end-of-life care
.

BACKGROUND: Few studies have explored dialysis patients' perspectives on dialysis decision-making and end-of-life-care (EoLC) preferences. We surveyed a racially diverse cohort of maintenance dialysis patients in the Cleveland, OH, USA, metropolitan area. MATERIALS AND METHODS: In this cross-sectional study, we administered a 41-item questionnaire to 450 adult chronic dialysis patients. Items assessed patients' knowledge of their kidney disease as well as their attitudes toward chronic kidney disease (CKD) treatment issues and EoLC issues. RESULTS: The cohort included 67% Blacks, 27% Caucasians, 2.8% Hispanics, and 2.4% others. The response rate was 94% (423/450). Most patients considered it essential to obtain detailed information about their medical condition (80.6%) and prognosis (78.3%). Nearly 19% of respondents regretted their decision to start dialysis. 41% of patients would prefer treatment(s) aimed at relieving pain rather than prolonging life (30.5%), but a majority would want to be resuscitated (55.3%). Only 8.4% reported having a designated healthcare proxy, and 35.7% reported completing a living will. A significant percentage of patients wished to discuss their quality of life (71%), psychosocial and spiritual concerns (50.4%), and end-of-life issues (38%) with their nephrologist. CONCLUSION: Most dialysis patients wish to have more frequent discussions about their disease, prognosis, and EoLC planning. Findings from this study can inform the design of future interventions.
.

MaSS-Simulator: A Highly Configurable Simulator for Generating MS/MS Datasets for Benchmarking of Proteomics Algorithms.

Mass Spectrometry (MS)-based proteomics has become an essential tool in the study of proteins. With the advent of modern MS machines huge amounts of data is being generated, which can only be processed by novel algorithmic tools. However, in the absence of data benchmarks and ground truth datasets algorithmic integrity testing and reproducibility is a challenging problem. To this end, MaSS-Simulator has been presented, which is an easy to use simulator and can be configured to simulate MS/MS datasets for a wide variety of conditions with known ground truths. MaSS-Simulator offers many configuration options to allow the user a great degree of control over the test datasets, which can enable rigorous and large- scale testing of any proteomics algorithm. MaSS-Simulator is assessed by comparing its performance against experimentally generated spectra and spectra obtained from NIST collections of spectral library. The results show that MaSS-Simulator generated spectra match closely with real-spectra and have a relative-error distribution centered around 25%. In contrast, the theoretical spectra for same peptides have relative-error distribution centered around 150%. MaSS-Simulator will enable developers to specifically highlight the capabilities of their algorithms and provide a strong proof of any pitfalls they might face. Source code, executables, and a user manual for MaSS-Simulator can be downloaded from https://github.com/pcdslab/MaSS-Simulator.

National outcomes of in-hospital cardiopulmonary resuscitation in patients with acute kidney injury: years 2005 - 2011
.

BACKGROUND: There is paucity of data on the outcomes of in-hospital cardiopulmonary resuscitation (CPR) in patients with acute kidney injury (AKI). We analyzed the impact of acute kidney injury on in-hospital CPR-related outcomes. MATERIALS AND METHODS: We analyzed data from Nationwide Inpatient Sample (NIS 2005 - 2011) including patients with and without AKI who had undergone in-hospital CPR. Baseline characteristics, in-hospital complications and discharge outcomes were compared between the two groups. We determined the effect of AKI on length of hospital stay, discharge destination, hospital mortality, survival trends, and discharge to home. RESULTS: 180,970 patients with primary or secondary diagnosis of AKI underwent in-hospital CPR compared to 323,620 patients without AKI. Unadjusted in-hospital mortality rates were higher in the AKI group (78.2 vs. 71.8%, p < 0.0001). After adjusting for age, sex, and potential confounders, patients in the AKI group had higher odds of mortality with odds ratio 1.3, 95% confidence interval 1.2 - 1.4, p < 0.0001. Survivors in the AKI group were more likely to be discharged to nursing homes and had higher mean hospitalization charges. In 2011 compared with 2005, there was an improved survival after CPR and higher rates of discharges to home. There was no significant change in the mean length of hospital stay between these time periods (p = 0.4). CONCLUSION: AKI independently increases the odds of in-hospital mortality and nursing home placement after in-hospital CPR. These data may facilitate CPR discussions and decision-making in critically ill patients.
.

MS-REDUCE: an ultrafast technique for reduction of big mass spectrometry data for high-throughput processing.

MOTIVATION: Modern proteomics studies utilize high-throughput mass spectrometers which can produce data at an astonishing rate. These big mass spectrometry (MS) datasets can easily reach peta-scale level creating storage and analytic problems for large-scale systems biology studies. Each spectrum consists of thousands of peaks which have to be processed to deduce the peptide. However, only a small percentage of peaks in a spectrum are useful for peptide deduction as most of the peaks are either noise or not useful for a given spectrum. This redundant processing of non-useful peaks is a bottleneck for streaming high-throughput processing of big MS data. One way to reduce the amount of computation required in a high-throughput environment is to eliminate non-useful peaks. Existing noise removing algorithms are limited in their data-reduction capability and are compute intensive making them unsuitable for big data and high-throughput environments. In this paper we introduce a novel low-complexity technique based on classification, quantization and sampling of MS peaks. RESULTS: We present a novel data-reductive strategy for analysis of Big MS data. Our algorithm, called MS-REDUCE, is capable of eliminating noisy peaks as well as peaks that do not contribute to peptide deduction before any peptide deduction is attempted. Our experiments have shown up to 100× speed up over existing state of the art noise elimination algorithms while maintaining comparable high quality matches. Using our approach we were able to process a million spectra in just under an hour on a moderate server. AVAILABILITY AND IMPLEMENTATION: The developed tool and strategy has been made available to wider proteomics and parallel computing community and the code can be found at https://github.com/pcdslab/MSREDUCE CONTACT: : fahad.saeed@wmich.edu SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Outcomes of transient ischemic attack in maintenance dialysis patients and those with chronic kidney disease.

BACKGROUND: In-hospital outcomes of transient ischemic attack (TIA) in patients with chronic kidney disease (CKD) and end-stage renal disease (ESRD) requiring maintenance dialysis are largely unknown. We evaluated TIA-related in-hospital outcomes in these patients using a national database. METHODS: Our study is observational in nature. Data from all adult (≥ 18 years) patients admitted to US hospitals between 2005 and 2011 with a primary discharge diagnosis of TIA and secondary diagnosis of CKD and ESRD were included using the Nationwide In-Patient Sample. We aimed to compare the following TIA-related outcomes between CKD and ESRD patients: (i) degree of disability (mainly functional status) derived from discharge destination, (ii) length of stay, (iii) charges of hospitalization, and (iv) mortality. The comparisons of TIA-related mortality and discharge outcomes between CKD and ESRD were analyzed after adjusting for potential confounders using logistic regression analysis. We adjusted for age, sex, co-morbidities, hospital size and hospital teaching status. RESULTS: A total of 18 316 dialysis and 67 256 CKD patients were admitted with TIA in the study period (2005-11). On univariate analysis, there was no difference in the rates of moderate-to-severe disability (20.5% versus 20.2%, P = 0.7) and in-hospital mortality (0.4% versus 0.2%, P = 0.07) in ESRD patients compared with those with CKD. After adjusting for age, sex and potential confounders, ESRD patients with TIA had higher odds of moderate-to-severe disability at discharge [odds ratio (OR): 1.53, 95% confidence interval (CI): 1.37-1.71, P ≤ 0.0001] and in-hospital death (OR: 2.87, 95% CI: 1.29-6.37, P = 0.009). CONCLUSION: ESRD patients with TIA have significantly higher rates of moderate-to-severe disability at discharge and in-hospital mortality when compared with the patients of other stages of CKD who are not dialysis-dependent.

Outcomes of In-Hospital Cardiopulmonary Resuscitation in Maintenance Dialysis Patients.

Outcomes of cardiopulmonary resuscitation (CPR) in hospitalized patients with ESRD requiring maintenance dialysis are unknown. Outcomes of in-hospital CPR in these patients were compared with outcomes in the general population using data from the Nationwide Inpatient Sample (NIS; 2005-2011). The study population included all adults (≥ 18 years old) from the general population and those with a history of ESRD. Baseline characteristics, in-hospital complications, and discharge outcomes were compared between the two groups. The effects of in-hospital CPR on mortality, length of stay, hospitalization charges, and discharge destination were analyzed. Yearly national trends in survival, discharge to home, and length of stay were also examined using the Cochran-Armitage trend test. During the study period, 56,069 patients with ESRD underwent in-hospital CPR compared with 323,620 patients from the general population. Unadjusted in-hospital mortality rates were higher in patients with ESRD (73.9% versus 71.8%, P<0.001) on univariate analysis. After adjusting for age, gender, and potential confounders, patients with ESRD had higher odds of mortality (odds ratio, 1.24; 95% confidence interval, 1.11 to 1.3; P<0.001). Survival after CPR improved in the year 2011 compared with 2005 (31% versus 21%, P<0.001). Multivariate analysis also revealed that a greater proportion of patients with ESRD who survived were discharged to skilled nursing facilities. In conclusion, outcomes after in-hospital CPR are improving in patients with ESRD but remain worse than outcomes in the general population. Patients with ESRD who survive are more likely to be discharged to nursing homes.

Comparative Outcomes of Carotid Artery Stent Placement and Carotid Endarterectomy in Patients with Chronic Kidney Disease and End-Stage Renal Disease.

BACKGROUND: Patients with chronic kidney disease (CKD) and end-stage renal disease (ESRD) have a high prevalence of carotid artery stenosis but are excluded from clinical trials. We sought to determine the clinical characteristics and outcomes related to carotid endarterectomy (CEA) and carotid artery stenting (CAS) in ESRD and CKD patients. METHODS: We determined the frequency of CAS and CEA performed in patients with ESRD and CKD and associated in-hospital outcomes using data from the nationwide inpatient sample data files from 2005 to 2011. All the in-hospital outcomes were analyzed after adjusting for potential confounders using multivariate analysis. RESULTS: Of the 43,875 CKD patients who underwent CEA, 3888 (8.8%) were ESRD patients. After adjusting for age, gender, race, presence of hypertension, congestive heart failure (CHF), dyslipidemia, nicotine dependence and alcohol abuse, CEA performed in ESRD patients was associated with higher rates of in-hospital mortality (odds ratio [OR] 4.3, 95% confidence interval [CI] 2.1-9.0; P ≤ .0001) and moderate to severe disability (OR 1.4, 95% CI 1.1-1.8; P = .009). Of the 8148 CKD patients who underwent CAS, 693 (8.5%) were ESRD patients. After adjusting for age, gender, race/ethnicity, presence of dyslipidemia, CHF, and hypertension, CAS performed in ESRD patients was associated with higher rates of in-hospital mortality (OR 3.7, 95% CI 1.0-13.9; P = .04) and moderate to severe disability (OR 1.7, 95% CI 1.0-3.3; P = .05). CONCLUSIONS: Both CAS and CEA were associated with 4-folds higher odds of in-hospital mortality in ESRD patients and such observations raise concerns regarding the risk : benefit ratio of carotid revascularization in these patients.

Variable pharmacokinetics of extended interval tobramycin or gentamicin among critically ill patients undergoing continuous venovenous hemofiltration.

BACKGROUND/AIMS: Aminoglycosides are a major weapon against serious Gram-negative rod infections, yet aminoglycoside usage is limited by the risk of nephrotoxicity. The risk of toxicity is reduced by extended-interval dosing of aminoglycosides, defined as 5 - 7 mg/kg given intravenously in intervals of 24 hours or greater based on serum drug concentrations. In critically ill patients undergoing continuous venovenous hemofiltration, there are few published reports of the pharmacokinetics of extended-interval dosing of aminoglycosides. METHODS: We evaluated the pharmacokinetics of extended-interval dosing of gentamicin and tobramycin in 9 critically ill patients on continuous venovenous hemofiltration at Dartmouth-Hitchcock Medical Center between April 2007 and September 2011. RESULTS: Aminoglycoside elimination half-life values were highly variable (median 7 hours, range 3 - 26 hours) and did not correlate with total body weight or estimated creatinine clearance derived from the dose of continuous venovenous hemofiltration. Five of 9 patients cleared infection, but only 4 patients survived to hospital discharge, 2 of whom were dialysis-dependent. CONCLUSION: Extended interval aminoglycoside dosing during continuous venovenous hemofiltration yields unpredictable half-lives and drug levels among high-risk critically ill patients. Close monitoring of serum aminoglycoside levels is required.