Evaluating Natural Language Processing Packages for Predicting Hospital-Acquired Pressure Injuries From Clinical Notes.

Incidence of hospital-acquired pressure injury, a key indicator of nursing quality, is directly proportional to adverse outcomes, increased hospital stays, and economic burdens on patients, caregivers, and society. Thus, predicting hospital-acquired pressure injury is important. Prediction models use structured data more often than unstructured notes, although the latter often contain useful patient information. We hypothesize that unstructured notes, such as nursing notes, can predict hospital-acquired pressure injury. We evaluate the impact of using various natural language processing packages to identify salient patient information from unstructured text. We use named entity recognition to identify keywords, which comprise the feature space of our classifier for hospital-acquired pressure injury prediction. We compare scispaCy and Stanza, two different named entity recognition models, using unstructured notes in Medical Information Mart for Intensive Care III, a publicly available ICU data set. To assess the impact of vocabulary size reduction, we compare the use of all clinical notes with only nursing notes. Our results suggest that named entity recognition extraction using nursing notes can yield accurate models. Moreover, the extracted keywords play a significant role in the prediction of hospital-acquired pressure injury.

GASP: Graph-based Approximate Sequential Pattern Mining for Electronic Health Records.

Sequential pattern mining can be used to extract meaningful sequences from electronic health records. However, conventional sequential pattern mining algorithms that discover all frequent sequential patterns can incur a high computational and be susceptible to noise in the observations. Approximate sequential pattern mining techniques have been introduced to address these shortcomings yet, existing approximate methods fail to reflect the true frequent sequential patterns or only target single-item event sequences. Multi-item event sequences are prominent in healthcare as a patient can have multiple interventions for a single visit. To alleviate these issues, we propose GASP, a graph-based approximate sequential pattern mining, that discovers frequent patterns for multi-item event sequences. Our approach compresses the sequential information into a concise graph structure which has computational benefits. The empirical results on two healthcare datasets suggest that GASP outperforms existing approximate models by improving recoverability and extracts better predictive patterns.

Privacy-preserving Sequential Pattern Mining in distributed EHRs for Predicting Cardiovascular Disease.

From electronic health records (EHRs), the relationship between patients' conditions, treatments, and outcomes can be discovered and used in various healthcare research tasks such as risk prediction. In practice, EHRs can be stored in one or more data warehouses, and mining from distributed data sources becomes challenging. Another challenge arises from privacy laws because patient data cannot be used without some patient privacy guarantees. Thus, in this paper, we propose a privacy-preserving framework using sequential pattern mining in distributed data sources. Our framework extracts patterns from each source and shares patterns with other sources to discover discriminative and representative patterns that can be used for risk prediction while preserving privacy. We demonstrate our framework using a case study of predicting Cardiovascular Disease in patients with type 2 diabetes and show the effectiveness of our framework with several sources and by applying differential privacy mechanisms.

MMiDaS-AE: Multi-modal Missing Data aware Stacked Autoencoder for Biomedical Abstract Screening.

Systematic review (SR) is an essential process to identify, evaluate, and summarize the findings of all relevant individual studies concerning health-related questions. However, conducting a SR is labor-intensive, as identifying relevant studies is a daunting process that entails multiple researchers screening thousands of articles for relevance. In this paper, we propose MMiDaS-AE, a Multi-modal Missing Data aware Stacked Autoencoder, for semi-automating screening for SRs. We use a multi-modal view that exploits three representations, of: 1) documents, 2) topics, and 3) citation networks. Documents that contain similar words will be nearby in the document embedding space. Models can also exploit the relationship between documents and the associated SR MeSH terms to capture article relevancy. Finally, related works will likely share the same citations, and thus closely related articles would, intuitively, be trained to be close to each other in the embedding space. However, using all three learned representations as features directly result in an unwieldy number of parameters. Thus, motivated by recent work on multi-modal auto-encoders, we adopt a multi-modal stacked autoencoder that can learn a shared representation encoding all three representations in a compressed space. However, in practice one or more of these modalities may be missing for an article (e.g., if we cannot recover citation information). Therefore, we propose to learn to impute the shared representation even when specific inputs are missing. We find this new model significantly improves performance on a dataset consisting of 15 SRs compared to existing approaches.

FuzzyGap: Sequential Pattern Mining for Predicting Chronic Heart Failure in Clinical Pathways.

The rapid growth of electronic health records (EHRs) facilitates the use of clinical pathways, an actionable plan for patients which is represented as sequences of diagnostic records ordered by visit dates. We propose to extract discriminative and representative clinical pathways from EHRs using sequential pattern mining. However, existing sequential patterns cannot efficiently extract patterns due to patient variations in length and time period between visits. To resolve this problem, we propose FuzzyGap, a sequential pattern mining-based framework that extracts a discriminative subsequent pattern from the proper representation of the sequence of encounters which also emphasizes the last visit that is more significant than others. We demonstrate FuzzyGap using a case study of heart failure and show the effectiveness of sequential pattern mining.

High-pressure pulsatile lavage irrigation of fresh intraarticular fractures: effectiveness at removing particulate matter from bone.

OBJECTIVE: To determine the effectiveness of high-pressure pulsatile lavage (HPL) versus bulb syringe (BS) irrigation in removing particulate matter from metaphyseal cancellous bone. DESIGN: Four grams of particulate graphite were placed in twenty distal femoral intraarticular osteotomies performed on New Zealand rabbit hind limbs. Two groups of ten specimens were then irrigated using either HPL or BS irrigation. A representative coronal section from each specimen was then prepared for histologic evaluation using 400x light microscopy. The number and distribution of graphite particles-present as small (less than 20 micrometers), medium (20 to 50 micrometers), and large (greater than 50 micrometers) aggregates-were then recorded. RESULTS: The mean maximum perpendicular distance of graphite aggregates of all sizes from the osteotomy site was 12.4 millimeters (+/-SD 2.5) in the HPL group and 12.5 millimeters (+/-SD 2.0) in the BS group (p > 0.5). The mean number of aggregates within four 400x fields (1.08 millimeters) of the osteotomy site was 21.9 (+/-SD 22.0) in the HPL group and 21.8 (+/-SD 27.5) in the BS group (p > 0.5). The mean total number of aggregates in the area surveyed was 129.4 (+/-SD 79.6) in the HPL group and 137.5 (+/-SD 113.6) in the BS group (p > 0.5). Separate analyses controlling for aggregate size of the specimens also revealed no significant differences between HPL and BS irrigation. CONCLUSION: HPL and BS irrigation appear equally effective in removing particulate matter from metaphyseal cancellous bone in an intraarticular fracture model. Furthermore, HPL does not appear to drive particulate matter farther into metaphyseal cancellous bone than BS irrigation.

Complications of thermal energy in knee surgery--Part II.

With the theoretical and reported complications of thermal energy use in the knee, an analysis of potential risks and benefits should be done on a case-by-case basis. Many of the basic science studies may not be directly applicable to clinical practice because they use normal (i.e., not diseased) tissues in animal models. Clinical studies are also dependent on surgical technique and equipment settings. With the benefits listed previously, however, it is likely that thermal energy will continue to play an important role in arthroscopic orthopedic surgery, and there are studies that strongly support its safety and efficacy. Janecki performed a retrospective review of 504 laser chondroplasties to determine safe parameters for Ho:YAG laser use in the knee [10]. In their series, they found an 88% patient satisfaction rate, no significant changes in the articular cartilage lesions in the failure group who underwent repeat arthroscopy, and no new cases of osteonecrosis. They concluded that the Ho:YAG laser was safe and recommended energy settings of less than or equal to 1 joule when performing chondroplasties, noncontact and tangential delivery of the laser beam, and maximizing laser spot size as methods for further decreasing complication rates. We agree with the above recommendations and with using the minimal power settings required to afford the desired surgical result. More studies are required to fully define the indications and consequences of thermal energy use in the knee.

A hybrid neural network model for noisy data regression.

A hybrid neural network model, based on the fusion of fuzzy adaptive resonance theory (FA ART) and the general regression neural network (GRNN), is proposed in this paper. Both FA and the GRNN are incremental learning systems and are very fast in network training. The proposed hybrid model, denoted as GRNNFA, is able to retain these advantages and, at the same time, to reduce the computational requirements in calculating and storing information of the kernels. A clustering version of the GRNN is designed with data compression by FA for noise removal. An adaptive gradient-based kernel width optimization algorithm has also been devised. Convergence of the gradient descent algorithm can be accelerated by the geometric incremental growth of the updating factor. A series of experiments with four benchmark datasets have been conducted to assess and compare effectiveness of GRNNFA with other approaches. The GRNNFA model is also employed in a novel application task for predicting the evacuation time of patrons at typical karaoke centers in Hong Kong in the event of fire. The results positively demonstrate the applicability of GRNNFA in noisy data regression problems.