Integrating knowledge-based systems and databases

Detecting adverse drug events (ADEs) and medications related information in clinical notes is important for both hospital medical care and medical research. We describe our clinical natural language processing (NLP) system to automatically extract medical concepts and relations related to ADEs and medications from clinical narratives. This work was part of the 2018 National NLP Clinical Challenges Shared Task and Workshop on Adverse Drug Events and Medication Extraction. The authors developed a hybrid clinical NLP system that employs a knowledge-based general clinical NLP system for medical concepts extraction, and a task-specific deep learning system for relations identification using attention-based bidirectional long short-term memory networks. The systems were evaluated as part of the 2018 National NLP Clinical Challenges challenge, and our attention-based bidirectional long short-term memory networks based system obtained an F-measure of 0.9442 for relations identification task, ranking fifth at the challenge, and had <2% difference from the best system. Error analysis was also conducted targeting at figuring out the root causes and possible approaches for improvement. We demonstrate the generic approaches and the practice of connecting general purposed clinical NLP system to task-specific requirements with deep learning methods. Our results indicate that a well-designed hybrid NLP system is capable of ADE and medication-related information extraction, which can be used in real-world applications to support ADE-related researches and medical decisions.

To solve the problem of advanced digital manufacturing technology in the practical application, a knowledge engineering technology was introduced into the computer numerical control (CNC) programming. The knowledge acquisition, knowledge representation and reasoning used in CNC programming were researched. The CNC programming system functional architecture of impeller parts based on knowledge based engineering (KBE) was constructed. The structural model of the general knowledge-based system (KBS) was also constructed. The KBS of CNC programming system was established through synthesizing database technology and knowledge base theory. And in the context of corporate needs, based on the knowledge-driven manufacturing platform (i.e. UG CAD/CAM), VC++6.0 and UG/Open, the KBS and UG CAD/CAM were integrated seamlessly and the intelligent CNC programming KBE system for the impeller parts was developed by integrating KBE and UG CAD/CAM system. A method to establish standard process templates was proposed, so as to develop the intelligent CNC programming system in which CNC machining process and process parameters were standardized by using this KBE system. For the impeller parts processing, the method applied in the development of the prototype system is proven to be viable, feasible and practical.

A modification of the paradigm of Artificial Intelligence (AI) is proposed in the paper. The modification is based on the assumption that there are algorithms which are inductive by construction, but can be mathematically proved. The content of traditional artificial intelligence concepts (knowledge, form of presentation, knowledge base, etc.) is determined within the proposed paradigm. The modification ensures unification of many concepts in the field of artificial intelligence.

Natural language processing systems for capturing and standardizing unstructured clinical information: A systematic review

Many ongoing clinical research projects, such as projects involving studies associated with cancer, involve manual capture of information in surgical pathology reports so that the information can be used to determine the eligibility of recruited patients for the study and to provide other information, such as cancer prognosis. Natural language processing (NLP) systems offer an alternative to automated coding, but pathology reports have certain features that are difficult for NLP systems. This paper describes how a preprocessor was integrated with an existing NLP system (MedLEE) in order to reduce modification to the NLP system and to improve performance. The work was done in conjunction with an ongoing clinical research project that assesses disparities and risks of developing breast cancer for minority women. An evaluation of the system was performed using manually coded data from the research project's database as a gold standard. The evaluation outcome showed that the extended NLP system had a sensitivity of 90.6% and a precision of 91.6%. Results indicated that this system performed satisfactorily for capturing information for the cancer research project.

Evaluation of Natural Language Processing (NLP) systems to annotate drug product labeling with MedDRA terminology

The need and desire to transform computers from machines that perform laborious, tedious and repetitive calculations to systems that can perform more intelligent tasks akin to human beings has been the single goal of the artificial intelligence (Al) community. With recent advances in the field of artificial intelligence this long awaited dream is becoming a reality. This success is due to what has become known as the knowledge-based expert systems technique. A characteristic of these systems is massive amount of knowledge in a specific domain which enables them to imitate the human problem solving process. Knowledge-based expert systems are able to perform tasks which are labeled as intelligent tasks when performed by human beings. More specifically, they are able to interpret data, monitor a system, diagnose a condition, plan an action, consult, reason, and explain their reasoning. These characteristics are the motivation for transforming expert systems from a few academic projects in the 1970’s to the explosive commercial market in the 1980’s. The importance of knowledge-based expert systems can be measured in several ways: the widespread application of these systems to various domains, a few in the 1970’s compared to 100s of applications in the 1980’s; the number of startup companies marketing knowledge-based expert systems and tools related to the development of these systems; the number of dollars spent by various governments and companies to achieve superiority and state of the art status in this field [Hayes-Roth 84].KeywordsExpert SystemVLSI DesignHuman DesignerProduction MemoryVLSI ChipThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

The purpose of this study is to evaluate the performance of a natural language processing (NLP) system in classifying a database of free-text knee MRI reports at two separate academic radiology practices. An NLP system that uses terms and patterns in manually classified narrative knee MRI reports was constructed. The NLP system was trained and tested on expert-classified knee MRI reports from two major health care organizations. Radiology reports were modeled in the training set as vectors, and a support vector machine framework was used to train the classifier. A separate test set from each organization was used to evaluate the performance of the system. We evaluated the performance of the system both within and across organizations. Standard evaluation metrics, such as accuracy, precision, recall, and F1 score (i.e., the weighted average of the precision and recall), and their respective 95% CIs were used to measure the efficacy of our classification system. The accuracy for radiology reports that belonged to the model's clinically significant concept classes after training data from the same institution was good, yielding an F1 score greater than 90% (95% CI, 84.6-97.3%). Performance of the classifier on cross-institutional application without institution-specific training data yielded F1 scores of 77.6% (95% CI, 69.5-85.7%) and 90.2% (95% CI, 84.5-95.9%) at the two organizations studied. The results show excellent accuracy by the NLP machine learning classifier in classifying free-text knee MRI reports, supporting the institution-independent reproducibility of knee MRI report classification. Furthermore, the machine learning classifier performed well on free-text knee MRI reports from another institution. These data support the feasibility of multiinstitutional classification of radiologic imaging text reports with a single machine learning classifier without requiring institution-specific training data.

Knowledge-based technology is being applied to complex problem-solving and critical tasks in many application domains. Concerns have naturally arisen as to the dependability of knowledge-base systems (KBSs). As with any software, attention to quality and safety must be paid throughout the development of a KBS, and rigorous verification and validation (V&V) techniques must be employed. Research in KBS V&V has emerged as a distinct field only in the last decade and is intended to address issues associated with KBS quality aspects and to credit such applications with the same degree of dependability as conventional applications. However, a major drawback of the current state of acceptance of KBS software is the lack of standardization. Although standards do exist for software, extensions are needed to cope with specific KBS software characteristics. This paper advocates the idea that, although quality assessment of KBS software is still a challenging issue, KBS software is not an impossible one. Some V&V techniques based on specific KBS software properties are described in this paper which aims at indicating KBS acceptability requirements may be specified and evaluated, being at the same time a good basis for certification.

: The Neal-Montgomery NLP Evaluation Methodology was developed under the 'Benchmark Investigation/Identification' project as a means of determining the linguistic competence of Natural Language Processing (NLP) systems. Embodied in an evaluation tool based on a detailed classification of linguistic phenomena with, currently, over 350 test items, the methodology produces descriptive profiles of NLP system linguistic capabilities, and can be applied without regard to the current system application, domain, or specific language processing function. To date, it has been applied to three NL data base query systems and three text processing systems. Researchers are invited to apply the evaluation methodology (included within this report) to their systems and report their critique and recommendations towards the evolution of standard evaluation procedures for NLP systems.

To evaluate the feasibility, accuracy, and interoperability of a natural language processing (NLP) system that extracts diagnostic assertions of pneumonia in different clinical notes and institutions. A rule-based NLP system was designed to identify assertions of pneumonia in 3 types of clinical notes from electronic health records (EHRs): emergency department notes, radiology reports, and discharge summaries. The lexicon and classification logic were tailored for each note type. The system was first developed and evaluated using annotated notes from the Department of Veterans Affairs (VA). Interoperability was assessed using data from the University of Utah (UU). The NLP system was comprised of 782 rules and achieved moderate-to-high performance in all 3 note types in VA (precision/recall/f1: emergency = 88.1/86.0/87.1; radiology = 71.4/96.2/82.0; discharge = 88.3/93.0/90.1). When applied to UU data, performance was maintained in emergency and radiology but decreased in discharge summaries (emergency = 84.7/94.3/89.3; radiology = 79.7/100.0/87.9; discharge = 65.5/92.7/76.8). Customization with 34 additional rules increased performance for all note types (emergency = 89.3/94.3/91.7; radiology = 87.0/100.0/93.1; discharge = 75.0/95.1/83.4). NLP can be used to accurately identify the diagnosis of pneumonia across different clinical settings and institutions. A limited amount of customization to account for differences in lexicon, clinical definition of pneumonia, and EHR structure can achieve high accuracy without substantial modification.

BackgroundCognitive test results from electronic health records (EHRs) are key information for assessing the severity and progression of patients with mild cognitive impairment (MCI) and Alzheimer’s’ disease (AD). However, such information is often recorded in unstructured clinical notes rather than in an administrative database. We developed and validated a natural language processing (NLP) system to extract cognitive test results from clinical notes in the Veterans Affair (VA) Healthcare System.MethodAn NLP system was developed using regular expression‐based rules and Python to extract results for six tests that have been used most frequently in VA: Mini‐Mental State Exam (MMSE), Montreal Cognitive Assessment (MoCA), Saint Louis University Mental Status Examination (SLUMS), Mini‐cog, Boston Naming Test (BNT), and Benton Visual Retention Test (BVRT). The system extracted test results from each note in two steps: (1) searched a test name, or variations and abbreviation of the test name and, if successful, (2) searched the quantitative results (e.g., 12/30 for MMSE, 74th percentile for BNT) and/or descriptive results (e.g., “borderline impairment” for BVRT) within 5 words or one sentence before or after the test name. To balance the system performance and speed, we developed 3‐8 extraction rules per test based on a manual review of 30‐50 notes for each test. We further validated NLP performance on 6 held‐out datasets (50‐200 notes/test). We automatically sampled the development and held‐out notes by searching the test name and its variations/abbreviation to increase positive cases, i.e., notes that contained the above test results.ResultThe NLP system achieved 0.72‐0.92 predictive positive values (PPV), 0.96‐1.00 recall, and 0.83‐0.95 F1 scores on the validation test sets (Table 1). In addition, it demonstrated a scalable performance (processed 200,000 notes in 7 min), allowing an extraction of millions of notes from ∼1 million patients within hours.ConclusionRule‐based NLP can extract cognitive test results with adequate performance and scalable capability for clinical notes from patients with MCI or AD within the VA Healthcare System.

Customer support process has seen a transformational shift in recent years. With the rapid proliferation of Artificial Integrating (AI), the human driven customer support has leapfrogged into automated customer services &amp; support. The field of Artificial Intelligence (AI) has seen phenomenal rise in the development of agents' capability right from autonomous decision-making and problem-solving abilities to adapt to changing environments. Their proficiency in learning from experience and adaptation greatly influences their effectiveness. They both drive improvement over time and insure response to dynamic customer needs and conditions. Adaptation and learning also permit strategies to be revised in light of new data provided to them. This paper explores the bases and techniques of adaptation and learning in AI agents, focusing on reinforcement learning, supervised learning, unsupervised learning, and the combination. In addition, it also addresses challenges like overfitting, exploration-exploitation tradeoffs and computational economics. The role of these processes in various AI applications, including robotics, natural language processing and autonomous systems help industry reduce dependency on manual effort and improve efficiency to drive growth. Keywords-Adaptation, Learning, AI agents, Reinforcement learning, Supervised learning, Autonomous systems.

As the field of Artificial Intelligence (AI) matures, methods relying less on ad hoc procedures and more on well defined operations in the context of formal structures are emerging. Evidence for this can be found, for example, in the increasingly sophisticated approaches to inexact reasoning in knowledge-based systems and in the mathematical framework developed for semantic net representation. This tutorial and brief survey presents a facet of formal language theory which provides a formalism for naturally representing and operating on strings of symbols and which also admits obvious means of handling issues such as specialization and generalization, pervasive in AI. The broad subject area covered is part of semigroup theory which has a natural relationship to both finite state automata theory and regular languages. This paper aims to introduce some of the underlying theory relevant to representation issues in AI in this context.

Recent advances in computer technology offer to the medical profession specialized tools for gathering medical data, processing power, as well as fast storing and retrieving capabilities. Artificial intelligence (AI), an emerging field of computer science is studying the issues of human problem solving and decision making. Furthermore, rule-based systems and knowledge-based systems that are other fields of AI have been adopted by many scientists in an effort to develop intelligent medical diagnostic systems. In this study artificial neural networks (ANN) are introduced as a tool for building an intelligent diagnostic system; the system does not attempt to replace the physician from being the decision maker but to enhance ones facilities for reaching a correct decision. An integrated diagnostic system for assessing certain neuromuscular disorders is used in this study as an example for demonstrating the proposed methodology. The diagnostic system is composed of modules that independently provide numerical data to the system from the clinical examination of a patient, and from various laboratory tests that are performed. The examination procedure has been standardized by developing protocols for each specialized area, in cooperation with experts in the area. At the conclusion of the clinical examination and laboratory tests, data in the form of a numerical vector represents a medical examination snapshot of the subject. Artificial neural network (ANN) models were developed using the unsupervised self-organizing feature maps algorithm. Data from 71 subjects were collected. The ANN models were trained with the data from 41 subjects, and tested with the data from the remaining 30 subjects. Two sets of models were developed; those trained with the data from only the clinical examinations; and those trained by combining the clinical and the laboratory test data. The diagnostic yield that was obtained for the unknown cases is in the region of 73 to 93% for the models trained with only the clinical data, and in the region of 73 to 100% for those trained by combining both the clinical and laboratory data. The pictorial representation of the diagnostic models through the self organized two dimensional feature maps provide the physician with a friendly human-computer interface and a comprehensive tool that can be used for further observations, for example in monitoring disease progression of a subject.