Cindy Marling

Case-based reasoning in the health sciences: What's next?

OBJECTIVES This paper presents current work in case-based reasoning (CBR) in the health sciences, describes current trends and issues, and projects future directions for work in this field. METHODS AND MATERIAL It represents the contributions of researchers at two workshops on case-based reasoning in the health sciences. These workshops were held at the Fifth International Conference on Case-Based Reasoning (ICCBR-03) and the Seventh European Conference on Case-Based Reasoning (ECCBR-04). RESULTS Current research in CBR in the health sciences is marked by its richness. Highlighted trends include work in bioinformatics, support to the elderly and people with disabilities, formalization of CBR in biomedicine, and feature and case mining. CONCLUSION CBR systems are being better designed to account for the complexity of biomedicine, to integrate into clinical settings and to communicate and interact with diverse systems and methods.

Case-Based Reasoning in the Care of Alzheimer's Disease Patients

Planning the ongoing care of Alzheimers Disease (AD) patients is a complex task, marked by cases that change over time, multiple perspectives, and ethical issues. Geriatric interdisciplinary teams of physicians, nurses and social workers currently plan this care without computer assistance. Although AD is incurable, interventions are planned to improve the quality of life for patients and their families. Much of the reasoning involved is case-based, as clinicians look to case histories to learn which interventions are effective, to document clinical findings, and to train future health care professionals. There is great variability among AD patients, and within the same patient over time. AD is not yet well enough understood for universally effective treatments to be available. The case-based reasoning (CBR) research paradigm complements the medical research approach of finding treatments effective for all patients by matching patients to treatments that were effective for similar patients in the past. The Auguste Project is an effort to provide decision support for planning the ongoing care of AD patients, using CBR and other thought processes natural to members of geriatric interdisciplinary teams. System prototypes are used to explore the reasoning processes involved and to provide the forerunners of practical clinical tools. The first system prototype has just been completed. This prototype supports the decision to prescribe neuroleptic drugs to AD patients with behavioral problems. It uses CBR to determine if a neuroleptic drug should be prescribed and rule-based reasoning to select one of five approved neuroleptic drugs for a patient. The first system prototype serves as proof of concept that CBR is useful for planning ongoing care for AD patients. Additional prototypes are planned to explore the research issues raised.

INTEGRATING CASE-BASED AND RULE-BASED REASONING TO MEET MULTIPLE DESIGN CONSTRAINTS

Although case‐based reasoning (CBR) was introduced as an alternative to rule‐based reasoning (RBR), there is a growing interest in integrating it with other reasoning paradigms, including RBR. New hybrid approaches are being piloted to achieve new synergies and improve problem‐solving capabilities. In our approach to integration, CBR is used to satisfy multiple numeric constraints, and RBR allows the performance of “what if” analysis needed for creative design.

Characterizing Blood Glucose Variability Using New Metrics with Continuous Glucose Monitoring Data

Objective: Glycemic variability contributes to oxidative stress, which has been linked to the pathogenesis of the long-term complications of diabetes. Currently, the best metric for assessing glycemic variability is mean amplitude of glycemic excursion (MAGE); however, MAGE is not in routine clinical use. A glycemic variability metric in routine clinical use could potentially be an important measure of overall glucose control and a predictor of diabetes complication risk not detected by glycosylated hemoglobin (A1C) levels. This study aimed to develop and evaluate new automated metrics of glycemic variability that could be routinely applied to continuous glucose monitoring (CGM) data to assess and enhance glucose control. Method: Individual 24 h CGM tracings from our clinical diabetes research database were scored for MAGE and two additional metrics designed to compensate for aspects of variability not captured by MAGE: (1) number of daily glucose fluctuations >75 mg/dl that leave the normal range (70–175 mg/dl), or excursion frequency, and (2) total daily fluctuation, or distance traveled. These scores were used to train machine learning algorithms to recognize excessive variability based on physician ratings of daily CGM charts, producing a third metric of glycemic variability: perceived variability. Finger stick A1C (average) and serum 1,5-anhydroglucitol (postprandial) levels were used as clinical markers of overall glucose control for comparison. Results: Mean amplitude of glycemic excursion, excursion frequency, and distance traveled did not adequately quantify the glycemic variability visualized by physicians who evaluated the daily CGM plots. A naive Bayes classifier was developed that characterizes CGM tracings based on physician interpretations of tracings. Preliminary results suggest that the number of excessively variable days, as determined by this naive Bayes classifier, may be an effective way to automatically assess glycemic variability of CGM data. This metric more closely reflects 90-day changes in serum 1,5-anhydroglucitol levels than does MAGE. Conclusion: We have developed a new automated metric to assess overall glycemic variability in people with diabetes using CGM, which could easily be incorporated into commercially available CGM software. Additional work to validate and refine this metric is underway. Future studies are planned to correlate the metric with both urinary 8-iso-prostaglandin F2 alpha excretion and serum 1,5-anhydroglucitol levels to see how well it identifies patients with high glycemic variability and increased markers of oxidative stress to assess risk for long-term complications of diabetes.

Case-based reasoning integrations

This article presents an overview and survey of current work in case-based reasoning (CBR) integrations. There has been a recent upsurge in the integration of CBR with other reasoning modalities and computing paradigms, especially rule-based reasoning (RBR) and constraint-satisfaction problem (CSP) solving. CBR integrations with model-based reasoning (MBR), genetic algorithms, and information retrieval are also discussed. This article characterizes the types of multimodal reasoning integrations where CBR can play a role, identifies the types of roles that CBR components can fulfill, and provides examples of integrated CBR systems. Past progress, current trends, and issues for future research are discussed.

Case-Based Decision Support for Patients with Type 1 Diabetes on Insulin Pump Therapy

This paper presents a case-based approach to decision support for diabetes management in patients with Type 1 diabetes on insulin pump therapy. To avoid serious disease complications, including heart attack, blindness and stroke, these patients must continuously monitor their blood glucose levels and keep them as close to normal as possible. Achieving and maintaining good blood glucose control is a difficult task for these patients and their health care providers. A prototypical case-based decision support system was built to assist with this task. A clinical research study, involving 20 patients, yielded 50 cases of actual problems in blood glucose control, with their associated therapeutic adjustments and clinical outcomes, for the prototypes case base. The prototype operates by: (1) detecting problems in blood glucose control in large quantities of patient blood glucose and life event data; (2) finding similar past problems in the case base; and (3) offering the associated therapeutic adjustments stored in the case base to the physician as decision support. Results from structured evaluation sessions and a patient feedback survey encourage continued research and work towards a practical tool for diabetes management.

Hypoglycemia in Type 2 Diabetes - More Common Than You Think A Continuous Glucose Monitoring Study

Background: Hypoglycemia is often the limiting factor for intensive glucose control in diabetes management, however its actual prevalence in type 2 diabetes (T2DM) is not well documented. Methodology: A total of 108 patients with T2DM wore a continuous glucose monitoring system (CGMS) for 5 days. Rates and patterns of hypoglycemia and glycemic variability (GV) were calculated. Patient and medication factors were correlated with rates, timing, and severity of hypoglycemia. Results: Of the patients, 49.1% had at least 1 hypoglycemic episode (mean 1.74 episodes/patient/ 5 days of CGMS) and 75% of those patients experienced at least 1 asymptomatic hypoglycemic episode. There was no significant difference in the frequency of daytime versus nocturnal hypoglycemia. Hypoglycemia was more frequent in individuals on insulin (alone or in combination) (P = .02) and those on oral hypoglycemic agents (P < .001) compared to noninsulin secretagogues. CGMS analysis resulted in treatment modifications in 64% of the patients. T2DM patients on insulin exhibited higher glycemic variability (GV) scores (2.3 ± 0.6) as compared to those on oral medications (1.8 ± 0.7, P = .017). Conclusions: CGMS can provide rich data that show glucose excursions in diabetes patients throughout the day. Consequently, unwarranted onset of hypo- and hyperglycemic events can be detected, intervened, and prevented by using CGMS. Hypoglycemia was frequently unrecognized by the patients in this study (75%), which increases their potential risk of significant adverse events. Incorporation of CGMS into the routine management of T2DM would increase the detection and self-awareness of hypoglycemia resulting in safer and potentially better overall control.

Integrations with case-based reasoning

This commentary succinctly summarizes work in integrating case-based reasoning (CBR) with other reasoning modalities. Including CBR in mixed mode approaches promotes synergies and benefits beyond those achievable using CBR or other individual reasoning approaches alone. Numerous examples of hybrid systems, with pointers to significant references, are provided.

An Artificial Intelligence System for Computer-Assisted Menu Planning

Planning nutritious and appetizing menus is a complex task that researchers have tried to computerize since the early 1960s. We have attempted to facilitate computer-assisted menu planning by modeling the reasoning an expert dietitian uses to plan menus. Two independent expert systems were built, each designed to plan a daily menu meeting the nutrition needs and personal preferences of an individual client. One system modeled rule-based, or logical, reasoning, whereas the other modeled case-based, or experiential, reasoning. The 2 systems were evaluated and their strengths and weaknesses identified. A hybrid system was built, combining the best of both systems. The hybrid system represents an important step forward because it plans daily menus in accordance with a persons needs and preferences; the Reference Daily Intakes; the Dietary Guidelines for Americans; and accepted aesthetic standards for color, texture, temperature, taste, and variety. Additional work to expand the systems scope and to enhance the user interface will be needed to make it a practical tool. Our system framework could be applied to special-purpose menu planning for patients in medical settings or adapted for institutional use. We conclude that an artificial intelligence approach has practical use for computer-assisted menu planning.

Synergistic case-based reasoning in medical domains

This paper presents four synergistic systems that exemplify the approaches and benefits of case-based reasoning in medical domains. It then explores how these systems couple Artificial Intelligence (AI) research with medical research and practice, integrate multiple AI and computing methodologies, leverage small numbers of available cases, reason with time series data, and integrate numeric data with contextual and subjective information. The following systems are presented: (1) CARE-PARTNER, which supports the long-term follow-up care of stem-cell transplantation patients; (2) the 4 Diabetes Support System, which aids in managing patients with type 1 diabetes on insulin pump therapy; (3) Retrieval of HEmodialysis in NEphrological Disorders, which supports hemodialysis treatment of patients with end stage renal disease; and (4) the Malardalen Stress System, which aids in the diagnosis and treatment of stress-related disorders.