Category: Case Definition

Generation of classification criteria for chronic fatigue syndrome using an artificial neural network and traditional criteria set

Abstract:

OBJECTIVE: The definition of chronic fatigue syndrome (CFS) is still disputed and no validated classification criteria have been published. Artificial neural networks (ANN) are computer-based models that can help to evaluate complex correlations. We examined the utility of ANN and other conventional methods in generating classification criteria for CFS compared to other diseases with prominent fatigue, systemic lupus erythematosus (SLE) and fibromyalgia syndrome (FMA).

PATIENTS AND METHODS: Ninety-nine case patients with CFS, 41 patients with SLE and 58 with FMA were recruited from a generalist outpatient population. Clinical symptoms were documented with help of a predefined questionnaire. The patients were randomly divided into two groups. One group (n = 158) served to derive classification criteria sets by two-fold cross-validation, using a) unweighted application of criteria, b) regression coefficients, c) regression tree analysis, and d) artificial neural networks in parallel. These criteria were validated with the second group (n = 40).

RESULTS: Classification criteria developed by ANN were found to have a sensitivity of 95% and a specificity of 85%. ANN achieved a higher accuracy than any of the other methods.

CONCLUSION: We present validated criteria for the classification of CFS versus SLE and FMA, comparing different classification approaches. The most accurate criteria were derived with the help of ANN. We therefore recommend the use of ANN for the classification of syndromes with complex interrelated symptoms like CFS.

 

Sour ce: Linder R, Dinser R, Wagner M, Krueger GR, Hoffmann A. Generation of classification criteria for chronic fatigue syndrome using an artificial neural network and traditional criteria set. In Vivo. 2002 Jan-Feb;16(1):37-43. http://www.ncbi.nlm.nih.gov/pubmed/11980359

 

The case definition of chronic fatigue syndrome

Abstract:

The 1994 case definition of chronic fatigue syndrome is widely used not only for diagnosis but also for clinical and laboratory-based observations of this clinical entity. The criteria for the 1994 case definition are based primarily on symptoms and not on physical signs or chemical or immunological tests. This situation has resulted in conflicting clinical and laboratory observations that in all likelihood is due to different populations of patients being studied in different centers.

Based on some of the recent publications, there appears to be an emerging picture of this disease entity that we propose could be used to subgroup chronic fatigue syndrome into four different subclasses. These subclasses would consist of chronic fatigue with primarily nervous system disorders such as impaired memory or concentration and headache, chronic fatigue with primarily endocrine system disorders such as unrefreshing sleep and postexertional malaise, chronic fatigue with musculoskeletal system disorders such as muscle pain and joint pain, and chronic fatigue with immune system/infectious disorders such as sore throat and tender lymph nodes.

It is suggested that if clinical and laboratory-based studies on chronic fatigue syndrome were conducted on more homogeneous subgroups of patients, the data from one center to the other might not be as conflicting and more insights can be shed on the nature of this clinical condition.

 

Source: Tan EM, Sugiura K, Gupta S. The case definition of chronic fatigue syndrome. J Clin Immunol. 2002 Jan;22(1):8-12. http://www.ncbi.nlm.nih.gov/pubmed/11958593

 

Symptom occurrence in persons with chronic fatigue syndrome

Abstract:

This investigation compared differences in the occurrence of symptoms in participants with CFS, melancholic depression, and no fatigue (controls). The following Fukuda et al. [Ann. Intern. Med. 121 (1994) 953] criteria symptoms differentiated the CFS group from controls, but did not differentiate the melancholic depression group from controls: headaches, lymph node pain, sore throat, joint pain, and muscle pain. In addition, participants with CFS uniquely differed from controls in the occurrence of muscle weakness at multiple sites as well as in the occurrence of various cardiopulmonary, neurological, and other symptoms not currently included in the current case definition. Implications of these findings are discussed.

 

Source: Jason LA, Torres-Harding SR, Carrico AW, Taylor RR. Symptom occurrence in persons with chronic fatigue syndrome. Biol Psychol. 2002 Feb;59(1):15-27. http://www.ncbi.nlm.nih.gov/pubmed/11790441

 

A definition-based analysis of symptoms in a large cohort of patients with chronic fatigue syndrome

Abstract:

OBJECTIVE: The Holmes and Fukuda criteria are widely used criteria all over the world, yet a specific European study regarding chronic fatigue syndrome (CFS) patient symptomatology has not been conducted so far. This study was performed to answer the need to assess the homogeneity of a large CFS population in relationship to the Fukuda or Holmes definitions and to assess the importance of a symptom severity scale.

DESIGN: Multivariate analyses were performed to assess the symptom presentation within a fatigued population and the differences between the Fukuda and Holmes definitions compared with an excluded chronic fatigued group in a large cohort of fatigued patients.

SETTING: An outpatient tertiary care setting fatigue clinic in Brussels.

MAIN OUTCOME MEASURES: Prevalence and severity of symptoms and signs in a CFS population and in a chronic fatigued population.

SUBJECTS AND METHODS: A total of 2073 consecutive patients with major complaints of prolonged fatigue participated in this study. Multivariate analyses were performed to assess the symptom presentation and severity and the differences between the Fukuda and Holmes definitions.

RESULTS: Of the 2073 patients complaining of chronic fatigue (CF), 1578 CFS patients fulfilled the Fukuda criteria (100% of CFS group) and 951 (60.3% of the CFS group) fulfilled the Holmes criteria. Discriminant function analysis revealed that the Fukuda and Holmes definitions can be differentiated by symptom severity and prevalence. The Holmes definition was more strongly associated than the Fukuda definition with the symptoms that differentiated the CFS patients from the patients that did not comply with the CFS definitions. The inclusion of 10 additional symptoms was found to improve the sensitivity/specificity and accuracy for selection of CFS patients.

CONCLUSIONS: The CFS patients fulfilling the Holmes criteria have an increased symptom prevalence and severity of many symptoms. Patients fulfilling the Fukuda criteria were less severely affected patients which leads to an increase in clinical heterogeneity. Addition of certain symptoms and removal of others would strengthen the ability to select CFS patients.

 

Source: De Becker P, McGregor N, De Meirleir K. A definition-based analysis of symptoms in a large cohort of patients with chronic fatigue syndrome. J Intern Med. 2001 Sep;250(3):234-40. http://onlinelibrary.wiley.com/doi/10.1046/j.1365-2796.2001.00890.x/full (Full article)

 

What is chronic fatigue syndrome? Heterogeneity within an international multicentre study

Abstract:

OBJECTIVE: We sought to compare the characteristics of patients presenting with chronic fatigue (CF) and related syndromes in eight international centres and to subclassify these subjects based on symptom profiles. The validity of the subclasses was then tested against clinical data.

METHOD: Subjects with a clinical diagnosis of CF completed a 119-item self-report questionnaire to provide clinical symptom data and other information such as illness course and functional impairment. Subclasses were generated using a principal components-like analysis followed by latent profile analysis (LPA).

RESULTS: 744 subjects returned complete data sets (mean age 40.8 years, mean length of illness 7.9 years, female to male ratio 3:1). Overall, the subjects had a high rate of reporting typical CF symptoms (fatigue, neuropsychological dysfunction, sleep disturbance). Using LPA, two subclasses were generated. Class one (68% sample) was characterized by: younger age, lower female to male ratio; shorter episode duration; less premorbid, current and familial psychiatric morbidity; and, less functional disability. Class two subjects (32%) had features more consistent with a somatoform illness. There was substantial variation in subclass prevalences between the study centres (Class two range 6-48%).

CONCLUSIONS: Criteria-based approaches to the diagnosis of CF and related syndromes do not select a homogeneous patient group. While substratification of patients is essential for further aetiological and treatment research, the basis for allocating such subcategories remains controversial.

 

Source: Wilson A, Hickie I, Hadzi-Pavlovic D, Wakefield D, Parker G, Straus SE, Dale J, McCluskey D, Hinds G, Brickman A, Goldenberg D, Demitrack M, Blakely T,Wessely S, Sharpe M, Lloyd A. What is chronic fatigue syndrome? Heterogeneity within an international multicentre study. Aust N Z J Psychiatry. 2001 Aug;35(4):520-7. http://www.ncbi.nlm.nih.gov/pubmed/11531735

 

Toward a new definition of chronic fatigue syndrome

To the editor,

I agree with Lane when he writes that the operative criteria for diagnosing chronic fatigue syndrome (CFS) are unsatisfactory. Some patients who have been assigned this label may be better described as having depression or somatization, and this mislabeling prejudices the understanding of CFS in cross-sectional studies.1 Lane is presumably referring to the definition of the Centers for Disease Control and Prevention, with its concentration on physical symptoms.2 This definition also is not all that helpful in assigning a label to individuals for the purposes of estimating prognosis or deciding on treatment because the physical symptoms cited are nonspecific.

You can read the rest of this comment here: http://www.ncbi.nlm.nih.gov/pmc/articles/PMC1071345/

 

Source: Robertson-Ritchie H. Toward a new definition of chronic fatigue syndrome. West J Med. 2001 Apr;174(4):241. http://www.ncbi.nlm.nih.gov/pmc/articles/PMC1071345/ (Full article)

 

Co-existence of chronic fatigue syndrome with fibromyalgia syndrome in the general population. A controlled study

Abstract:

OBJECTIVE: To determine the proportion of adults with fibromyalgia syndrome (FMS) in the general population who also meet the 1988 Centre for Disease Control (CDC) criteria for chronic fatigue syndrome (CFS).

METHODS: Seventy-four FMS cases were compared with 32 non-FMS controls with widespread pain and 23 with localized pain, all recruited in a general population survey.

RESULTS: Among females, 58.0% of fibromyalgia cases met the full criteria for CFS, compared to 26.1% and 12.5% of controls with widespread and localized pain, respectively (p=0.0006). Male percentages were 80.0, 22.2, and zero, respectively (p=0.003). Compared to those with FMS alone, those meeting the case definitions for both FMS and CFS reported a worse course, worse overall health, more dissatisfaction with health, more non-CFS symptoms, and greater disease impact. The number of total symptoms and non-CFS symptoms were the best predictors of co-morbid CFS.

CONCLUSIONS: There is significant clinical overlap between CFS and FMS.

 

Source: White KP, Speechley M, Harth M, Ostbye T. Co-existence of chronic fatigue syndrome with fibromyalgia syndrome in the general population. A controlled study. Scand J Rheumatol. 2000;29(1):44-51. http://www.ncbi.nlm.nih.gov/pubmed/10722257

 

Idiopathic chronic fatigue and chronic fatigue syndrome: a comparison of two case-definitions

Abstract:

The aim of the study was to compare the signs and symptoms of individuals meeting two different definitions of chronic fatigue syndrome (CFS). Ninety-four patients fitting the eligibility criteria for idiopathic fatigue were enrolled into the study. Of the 94 patients, 48 met the 1988 definition of CFS, 20 the 1994 (but not the 1988) definition of CFS, and 26 met neither definition.

The 1994 defined cases were more likely than 1988 defined cases, and non-syndromal individuals to be male, married, and high school educated. The 1994 cases were less likely than 1988 cases to present acute onset, self reported sore throat, mild fever lymphadenopathy, pharyngitis.

In conclusion, the 1994 criteria increased the number of patients classified as CFS; however, those who fit only the 1994 criteria were less likely to have an acute symptomatic onset and signs and symptoms suggestive of an infectious process.

 

Source: Arpino C, Carrieri MP, Valesini G, Pizzigallo E, Rovere P, Tirelli U, Conti F, Dialmi P, Barberio A, Rusconi N, Bosco O, Lazzarin A, Saracco A, Moro ML,Vlahov D. Idiopathic chronic fatigue and chronic fatigue syndrome: a comparison of two case-definitions. Ann Ist Super Sanita. 1999;35(3):435-41. http://www.ncbi.nlm.nih.gov/pubmed/10721210

 

Developing case definitions for symptom-based conditions: the problem of specificity

Symptom-based conditions are postulated organic diseases that are characterized primarily by chronic physical (somatic) symptoms (1, 2). Contemporary conditions associated with multisystem complaints are generally referred to as chronic fatigue syndrome, fibromyalgia, multiple chemical sensitivities, silicone associated atypical rheumatic disease, sick building syndrome, and most recently, Gulf War syndrome (table 1). Possibly related disorders that will not be considered in the following analysis include epidemic neuromyasthenia, hyperventilation syndrome, reactive hypoglycemia, post-lyme disease syndrome, and irritable bowel syndrome (3).

Although the need to consistently define symptombased conditions has been repeatedly emphasized, there has been limited progress in establishing widely accepted diagnostic criteria (1,4). Based on reports in English-language publications, symptom-based conditions were analyzed to determine why it has been difficult to develop case definitions of unique diseases.

You can read the rest of this article here: http://epirev.oxfordjournals.org/content/20/2/148.long

 

Source: Hyams KC. Developing case definitions for symptom-based conditions: the problem of specificity. Epidemiol Rev. 1998;20(2):148-56. http://epirev.oxfordjournals.org/content/20/2/148.long (Full article)

Chronic fatigue and chronic fatigue syndrome: shifting boundaries and attributions

Abstract:

The subjective symptom of “fatigue” is one of the most widespread in the general population and is a major source of healthcare utilization. Prolonged fatigue is often associated with neuropsychological and musculoskeletal symptoms that form the basis of several syndromal diagnoses including chronic fatigue syndrome, fibromyalgia, and neurasthenia, and is clearly not simply the result of a lack of force generation from the muscle.

Current epidemiologic research in this area relies predominantly on self-report data to document the prevalence and associations of chronic fatigue. Of necessity, this subjective data source gives rise to uncertain diagnostic boundaries and consequent divergent epidemiologic, clinical, and pathophysiologic research findings.

This review will highlight the impact of the case definition and ascertainment methods on the varying prevalence estimates of chronic fatigue syndrome and patterns of reported psychological comorbidty. It will also evaluate the evidence for a true postinfective fatigue syndrome.

 

Source: Lloyd AR. Chronic fatigue and chronic fatigue syndrome: shifting boundaries and attributions. Am J Med. 1998 Sep 28;105(3A):7S-10S. http://www.ncbi.nlm.nih.gov/pubmed/9790475