Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Predictive”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,081 records · Page 60Linked to original sources
PubMed2002

Improving the prediction of outcome in severe acute closed head injury by using discriminant function analysis of normal auditory brainstem response latencies and amplitudes.

OBJECT: The auditory brainstem response (ABR) is a useful addition to standard medical measures for predicting outcome in patients with severe acute closed head injury (ACHI). Limiting this success, however, is the poor predictive value of a so-called "normal" ABR. In this study the authors used discriminant function analysis (DFA) of ABR Wave I, III, and V latencies and amplitudes to improve the predictive accuracy of the normal ABR, both as a single measure and in combination with other standard medical measures. METHODS: The DFAs were conducted using the ABR and medical results in 68 patients with severe ACHI (30 who died [ACHI-died], and 38 who survived [ACHI-lived]) who presented with normal ABR responses in the neurosurgical intensive care unit of the authors' hospital in Johannesburg. All patients had undergone surgery to remove an intracranial hematoma. Correct predictions of outcome by ABR DFA measures were 83% for the ACHI-died group (48% at > or = 90% confidence level) and 87% for the ACHI-lived group (71% at > or = 90% confidence level); by medical DFA measures the correct predictions were 83% for the ACHI-died group (96% at >; or = 90% confidence level) and 95% for the ACHI-lived group (94% at > or = 90% confidence level); and by combined ABR and medical DFA measures correct predictions were 100% for the ACHI-died group (100% at > or = 90% confidence level) and 97% for the ACHI-lived group (100% at > or = 90% confidence level). CONCLUSIONS: The DFA of ABR Wave I, III, and V latencies and amplitudes improved the predictive ability of normal ABR results to rates similar to those obtained using DFA for the medical measures, although at lower confidence levels. The DFA of the combined ABR and medical measures improved correct predictions to rates significantly higher than for either of the measures on its own.

Acute Disease↗
PubMed1994

Lower anion gap increases sensitivity in predicting elevated lactate.

OBJECTIVE: The normal reference range for the anion gap (AG) has recently been questioned by several authors. Lowering the upper limit of normal of the AG has been found to be more sensitive in predicting elevated lactate in critically ill adults. The objectives of this study are i) to define a new upper limit of normal of the AG in a study population of healthy adult volunteers, ii) to determine the sensitivity, specificity, the positive predictive value and the negative predictive value of the new upper limit for AG in detecting elevated lactate in critically ill children and to compare these results to the old upper limit of normal of AG (16 mmol/l), iii) to construct a receiver-operating-characteristic (ROC) curve for anion gap as a predictor of elevated lactate, iv) to determine the relationship between anion gap and serum lactate levels in critically ill patients. DESIGN: A prospective, cohort study. SETTING: Paediatric Intensive Care Unit of a University Hospital. SUBJECTS: Part I: Convenience sample of healthy adult volunteers to provide a reference range for anion gap calculation. Part II: Consecutive children admitted to the Paediatric Intensive Care Unit who had lactate levels measured for clinical reasons. MEASUREMENTS: Part I: Electrolytes and blood gases were measured from blood samples drawn from 25 adult volunteers. The reference range for AG was calculated using the equation, AG = Na - (Cl + HCO3). The upper limit of normal was calculated as mean + 2 SD. Part II: Eligible ICU patients were included in this study if they had lactate, electrolytes and blood gases obtained simultaneously. The AG was calculated as above. The new upper limit of normal AG was compared to an AG of 16 for diagnosing an elevated plasma lactate. RESULTS: The mean anion gap in the normal population was 9.4 +/- 1 mmol/l with 11 mmol/l being used as the new upper limit of normal. Thirty-six ICU patients had 189 arterial blood samples from which lactate, electrolytes and blood gas were measured simultaneously. The sensitivity, specificity, positive predictive value and negative predictive value of using an AG of 11 mmol/l as the upper limit of normal were 86%, 40%, 65% and 69% respectively, compared to 49%, 84%, 80% and 55% respectively using the upper limit of normal of AG of 16 mmol/l. The ROC curve supported lowering the upper limit of normal for the anion gap to predict an elevated lactate. There was a linear relationship between anion gap and serum lactate levels. CONCLUSIONS: An AG of 11 mmol/l as the upper limit of normal has a higher sensitivity and higher negative predictive value but lower specificity and lower positive predictive value for detecting elevated lactate in critically ill children.

Acid-Base Equilibrium↗
PubMed2000

Isolated demyelinating syndromes: comparison of different MR imaging criteria to predict conversion to clinically definite multiple sclerosis.

BACKGROUND AND PURPOSE: Various authors have developed criteria to classify MR imaging findings that suggest the possibility of multiple sclerosis. The purpose of this study was to evaluate and compare the capacity of three sets of MR imaging criteria for predicting the conversion of isolated demyelinating syndromes to clinically definite multiple sclerosis. METHODS: Seventy patients with clinically isolated neurologic symptoms suggestive of multiple sclerosis were prospectively studied with MR imaging. The MR imaging findings were evaluated by two independent neuroradiologists who were blinded to clinical follow-up data. Based on the clinical outcome at follow-up (presence of a second attack that established clinically definite multiple sclerosis), the sensitivity, specificity, accuracy, positive predictive value, and negative predictive value of the criteria proposed by Paty et al, Fazekas et al, and Barkhof et al were calculated. RESULTS: Clinically definite multiple sclerosis developed in 22 (31%) patients after a mean follow-up time of 28.3 months. The criteria proposed by Paty et al and those proposed by Fazekas et al showed identical results: sensitivity, 86%; specificity, 54%; accuracy, 64%; positive predictive value, 46%; and negative predictive value, 89%. The criteria proposed by Barkhof et al showed the following: sensitivity, 73%; specificity, 73%; accuracy, 73%; positive predictive value, 55%; and negative predictive value, 85%. CONCLUSION: The four dichotomized MR imaging parameters proposed by Barkhof et al are more specific and accurate than the criteria proposed by Paty et al or Fazekas et al for predicting conversion to clinically definite multiple sclerosis.

Adult↗
PubMed2002

Clinical pretreatment risk factors and Ga-67 scintigraphy early during treatment for prediction of outcome of patients with aggressive non-Hodgkin lymphoma.

BACKGROUND: Clinical pretreatment risk factors indicate the severity of disease in patients with aggressive non-Hodgkin lymphoma (NHL). Ga-67 scintigraphy during treatment is an early indicator of treatment-related features of lymphoma cells. The ability of risk factors and Ga-67 to predict disease outcome was compared in 139 patients with aggressive NHL. METHODS: Pretreatment clinical risk factors and Ga-67 scintigraphy performed after one cycle and at mid-treatment were evaluated for their correlation with response rate and as predictors of 5-year failure-free survival (FFS). Univariate analysis was performed to determine the ability of pretreatment risk factors and Ga-67 early during treatment to predict FFS. Subsequently, multivariate analysis was performed on the variables with significant univariate results using the Cox proportional hazards method. The predictive value of risk factors and Ga-67 scintigraphy was calculated to determine their suitability in selecting patients with poor outcome. RESULTS: Response rate correlated with stage of disease (P < 0.01) and the international prognostic index (IPI) score (P < 0.05). Five-year FFS was predicted by stage of disease (P < 0.004), performance status (P < 0.02), and the IPI score (P < 0.01). Response rate correlated with results of Ga-67 scintigraphy after one cycle of chemotherapy (P < 0.001) and at mid-treatment (P < 0.001). Five-year FFS was predicted by Ga-67 after one cycle of chemotherapy (P < 0.0004) and at mid-treatment (P < 0.0001). Positive Ga-67 after the first cycle of treatment predicted 64% of patients who had failure of treatment. A positive study at mid-treatment predicted 77% of patients who had treatment failure. Cox analysis showed Ga-67 after one course (P < 0.0012) and at mid-treatment (P < 0.0002) as being the most significant variables in predicting FFS. CONCLUSIONS: Ga-67 scintigraphy demonstrates early the effect of treatment in patients with aggressive NHL. It is a better predictor than pretreatment risk factors of both response rate and FFS. Positive Ga-67 early during treatment may be used as an independent test in selecting patients who will not respond favorably to current protocol treatment for early therapeutic modifications.

Adolescent↗
PubMed2002

Predicting fetal weight. Are Leopold's maneuvers still worth teaching to medical students and house staff?

OBJECTIVE: To assess the value of teaching Leopold's maneuvers to medical students and house staff physicians for the purpose of estimating term fetal weight. STUDY DESIGN: Forty-four patients between 37 and 42 weeks of gestation were asked to estimate their fetus's weight upon presentation for delivery. A medical student or house staff physician then performed Leopold's maneuvers to assess fetal weight manually. For comparison, a previously published birth weight prediction equation was used to calculate fetal weight based upon maternal and pregnancy-specific characteristics alone, and obstetric ultrasonography was performed to measure fetal biometric parameters for use with standard ultrasonic fetal weight prediction equations. RESULTS: House staff physicians performed significantly better than medical students in making fetal weight predictions to within +/- 10% of actual birth weight using Leopold's maneuvers (71% vs. 38%, P < .05). House staff who made tactile assessments of fetal weight were able to predict birth weight to within 15% of actual weight more often than mothers making estimations (P < .05), but medical students could not (P = .53). The correlation between predicted and actual birth weights was .60 for Leopold's maneuvers, .45 for maternal estimates of fetal weight, .55 for the birth weight prediction equation and .63 for the best of eight ultrasonic prediction equations tested. CONCLUSION: House staff physicians make more accurate predictions of term fetal weight using Leopold's maneuvers than do medical students. This is presumably due to the increased experience of house staff in using such tactile techniques. Leopold's maneuvers are a useful method of estimating fetal weight and should continue to be taught to both medical students and house staff.

Birth Weight↗
PubMed2002

Predictive values of serial C-reactive protein in neonatal sepsis.

BACKGROUND: Infection is one of the major problems in neonates. The diagnosis of neonatal septicemia is difficult to establish based on the clinical criteria alone. However, empirical treatment should not be delayed because of the high mortality. Laboratory tests used to support diagnosis have shown variable predictive values. C-reactive protein (CRP), an acute phase protein, increases in inflammatory disorders and tissue injury. Serial CRP have been shown to be more useful than a single measured CRP in the diagnostic evaluation of neonates with suspected infection. OBJECTIVES: 1. To evaluate the diagnostic accuracy of serial CRP in neonatal sepsis. 2. To compare the diagnostic values between CRP and leukocyte index from a complete blood count (CBC). METHOD: A prospective observational study included newborn infants, aged > 3 days and diagnosed with clinical sepsis, who were admitted in the newborn intensive care unit and special care nursery at Ramathibodi Hospital during a 14-months period. Newborn infants who received antibiotics prior to septic work up were excluded. CRP levels were measured initially at the time of septic work-up and at 24-48 hours later. Investigations for infection included CBC, blood culture and urine culture. Radiological study and lumbar puncture were performed if clinically indicated. Based on clinical and biological data, diagnosis of infants can be categorized into 4 groups as follows; (1) proven sepsis with positive culture, (2) localized infection with negative culture, (3) probable infection (clinically consistent with sepsis, negative culture without localized infection), and (4) no infection (findings not consistent with sepsis and antibiotics were discontinued within 3 days). Diagnosis was made before the CRP results were known. RESULTS: Of 76 newborn infants with 90 episodes of clinical sepsis, there were 24 episodes of proven sepsis, 11 episodes of localized infection with negative culture, 18 episodes of probable infection and 37 episodes of no infection. Serial CRP had better predictive values than those of CBC. The sensitivity, specificity, positive predictive value, and negative predictive value of CRP for proven sepsis and localized infection at cutoff point > or = 5 mg/L were 100 per cent, 94 per cent, 91.6 per cent and 100 per cent respectively. False positive CRP were found in post-operative patent ductus arteriosus ligation, intracerebral hemorrhage, and post resuscitation with chest compression. To improve the predictive value of CBC, analysis of the receiver operating characteristic (ROC) curve showed that the predictive value of CBC for sepsis would be enhanced by using abnormal leukocyte index 2 2 parameters. CONCLUSIONS: Predictive value of CRP could be enhanced by serial rather than a single measurement. Serial CRP showed very high predictive values for diagnosis of neonatal sepsis and were better than those of leukocyte indices of CBC.

C-Reactive Protein↗
PubMed2003

Artificial intelligence in predicting bladder cancer outcome: a comparison of neuro-fuzzy modeling and artificial neural networks.

PURPOSE: New techniques for the prediction of tumor behavior are needed, because statistical analysis has a poor accuracy and is not applicable to the individual. Artificial intelligence (AI) may provide these suitable methods. Whereas artificial neural networks (ANN), the best-studied form of AI, have been used successfully, its hidden networks remain an obstacle to its acceptance. Neuro-fuzzy modeling (NFM), another AI method, has a transparent functional layer and is without many of the drawbacks of ANN. We have compared the predictive accuracies of NFM, ANN, and traditional statistical methods, for the behavior of bladder cancer. EXPERIMENTAL DESIGN: Experimental molecular biomarkers, including p53 and the mismatch repair proteins, and conventional clinicopathological data were studied in a cohort of 109 patients with bladder cancer. For all three of the methods, models were produced to predict the presence and timing of a tumor relapse. RESULTS: Both methods of AI predicted relapse with an accuracy ranging from 88% to 95%. This was superior to statistical methods (71-77%; P < 0.0006). NFM appeared better than ANN at predicting the timing of relapse (P = 0.073). CONCLUSIONS: The use of AI can accurately predict cancer behavior. NFM has a similar or superior predictive accuracy to ANN. However, unlike the impenetrable "black-box" of a neural network, the rules of NFM are transparent, enabling validation from clinical knowledge and the manipulation of input variables to allow exploratory predictions. This technique could be used widely in a variety of areas of medicine.

Artificial Intelligence↗
PubMed2004

Prediction of maximal VO2 from a submaximal StairMaster test in young women.

The StairMaster 4000 PT is a popular step ergometer which provides a submaximal test protocol (SM Predicted VO(2)max) for the prediction of VO(2)max (ml.kg(-1).min(-1)). The purpose of this study was to evaluate the SM Predicted VO(2)max protocol by comparing it to results from a VO(2)max treadmill test in 20 young healthy women aged 20-25 years. Subjects were 10 step-trained (ST) women who had performed aerobic activities and exercised on a step ergometer for 20-30 minutes at least 3 times per week for the past 3 months, and 10 non-step-trained (NST) women who had performed aerobic activities no more than twice a week during the past 3 months and had no previous experience on a step ergometer. The SM Predicted VO(2)max protocol used 2 steady state heart rates between approximately 115-150 b.min(-1) to estimate VO(2)max. The Bruce maximal treadmill protocol (Actual VO(2)max) was used to measure VO(2)max by open circuit spirometry. Each subject performed both tests within a 7-day period. The means and standard deviations for the Actual VO(2)max tests were 39.8 +/- 6.1 ml.kg(-1).min(-1) for the ST group, 37.6 +/- 6.3 ml.kg(-1).min(-1) for the NST group, and 38.7 +/- 6.2 ml.kg(-1).min(-1) for the Total group (N = 20); and for the SM Predicted VO(2)max tests, means and standard deviations were 40.78 +/- 14.0 ml.kg(-1).min(-1), 30.9 +/- 4.8 ml.kg(-1).min(-1) and 35.9 +/- 11.4 ml.kg(-1).min(-1). There was no significant difference (p > 0.05) between the means of the Actual VO(2)max and SM Predicted VO(2)max test for the Total group (N = 20) or the ST group (n = 10), but a significant difference (p < 0.05) was shown for the NST group. The coefficient of determination (R(2)) and standard error of estimate (SEE) for the SM Predicted VO(2)max and Actual VO(2)max tests were R(2) = 0.18, SEE = 5.72 ml.kg(-1).min(-1) for the Total group; R(2) = 0.00, SEE = 6.68 ml.kg(-1).min(-1) for the NST group; and R(2) = 0.33, SEE = 5.32 ml.kg(-1).min(-1) for ST group. In conclusion, the SM Predicted VO(2)max test has acceptable accuracy for the ST group, but significantly underpredicted the NST group by almost 7 ml; and, as demonstrated by the high SEEs, it has a low level of precision for both ST and NST subjects.

Adult↗
PubMed2004

[Preoperative prediction of creatinine clearance by using serum creatinine].

BACKGROUND: Creatinine clearance (Ccr) is an efficient index of renal function. However, measurement of Ccr is not routinely performed for preoperative patients. To predict preoperative renal impairment, we estimated the preoperative Ccr by using serum creatinine (sCr) and other laboratory findings. METHODS: 702 patients served as the training samples and other 128 patients as the validation samples. (1) Values of sCr and BUN to predict lower Ccr levels were developed from the training samples. In the combination of sCr and BUN, we selected the optimal combination in receiver operating characteristics curve. This value was applied to the validation samples. (2) The predictive equation was derived from the training samples by multiple regression analysis, and it was compared with the equations previously reported. RESULTS: (1) The optimal sensitivity and specificity for predicting Ccr less than 30 ml x min(-1) x 1.48 m(-2) were 60% and 84%, respectively. (2) Among the equations to predict Ccr, our equation showed the highest correlation coefficient (r), and the smallest differences between predicted and measured Ccr. CONCLUSIONS: We determined the values of sCr and BUN to predict renal impairment and derived predictive equation. Our equation was the best to assess the preoperative renal function.

Blood Urea Nitrogen↗
PubMedDate not supplied

Antepartum prediction of respiratory distress syndrome: a comparison of the shake test, the tap test and the turbidity test.

The shake test, the tap test and the turbidity test were evaluated to determine their accuracy in predicting lung function maturity, ie their ability to predict respiratory distress syndrome (RDS). The turbidity test was the most efficient with a sensitivity of 60%, a specificity of 97%, a positive predictive value of 82% and a negative predictive value of 92%. The shake test had a sensitivity of 40%, a specificity of 95%, a positive predictive value of 63% and a negative predictive value of 88%. The tap test at 2 minutes had a sensitivity of 57%, a specificity of 78%, a positive predictive value of 35% and a negative predictive value of 89%. It was fortuitous that the simplest and cheapest test was found to be the most efficient test of the three. We recommend that the turbidity test or at least one of these tests should be used to determine the maturity of lung function when non-urgent elective deliveries are contemplated, to help reduce the incidence of RDS in this group of patients.

Amniotic Fluid↗
PubMed2005

Use of diagnosis-based risk adjustment models to predict individual health care expenditure under the National Health Insurance system in Taiwan.

BACKGROUND AND PURPOSE: Diagnostic information has been extensively studied and employed in the prediction of risk adjusted capitation payments in some countries. Nevertheless, few studies have been dedicated to the development of diagnosis-based risk adjusters in Taiwan. The purposes of this study were to develop outpatient diagnosis-based risk adjusters for a model of Taiwan's National Health Insurance (NHI) system and to evaluate the predictability of the risk adjustment models generated utilizing these adjusters. METHODS: Using a 2% random sample of 371,620 NHI enrollees, 5 risk adjustment models--i.e., demographic, inpatient diagnostic information outpatient diagnostic information, full diagnostic information, and prior utilization models--were evaluated with respect to predictive R2 and predictive ratios. While inpatient diagnosis-based risk adjusters were borrowed from previous research, outpatient diagnosis-based risk adjusters, referred to as Taiwan Ambulatory Spending Groups (TASGs), were developed based on 1996 claims data. RESULTS: The values of predictive R2 for the 5 risk adjustment models showed that the inclusion of outpatient diagnostic information considerably improved the predictability of the risk adjustment models for Taiwan's NHI system. Moreover, the predictive ratios revealed that the full diagnostic information model would reimburse different risk subgroups more fairly than the demographic, inpatient diagnostic information, and outpatient diagnostic information models and also outperform the prior utilization model with respect to disease risk groups. CONCLUSIONS: The risk adjustment model including the TASG risk adjusters can significantly improve predictability and can be employed to assess the NHI's current and proposed reform measures.

Capitation Fee↗
PubMed2005

Inter-species validation for domain combination based protein-protein interaction prediction method.

Domain Combination based Protein-Protein Interaction Prediction (DCPPIP) method is revealed to show outstanding prediction accuracy in Yeast proteins. However, it is not yet apparent whether the method is still valid and can achieve comparable prediction accuracy for the proteins in other species. In this paper, we report the validation results of applying the DCPPIP method for Fly and Human proteins. We also report the results of inter-species validation, in which protein interaction and domain data of other species are used as learning set. 10,351 interacting protein pairs are used for the validation for Fly, 2,345 protein pairs for Human. 80% of the data are used as learning sets and 20% are reserved as test sets. High prediction accuracies (Fly: sensitivity approximately 77%, specificity approximately 92%, Human: sensitivity approximately 96%, specificity approximately 95%) are achieved in both Fly and Human cases. Interactions of proteins in Human, Mouse, H. pylori, E. coli, and C. elegans are predicted and validated using the protein interaction and domain data in Yeast, Fly, and the combination of Yeast and Fly respectively. Again, good prediction accuracy is achieved when the test protein pair has common domains with the proteins in a learning set of proteins. A notion of Domain Overlapping Rate (DOR) among species is newly developed in this paper and the correlation between DOR and prediction accuracy is examined. According to out test results, there exists fairly obvious correlation between DOR and prediction accuracy.

Animals↗
PubMed1991

[Simplified prediction of postoperative lung function by plain chest roentgenogram in patients with primary lung cancer--in correlation to postoperative respiratory complications].

For the purpose of simplification of prediction of postoperative lung function, we studied to predict lung function by analizing the frontal and lateral view of chest plain roentgenogram and investigate the correlation to respiratory complication on 111 patients with lung cancer. According to TNM classification of lung cancer, prediction was performed as follows. Predicted postoperative lung function = [(42-number of resected subsegments)/(42-number of occupied subsegments)] x preoperative VC or FEV1.0. In this formula, 42 was the number of functioning subsegments of whole lung (right: 22, left: 20), and then preoperative occupied subsegments was ordered by T factor, where T1 lesion in lung field was prescribed as 1 subsegment and T2 was more than 2 subsegments respectively in plain chest roentgenogram. And also, on the patients having hilar lesions, it was required to calculate the number of subsegments in atelectasis, peripheral obstructive pneumonia and/or partial emphysematous change due to intrabronchial lesions. There was uniformly positive correlations in VC (R = 0.7949) and FEV1.0 (R = 0.8235) of the patients studied respectively. The patients having pneumonectomy showed tendency of over estimation, on the other hand, the patients having resection of a few segments showed under estimation. To predict the postoperative respiratory condition, we calculated the predicted post-operative %VC and %FEV1.0 for predicted preoperative normal VC and FEV1.0. Above the al, we tried to investigate the correlation with predicted postoperative %VC, %FEV1.0 and postoperative respiratory complications.(ABSTRACT TRUNCATED AT 250 WORDS)

Adult↗
PubMed1994

Appropriate use of predictive values in clinical decision making and evaluating diagnostic tests for TMD.

Temporomandibular disorder literature contains serious misunderstandings and misapplications of statistical concepts, including predictive values, in evaluating diagnostic modalities and in clinical decision making. The use of general population prevalence data for temporomandibular disorders to evaluate positive predictive values of diagnostic modalities is shown to be invalid. The positive predictive value of a diagnostic tool should not be used to evaluate the efficacy of the tool or to confirm the presence of temporomandibular disorders when the pretest likelihood of temporomandibular disorder is low (eg, 10%). In such a situation, the TMJ Scale's negative predictive value of 98% supports the dentist's clinical impression of the absence of temporomandibular disorders. When the pretest likelihood of TMD is high (eg, 90%), the TMJ Scale's positive predictive value of 97% supports the dentist's clinical impression of the presence of temporomandibular disorders. The predictive values of the subscales of the TMJ Scale that measure joint dysfunction and stress may be used to further refine the diagnostic impression. When the dentist is unsure of the presence of TMD and makes a pretest estimate of 50%, the TMJ Scale's positive predictive value of 81% and negative predictive value of 83% substantially improve the accuracy of clinical decisions.

Decision Support Techniques↗
PubMed1997

Clinical prediction rules. A review and suggested modifications of methodological standards.

BACKGROUND: Clinical prediction rules are decision-making tools for clinicians, containing variables from the history, physical examination, or simple diagnostic tests. OBJECTIVE: To review the quality of recently published clinical prediction rules and to suggest methodological standards for their development and evaluation. DATA SOURCES: Four general medical journals were manually searched for clinical prediction rules published from 1991 through 1994. STUDY SELECTION: Four hundred sixty potentially eligible reports were identified, of which 30 were clinical prediction rules eligible for study. Most methodological standards could only be evaluated in 29 studies. DATA ABSTRACTION: Two investigators independently evaluated the quality of each report using a standard data sheet. Disagreements were resolved by consensus. DATA SYNTHESIS: The mathematical technique was used to develop the rule, and the results of the rule were described in 100% (29/29) of the reports. All the rules but 1 (97% [28/29]) were felt to be clinically sensible. The outcomes and predictive variables were clearly defined in 83% (24/29) and 59% (17/29) of the reports, respectively. Blind assessment of outcomes and predictive variables occurred in 41% (12/29) and 79% (23/29) of the reports, respectively, and the rules were prospectively validated in 79% (11/14). Reproducibility of predictive variables was assessed in only 3% (1/29) of the reports, and the effect of the rule on clinical use was prospectively measured in only 3% (1/30). Forty-one percent (12/29) of the rules were felt to be easy to use. CONCLUSIONS: Although clinical prediction rules comply with some methodological criteria, for other criteria, better compliance is needed.

Decision Support Techniques↗
PubMed1997

Can goals of care be used to predict intervention preferences in an advance directive?

BACKGROUND: Some have suggested that advance directives elicit goals of care from patients, instead of or in addition to specific intervention preferences, but little is known about whether goals of care can be used in a meaningful way on documents or whether they can predict preferences for specific interventions. METHODS: Attending physicians (n = 716) at the Massachusetts General Hospital in Boston were surveyed to elicit general goals of care (eg, treat everything or comfort measures only) along with specific preferences for 11 medical, interventions in 6 scenarios. In each scenario, each goal was classified as an adequate predictor of acceptance or rejection of an intervention if its predictive value of the preference for that intervention was at least 80%. RESULTS: Goals varied with scenarios (P < .001) in a predictable manner. The goal treat everything was an adequate predictor of acceptance of each intervention, and comfort was an adequate predictor of rejection for nearly every intervention. Attempt cure adequately predicted acceptance of almost every nonaggressive intervention, but did not predict acceptance of aggressive interventions. Quality of life predicted rejection of aggressive interventions in 3 scenarios, but was not useful in other cases. When goals were predictors of preferences, the mean range of 95% confidence intervals for their predictive values was generally 20% or less. CONCLUSIONS: Goals have a valid role in advance directives, since the goal choices had a logical relationship to scenarios and intervention choices. However, the 2 goals attempt cure and choose quality of life were not predictive in many instances. If these findings hold true for more general populations of patients, then advance directive documents will need to rely on more than these general goal statements if they are to adequately represent patient preferences.

Acute Disease↗
PubMed1997

[Value of a predictive model of ambulatory blood pressure integrating physical activity].

OBJECTIVE: To determine how much of the variations of blood pressure during a 24 hour period could be accounted for by a change in activity and establish a predictive model. MATERIALS AND METHODS: Twenty three healthy subjects (mean age 25 +/- 2 years) were studied. The BP, heart rate (HR), and time of measure (T) were recorded by ambulatory BP monitoring using Spacelabs (4 measures per hour). At each measure the subject noted in a diary the degree of activity on a six level semi-quantitative scale. DATA ANALYSIS: A model was constructed using an analysis of covariance. Different parameters were added in succession to reach a model of the type P: P0 + A + beta + (HR-HR0) + H, were P = predicted systolic pressure, P0 = mean systolic BP over the 24 hours. A variation in systolic BP for activity level, beta = the slope of the regression between systolic BP and HR during activity A, and HR0 the mean HR during this activity. RESULTS: 1) In order to test the model, the values measured in one subject were compared to the predicted values from the model in 22 others. The procedure was then repeated for the other subjects. This common model predicted 41 +/- 21% of fluctuations in BP of the subject analysed with a range of 0 to 66%. 2) In order to refine the individual model two subjects were explored 7 times over 24 h of non consecutive days. The measures of the last recording were compared to the predicted values from the application of the model to the six preceding recordings. The model then predicted 81% and 66% of the BP values of the test day. The mean of the 24 hour individual difference over a one hour period between the measures and its predicted value by the model was 0.13 +/- 4.8 mmHg, and -0.75 +/- 7.7 mmHg. CONCLUSION: This study expresses in a quantitative fashion the importance of the level of activity in the evaluation of the level of ambulatory BP. The introduction of this method of quantification and analysis seems logical in therapeutic trial. The difference in the predictions by the model for some subjects poses the problem of uniform coding of activities and that of the recognition of other events such as stress and dreaming in sleep.

Adult↗
PubMed2026

The Progress of Gout Prediction Models Based on Multi-source Data.

INTRODUCTION: Gout, a highly serious inflammatory disease that is caused by monosodium urate crystals, is becoming an increasingly significant health concern. Artificial Intelligence and multi-omics-based research have made significant gains for the early detection and prevention of gout based on diverse approaches. This review intends to summarize current advances in forecasting gout susceptibility and gout-related symptoms, evaluate the predictive efficacy of different features, and ascertain which clinical and omics characteristics are most effective in these prediction models. METHODS: We explored the PubMed database after 2010 using keywords such as "gout", "predictive model", "risk prediction", and "machine learning", and confined our search to Englishlanguage articles. The original peer-reviewed research articles that developed gout models were selected. Research that was not original or lacked internal validation was excluded. RESULTS: Clinical features, genomics, microbiomics, radiomics, and metabolomics have been utilized to construct models related to gout and have demonstrated excellent predictive performance. Multisource data prediction models usually exhibit better effectiveness. DISCUSSION: Gout-oriented models performed excellently in predictive performance but present limitations in certain clinical and omics domains. However, if they are to affect actual patient care, they must overcome some external confirmation roadblocks and the fiscal and practical implications they will face ahead of time. CONCLUSION: This review indicates that clinical and multi-omics models of gout are significant instruments for clinical decision-making. The models constructed in these studies may be crucial for the treatment of gout and its practical benefits.

Gout↗