Classification of pregnancies of unknown location according to four different hCG-based protocols

Abstract

STUDY QUESTION: How do four protocols based on serial human chorionic gonadotropin (hCG) measurements perform when classifying pregnancies of unknown location (PULs) as low or high risk of being an ectopic pregnancy (EP)?SUMMARY ANSWER: The use of cut-offs in hCG level changes published by NICE, and a logistic regression model, M4, correctly classify more PULs as high risk, compared with two other protocols.WHAT IS KNOWN ALREADY: A logistic regression model, M4, based on the mean of two consecutive hCG values and the hCG ratio (hCG 48 h/hCG 0 h) that classify PULs into low-and high-risk groups for triage purposes, identifies more EPs than a protocol using the cutoffs between a 13% decline and a 66% rise in hCG levels over 48 h. STUDY DESIGN, SIZE, DURATION:A retrospective comparative study of four different hCG-based protocols classifying PULs as low or high risk of being an EP was performed at a gynaecological emergency unit over 3 years. PARTICIPANTS/MATERIALS, SETTING, METHOD:We identified 915 women with a PUL. Initial transvaginal ultrasonography (TVS) findings categorised 187 of the PULs as probable intrauterine pregnancies (IUPs) and 16 as probable EPs. The rate of change in hCG levels over 48 h was calculated for each patient and subjected to three different hCG threshold intervals and a logistic regression model for outcome prediction. Each PUL was subsequently dichotomised to either low-risk (i.e. failed PUL/IUP) or high-risk (i.e. EP) classification, which allowed us to compare the diagnostic performance. In 'Protocol A', a PUL was classified as low risk if >13% hCG level decline or >66% hCG level rise was achieved; otherwise, the PUL was classified as high risk of being an EP. 'Protocol B' classified a PUL as low or high risk using cut-offs of 35-50% declining hCG levels and of 53% rising hCG levels. Similarly, 'Protocol C' used hCG level cut-offs published by NICE, 50% for declining hCG levels and 63% for rising hCG levels. Finally, if a logistic regression model 'Protocol M4' calculated a ≥5% risk of the PUL being an EP, it was classified as high risk, and otherwise the PUL was classified as low risk. When the time interval between two hCG measurements failed to meet an exact 48 h, extrapolation and interpolation of hCG values was made, using log linear transformation.MAIN RESULTS AND THE ROLE OF CHANCE: Protocols A, B, C and M4 classified 73, 66, 55 and 56% of PULs as low risk. The sensitivity for protocols A, B, C and M4 was 68% (95% confidence interval (CI) 61-75%), 81% (74-86%), 87% (82-92%) and 88% (83-93%), respectively. The specificity was 82% (80-85%), 77% (74-80%), 66% (62-69%) and 67% (63-70%) for protocols A, B, C and M4, respectively. All comparisons of sensitivity and specificity between the protocols were statistically significant except for protocol C versus protocol M4. In protocol C, 87% (66-97%) of misclassified EPs had rising hCG levels, compared with 19% (6-41%) for protocol M4 (P < 0.01). In a secondary analysis excluding probable IUPs and probable EPs, the results for 712 PULs ...

The clinical outcome of pregnancies of unknown location: an audit of 112 cases

“…Appropriately rising bHCG can be used as a predictor of IUPs, but IUPs represent only a modest proportion of PULs (13% in our series) . Mathematical modelling has been used in research and clinical settings, not necessarily to stratify precise outcome, but to stratify women to high‐ and low‐risk groups for the purpose of streamlining early pregnancy clinics and reducing the burden of repeat examinations …”

“…16,17 Mathematical modelling has been used in research and clinical settings, not necessarily to stratify precise outcome, but to stratify women to high-and low-risk groups for the purpose of streamlining early pregnancy clinics and reducing the burden of repeat examinations. 3,[18][19][20][21][22] Because of the inherent diagnostic uncertainty, women with PUL have a very high rate of reinvestigation with serial bHCG and transvaginal sonography. 4 In our series of 112 women with PUL, a total of 175 transvaginal ultrasound examinations were required, with 15 (10%) women requiring three ultrasound visits, at least three set of blood tests, and three clinic visits before a final clinical outcome was reached.…”

Hematological and Biochemical Changes Associated with Ectopic Pregnancy in Jazan Area Saudi Arabia

“…On the other hand, the level of β-hCG considered the first and important indicator of EP [23] . The decrease in β-hCG in both ruptured and non-rupured TEP should be considered, as, Fistouris et al [24] classified Ep to low and high risk according to the percentage of decline in β-hCG. The increase in the level of β-hCG in ruptured TEP than non-ruptured is in agreement with Di Marchi et al [25] .…”

External validation of risk prediction model M4 in an Australian population: Rationalising the management of pregnancies of unknown location

“…This model has been externally validated in the UK, 11 the United States and Sweden. 12,13 According to a recent systematic review and meta-analysis, 14 M4 has the overall best performance of all models, with an area under receiver-operator characteristics curve of 0.87 for EP, 0.84 for failing PUL, and 0.86 for ongoing PUL. Furthermore, M4 has been demonstrated to be safe with a 2% incidence of adverse events and no serious adverse events observed in a multicentre prospective study.…”

“…This model has been externally validated in the UK, 11 the United States and Sweden 12,13 . According to a recent systematic review and meta‐analysis, 14 M4 has the overall best performance of all models, with an area under receiver‐operator characteristics curve of 0.87 for EP, 0.84 for failing PUL, and 0.86 for ongoing PUL.…”