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

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 cut-offs 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 were analysed. The sensitivity subsequently remained stable for all protocols. Protocol M4 reached a 78% (74-81%) specificity, which was significantly higher than 70% (66-74%) for protocol C (P = 0.01) and protocol M4 classified 63% of PULs as low risk compared with 58% for protocol C.

LIMITATIONS, REASONS FOR CAUTION: The retrospective design of the study is a limitation. The results are derived from a population where laparoscopy played an important role in PUL management and diagnosis of EPs, although it did reflect real clinical practice. Although we tried to adhere to definitions of PUL and final outcomes as in previous studies and a recent consensus statement, potential differences in this regard must be acknowledged. Where the time interval between two serial hCG measurements deviated from 48 h we estimated 48 h hCG values.

WIDER IMPLICATIONS OF THE FINDINGS: A logistic regression model, M4, classifies more PULs correctly as low risk in a selected PUL population without probable IUPs and EPs and identifies as many EPs, in comparison with the cut-offs available in the NICE guideline. This advantage for model M4 may result in a reduction of unnecessary follow-up visits, when fewer low-risk PULs are misclassified as high risk. These findings, however, ought to be clarified in a randomised controlled trial.

STUDY FUNDING/COMPETING INTERESTS: The study was supported by LUA/ALF grant No. 70940. There are no competing interests.