T 0582/15 (Automated treatment of brain imbalance I/CNS) of 14.3.2018

Summary of Facts and Submissions

I. The appeal is against the decision of the examining division to refuse the present European patent application, divided from its parent application EP 01908996.0, on the grounds of added subject-matter (Articles 76(1) and 123(2) EPC) and lack of inventive step (Article 56 EPC), having regard to the disclosure of

D2: E.R. John: "Principles of Neurometrics", American Journal of EEG Technology, pp. 251-266, December 1990.

II. With the statement setting out the grounds of appeal, the appellant filed amended sets of claims according to a main request and first and second auxiliary requests. It requested that the examining division's decision be set aside and that a patent be granted on the basis of one of the above claim requests. In addition, oral proceedings were requested as an auxiliary measure.

III. In a communication annexed to the summons to oral proceedings pursuant to Article 15(1) RPBA, the board gave its preliminary opinion on the appeal. In particular, it raised objections under Articles 76(1), 123(2), 84 and 83 EPC, and indicated that all the claim requests on file appeared to lack inventive step (Article 56 EPC), mainly having regard to D2.

IV. With a letter of reply dated 12 March 2018 (i.e. two days before the scheduled oral proceedings), the appellant indicated that it would not be attending the oral proceedings. It did not submit any comments on the substance of the board's communication either.

V. Oral proceedings were held as scheduled on 14 March 2018 in the absence of the appellant. The board established from the file that the appellant's final requests were that the decision under appeal be set aside and that a patent be granted on the basis of the main request or, subsidiarily, on the basis of either of the first and second auxiliary request, all requests as submitted with the statement setting out the grounds of appeal filed on 6 March 2015.

After due deliberation on the basis of those final requests and the written submissions, the board's decision was announced at the end of the oral proceedings.

VI. Claim 1 of the main request reads as follows:

"A method for predicting a response to a treatment therapy regime, the method comprising:

using a treatment-response database that has (a) a plurality of multivariate Z scores related to clinical manifestations of a symptomatic reference population, said population comprising a plurality of

medication-free subjects diagnosed with a plurality of psychiatric imbalances, wherein said plurality of multivariate Z scores is derived from EEG/QEEG information, and (b) a plurality of known medication response profiles for a plurality of therapy regimens associated with said multivariate Z scores of said plurality of medication-free subjects;

using a rule based classifier to compare a plurality of pretreatment multivariate Z scores derived from EEG/QEEG information from a patient with the said plurality of multivariate Z scores in the

treatment-response database, and

predicting a response to at least one of said plurality of therapy regimens for said patient based on said comparison of the patient multivariate Z scores and the database multivariate Z scores."

Claim 1 of the first auxiliary request reads as follows (amendments to claim 1 of the main request highlighted by the board):

"A method for predicting a response to a treatment therapy regime, the method comprising:

using a treatment-response database that has (a) a plurality of multivariate Z scores related to clinical manifestations of a symptomatic reference population, said population comprising a plurality of

medication-free subjects diagnosed with a plurality of psychiatric imbalances, wherein said plurality of multivariate Z scores are derived from EEG/QEEG information, and (b) a plurality of known medication response profiles for a plurality of drug therapy regimens associated with said multivariate Z scores of said plurality of medication-free subjects;

[deleted: using a rule based classifier to compare] comparing a plurality of pretreatment multivariate Z scores derived from EEG/QEEG information from a patient with the said plurality of multivariate Z scores in the treatment-response database, and

predicting a response to at least one of said plurality of said drug therapy regimens for said patient based on said comparison of the patient multivariate Z scores and the database multivariate Z scores."

Claim 1 of the second auxiliary request reads as follows (amendments to claim 1 of the first auxiliary request indicated by the board):

"A method for predicting a response to a treatment therapy regime, the method comprising:

using a treatment-response database that has (a) a plurality of multivariate Z scores related to clinical manifestations of a symptomatic reference population, said population comprising a plurality of

medication-free subjects diagnosed with a plurality of psychiatric imbalances, wherein said plurality of multivariate Z scores are derived from EEG/QEEG information, and (b) a plurality of known medication response profiles for a plurality of drug therapy regimens associated with said multivariate Z scores of said plurality of medication-free subjects;

comparing a plurality of pretreatment multivariate Z scores derived from EEG/QEEG information from a patient with the said plurality of multivariate Z scores in the treatment-response database;

identifying multivariate Z scores in the

treatment-response database that match the pretreatment multivariate Z scores derived from EEG/QEEG information from a patient;

identifying at least one candidate medication for the patient based on the known medication responses in the treatment response database for the matched multivariate Z scores, and

predicting a response to said at least one [deleted: of said] [deleted: plurality of said drug therapy regimens for said patient] candidate medication based on said comparison of the patient multivariate Z scores and the database multivariate Z scores."

Reasons for the Decision

1. Non-attendance of the appellant at oral proceedings

1.1 The appellant decided not to attend the scheduled oral proceedings before the board (cf. point IV above). Pursuant to Article 15(3) RPBA, the board is not "obliged to delay any step in the proceedings, including its decision, by reason only of the absence at the oral proceedings of any party duly summoned who may then be treated as relying only on its written case."

1.2 In the present case, the appellant did not respond in substance to the objections raised in the board's communication under Article 15(1) RPBA. So, in the exercise of its discretion under Article 15(3) RPBA, the board took a decision at the end of the oral proceedings, in the absence of the duly summoned appellant.

2. MAIN REQUEST

Claim 1 comprises the following features, as labelled by the board:

A method for predicting a response to a treatment therapy regime, the method comprising:

A) using a treatment-response database that has

A1) a plurality of multivariate Z scores related to clinical manifestations of a symptomatic reference population, said population comprising a plurality of medication-free subjects diagnosed with a plurality of psychiatric imbalances, wherein said plurality of multivariate Z scores is derived from EEG/QEEG information,

A2) a plurality of known medication response profiles for a plurality of therapy regimens associated with said multivariate Z scores of said plurality of medication-free subjects;

B) using a rule-based classifier to compare a plurality of pretreatment multivariate Z scores derived from EEG/QEEG information from a patient with said plurality of multivariate Z scores in the treatment-response database;

C) predicting a response to at least one of said plurality of said therapy regimens for said patient based on said comparison of the patient multivariate Z scores and the database multivariate Z scores.

2.1 Added subject-matter (Articles 76(1) and 123(2) EPC)

In reaction to the objections raised under Articles 76(1) and 123(2) EPC in the decision under appeal (see Reasons 2), claim 1 was amended with the statement setting out the grounds of appeal so as to further specify that the multivariate Z scores are derived from EEG (electro-encephalography) or QEEG (quantitative electro-encephalography) information. The board, however, holds that claim 1 still infringes Articles 76(1) and 123(2) EPC, for the reasons set out below.

2.1.1 Claim 1 is evidently based on the embodiment relating to "Treating Physiologic Brain Imbalance" (cf. page 23, line 21 to page 27, line 9 and page 4, lines 10-26 of the present and parent applications as originally filed).

2.1.2 As to feature A1) of claim 1, the present and parent applications as filed teach that the treatment-response database (i.e. "Outcomes Database" or "symptomatic database") not only contains the corresponding multivariate Z scores but also "the treatment modalities that convert the abnormal multivariate Z scores of these patients to normal" (cf. page 25, lines 10-13). Hence, feature A1) amounts to an intermediate generalisation of the present and parent application's original content.

2.1.3 As to feature B), the present and parent applications as filed indicate that the "rule-based classifier" associates the current patient study with data of patients with known abnormalities and medication responses (cf. Fig. 1, step k) and may review pretreatment EEG/QEEG information from each study patient (cf. page 44, lines 1-3). However, there is no disclosure as to any comparison whatsoever of a patient's pretreatment multivariate Z scores derived from EEG/QEEG information with the multivariate Z scores in the treatment-response database. Accordingly, feature B) constitutes an unallowable extension of the present and parent application's original content.

2.1.4 Lastly, as to feature C), the present and parent applications as filed teach merely that the probability that a patient will respond to different types of medication is established (cf. page 25, lines 19-20). However, it cannot be directly and unambiguously derived that a patient's therapy response is actually predicted based on a comparison of patient and database multivariate Z scores. Thus, feature C) gives rise to an unallowable limitation of the original content.

2.1.5 The appellant did not comment on the above objections indicated in the board's communication under Article 15(1) RPBA.

2.2 As a consequence, in view of the above deficiencies under Articles 76(1) and 123(2) EPC alone, the board concludes that the main request is not allowable.

3. AUXILIARY REQUESTS

3.1 Given that claim 1 of the first and second auxiliary requests still includes features A1) and C) in unamended form, the objections set out in points 2.1.2 and 2.1.4 above clearly also apply to the present auxiliary requests.

3.2 Hence, the first and second auxiliary requests are likewise not allowable under Articles 76(1) and 123(2) EPC.

Order

For these reasons it is decided that:

The appeal is dismissed.