Important note: Springer Nature is the only authorised publisher of the paper mentioned below. Moreover, the full content of the paper is available only to subscribers, or to non-subscribers for a small charge by the publisher. Thus, as authors, we would like to ask the Award Committee not to make the paper publicly available in its entirety but to use the attached copy of the manuscript for the sole purpose of assessing the suitability of our results to be human-competitive. 
 
1. 
Title of the first paper: “A novel hybrid algorithm for aiding prediction of prognosis in patients with hepatitis.

2. 

   Name: Mr Luca Parisi
   Mailing address: 20 Symonds Street, Grafton, Auckland 1010, New Zealand.
   E-mail address: luca.parisi@ieee.org.
   Phone number: +39 3395901660.

   Name: Mr Narrendar RaviChandran
   Mailing address: 20 Symonds Street, Grafton, Auckland 1010, New Zealand.
   E-mail address: narrendar@ieee.org.
   Phone number: +64 223917812.

   Name: Ms Marianne Lyne Manaog
   Mailing address: 4 Colonel Barton Glade, St Johns, Auckland 1072, New Zealand.
   E-mail address: marianne@medintellego.com.
   Phone number: +64 223917807.

3. Mr Luca Parisi  

4. 
Abstract of the first paper:

This study investigated the application of a novel hybrid artificial intelligence (AI)-based classifier for aiding prediction of the prognosis in patients with chronic hepatitis. Nineteen biomarkers on 155 patients with hepatitis from the University California Irvine Machine Learning repository were used as input data. Weights derived by applying the geometric margin maximisation criterion of a Lagrangian support vector machine (LSVM) were used for selecting the features associated with the highest relative importance towards the required classification, i.e. to predict whether a patient with hepatitis would have survived or died. Thus, the 19 initial features were reduced to the 16 most important prognostic factors and were fed into various AI-based classifiers. Results indicated an overall classification accuracy and area under the receiver operating characteristic curve of 100% for the proposed hybrid algorithm, the LSVM multilayer perceptron (MLP), thus demonstrating its potential for aiding prediction of prognosis in patients with hepatitis in a clinical setting.

5.
List relative to the first paper: A, B and E.

6. The international scientific community, along with the editors and reviewers involved in the assessment of our paper for publication in the Springer Nature journal, our institutions (both in academia and industry) and colleagues working with Artificial Intelligence (AI)-based classifiers thankfully judged our contributions as achieving:
a considerable improvement over a patented invention, i.e., the Lagrangian Support Vector Machine (LSVM, link to the patent: https://patents.google.com/patent/US7395253B2/en), which was 84.78% accurate in predicting the prognosis of patients with hepatitis when using the same benchmark data set, as opposed to 100% accuracy of the proposed hybrid algorithm, i.e., LSVM-MLP. To further support this finding, the novel algorithm (LSVM-MLP) was also tested on an additional benchmark data set on similar prognostic data and resulted to be 97.70% accurate;
an equal result to the only one that reached 100% accuracy on the same benchmark data set in the literature but with a reduced computational cost, i.e., the study of Kaya Y. and Uyar M. (2013, "A hybrid decision support system based on rough set and extreme learning machine for diagnosis of hepatitis disease." Appl Soft Comput, 13(8): pp. 3429-3438);   
an equal result to the most recent human-created solution (the study of Kaya and Uyar in 2013, as cited above) to the long-standing problem of predicting survival in patients with chronic hepatitis for which there has been a succession of increasingly better human-created solutions, e.g., 
   	- Tan KC, Teoh EJ, Yu Q, Goh KC (2009). A hybrid evolutionary algorithm for attribute selection in data mining. Expert Syst Appl, 36(4):8616–8630: 89.67% classification accuracy via a Genetic Algorithm (GA)-SVM;
   	- Calisir D, Dogantekin E (2011) A new intelligent hepatitis diagnosis system: PCA–LSSVM. Expert Syst Appl, 38(8):10705–10708: 96.12% classification accuracy via a PCA-LSSVM;
	- Afif MH, Hedar AR, Hamid THA, Mahdy YB (2013) SS-SVM (3SVM): a new classification method for 	hepatitis disease diagnosis. Int J Adv Comput Sci Appl, 4(2):54–58: 98.75% classification accuracy via a SS-SVM;
	- Kaya Y, Uyar M (2013) A hybrid decision support system based on rough set and extreme learning machine for diagnosis of hepatitis disease. Appl Soft Comput, 13(8):3429–3438: 100% classification accuracy via a RS-ELM.
  
7.
Full citation of the paper: Parisi, L., RaviChandran, N. & Manaog, M.L. (2019). A novel hybrid algorithm for aiding prediction of prognosis in patients with hepatitis. Neural Comput & Applic. https://doi.org/10.1007/s00521-019-04050-x.

8. 
Any monetary prize, if any, is to be divided equally amongst the three co-authors, i.e., LP, NR, MLM.

9. 
We expect to be the 'best' by virtue of the outstanding contribution that, as researchers in the field of Machine Learning for Decision Support Systems, we believe to have given to the scientific community via our study. Not only we improved on results achieved by a patented algorithm, i.e., the LSVM, on the same benchmark data set but we demonstrated the usefulness of the novel hybrid algorithm we created (LSVM-MLP) as applied to the particular clinical problem of predicting the prognosis of patients with hepatitis with a relatively computationally inexpensive algorithm. 

10. 
The hybrid algorithm developed and tested in our study is a type of LCS (learning classifier system). In particular, we coupled the Lagrangian Support Vector Machine and the Multi-Layer Perceptron in a novel, augmented hybrid classifier.

11. 
Paper of Parisi et al., 2019: 31 January 2019 (available online)