FRESH PERSPECTIVES
Figure 3 - PCA analysis; Preprocessing: 2nd Derivative (Filter Width = 15, 2nd order polynomial), SNV, Mean Center at ranges of 650 – 840 cm-1
and 1480 to 1780 cm-1
Figure 5 - Calibration and validation results of model – Y-axis shows the model-estimated probability that a given sample belongs to the Placebo class.
Figure 4 - PLSDA; Preprocessing: 2nd Derivative (Filter Width = 15, 2nd order polynomial), SNV, Mean Center at ranges of 650 – 840 cm-1
and 1480 to 1780 cm-1
Figure 6 - Predicted Sample Results – scores on LVs 1 & 2
7). As demonstrated, the actives and placebos were accurately classifi ed, demonstrating reproducible results across multiple products, for both tablets and capsules.
ellipses demonstrated that the placebo and active separation were within the error of the model.
Finally, model robustness was challenged with the addition of two new products. In this case, the added products and placebos shared the same unit formulation, and the placebo formulations were signifi cantly diff erent from the placebos included in the model. The model was unable to distinguish the placebos from their respective actives (Figure 8), and classifi ed the placebos as actives. The unit formula for the new placebos included an excipient spectral peak at approximately 790 cm-1
that was
not consistent with the placebos included in the model and consequently, the excipient peak was interpreted as an active by the model (Figure 9). Further refi nement of the model by removing the excipient spectral peaks
63 American Pharmaceutical Review | Fresh Perspectives 2013
associated with the new samples was not successful in accurately modeling the new data. Other model preprocessing parameters were also introduced (baseline correction, MSC, etc) without success.
In addition, as shown in (Figure 6), 95% confi dence
Because the model was not successful at properly classifying the new materials, a diff erent modeling approach was required. Based in part on some earlier success1 this approach.
with hierarchical models, it was decided to investigate
Hierarchical, or layered, models can be used to simplify a classifi cation problem that is too complex to accurately resolve with simple standard linear models. Rather than attempt to separate all classes at once using a single model (one versus many), the problem is broken down into multiple steps. At each step, simple models are used to identify and eliminate either obviously-diff erent classes, or to separate the possibilities into natural groups of classes. Subsequent steps (branches) use additional models to separate the remaining class possibilities further until all classes have been separated. By eliminating possible classes at each step, the requirements for subsequent models are simplifi ed, thereby improving accuracy.
1 IFPAC 2013 Presentation – Enhanced Classifi cation Using Fused Data, Michael Dotlich, Eli Lilly, Bob Roginski, Jeremy Shaver, Eigenvector Research
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80 |
Page 81 |
Page 82 |
Page 83 |
Page 84 |
Page 85 |
Page 86 |
Page 87 |
Page 88 |
Page 89 |
Page 90 |
Page 91 |
Page 92