DIGITAL BIOMARKER

Abstract

Aspects described herein relate to the field of disease tracking and diagnostics. Specifically, they relate to a method of assessing a muscular disability and, in particular, spinal muscular atrophy (SMA) in a subject comprising the steps of determining at least one parameter from a dataset of sensor measurements of the subject using a mobile device, and comparing the determined at least one parameter to a reference, whereby the muscular disability and, in particular, SMA will be assessed. Aspects described herein also relate to a mobile device comprising a processor, at least one pressure sensor and a database as well as software which is tangibly embedded to said device and, when running on said device, carries out the method of the invention as well as the use of such a device for assessing a muscular disability and, in particular, SMA.

Claims

1. A method of assessing spinal muscular atrophy (SMA) in a subject comprising the steps of: a) determining at least one parameter from a dataset of sensor measurements from said subject using a mobile device; and b) comparing the determined at least one parameter to a reference, whereby SMA is assessed from the result of the comparison.

2. The method of claim 1, wherein the said at least one parameter is a parameter indicative for distal motor function, central motor function, or axial motor function.

3. The method of claim 1, wherein the dataset of sensor measurements of the individual motor function comprises data from the measurement the maximal pressure which can be exerted by a subject with an individual finger or for the capability of exerting pressure with an individual finger over time, the measurement the maximal duration of the tone “aaah”, the maximal amount of touching the screen in a defined time period, in particular within 30 sec, the maximal double touch asynchronity, the variability of acceleration after wind, the number of a thing collected, in particular collected coins and/or the maximal turn speed of the hand.

4. The method of claim 1, wherein the dataset of sensor measurements of the individual motor function comprises data from the following feature measurements: i. mean pressure applied, ii. pitch variability, iii. median time to hit the screen, iv. double touch asynchronity, v. time to draw a shape, vi. maximum turning speed of the phone, vii. variability of acceleration (after wind), and/or viii. number of collected coins.

5. The method of claim 1, wherein the dataset of sensor measurements of the individual motor function comprises data from the following feature test: i. Ring the bell, ii. Cheer the monster, iii. Tap the monster, iv. Squeeze the tomato, v. Walk the trails, vi. Turn the phone, vii. Walk the rope, and/or viii. Collect the coins.

6. The method of claim 1, wherein the dataset of sensor measurements of the individual motor function comprises data from daily or at least from measurements of every other day, in particular wherein the dataset of sensor measurements of the individual motor function comprises data from sensor measurements obtained in the morning.

7. The method of claim 1, wherein said mobile device has been adapted for carrying out on the subject one or more of the sensor measurements referred to in claim 3.

8. The method of claim 1, wherein a determined at least one parameter being essentially identical compared to the reference is indicative for a subject with SMA.

9. A mobile device comprising a processor, at least one pressure sensor and a database as well as software which is tangibly embedded to said device and, when running on said device, carries out the method of claim 1.

10. A system comprising a mobile device comprising at least one pressure sensor and a remote device comprising a processor and a database as well as software which is tangibly embedded to said device and, when running on said device, carries out the method of claim 1, wherein said mobile device and said remote device are operatively linked to each other.

11. Use of the mobile device according to claim 9 for assessing SMA on a dataset of sensor measurements of the individual subject.

12. A combination of the method according to claim 1 with a pharmaceutical agent suitable to treat SMA in a subject, in particular a m7GpppX Diphosphatase (DCPS) Inhibitors, Survival Motor Neuron Protein 1 Modulators, SMN2 Expression Inhibitors, SMN2 Splicing Modulators, SMN2 Expression Enhancers, Survival Motor Neuron Protein 2 Modulators or SMN-AS1 (Long Non-Coding RNA derived from SMN1) Inhibitors, more particular Nusinersen, Onasemnogene abeparvovec, Risdiplam or Branaplam.

13. A pharmaceutical agent suitable to treat SMA in a subject, in particular a m7GpppX Diphosphatase (DCPS) Inhibitors, Survival Motor Neuron Protein 1 Modulators, SMN2 Expression Inhibitors, SMN2 Splicing Modulators, SMN2 Expression Enhancers, Survival Motor Neuron Protein 2 Modulators or SMN-AS1 (Long Non-Coding RNA derived from SMN1) Inhibitors, more particular Nusinersen, Onasemnogene abeparvovec, Risdiplam or Branaplam wherein the disease of the subject being treated is monitored with a method according to claim 1.

14. A method for the treatment of SMA, wherein the method comprise administering a m7GpppX Diphosphatase (DCPS) Inhibitors, Survival Motor Neuron Protein 1 Modulators, SMN2 Expression Inhibitors, SMN2 Splicing Modulators, SMN2 Expression Enhancers, Survival Motor Neuron Protein 2 Modulators or SMN-AS1 (Long Non-Coding RNA derived from SMN1) Inhibitors, more particular Nusinersen, Onasemnogene abeparvovec Risdiplam or Branaplarn to a subject and wherein the method further comprises a method according to claim 1 to monitor the disease of the subject.

15. A combination of the method according to claim 12, whereby a determined at least one parameter being better compared to the reference parameter of said patient before said subject received treatment with the pharmaceutical agent.

16. A computer-implemented method using machine learning to predict the MFM32 score of a subject suffering from SMA.

17. A computer-implemented method using machine learning to predict the FVC score of a subject suffering from SMA.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0177] FIG. 1A and FIG. 1B depict the illustrative screenshots and progression for a diagnostic test according to one or more illustrative aspects described herein. The user needs to select “Start” to begin the task.

[0178] FIG. 2 are plots illustrating various sensor feature results according to the diagnostic test depicted in FIG. 1A and FIG. 1B. Sensor feature (duration of the longest “aaah” in the test in seconds) results are in agreement with clinical anchor (forced volume vital capacity) in both studies.

[0179] FIG. 3A, FIG. 3B, and FIG. 3C depict the illustrative screenshots and progression for a diagnostic test according to one or more illustrative aspects described herein. The user needs to select “Start” to begin the task.

[0180] FIG. 4 are plots illustrating the sensor feature results according to the example 2 “Tap the monster” diagnostic test depicted in FIG. 3A, FIG. 3B, and FIG. 3C. Sensor feature (median time to hit the monster) results are in agreement with clinical anchor (go round the edge of a CD without compensatory movements) in both studies.

[0181] FIG. 5A and FIG. 5B depict the illustrative screenshots and progression for a diagnostic test according to one or more illustrative aspects described herein. The user needs to select “Start” to begin with the task.

[0182] FIG. 6 are plots illustrating the sensor feature results according to the example 3 “Squeeze the tomato”, diagnostic test depicted in FIG. 5A and FIG. 5B. Sensor feature (time difference between fingers touching the screen in seconds) results are in agreement with clinical anchor (mean of MFM004, MFM017, MFM018, MFM019,MFM020,MFM021,MFM022) in both studies.

[0183] FIG. 7A, FIG. 7B, FIG. 7C, FIG. 7D, and FIG. 7E depict the illustrative screenshots and progression for a diagnostic test according to one or more illustrative aspects described herein. The user needs to select “Start” to begin with the task.

[0184] FIG. 8 are plots illustrating the sensor feature results according to the example 4 “Walk the trail”, diagnostic test depicted in FIG. 7A, FIG. 7B, FIG. 7C, FIG. 7D, and FIG. 7E. Sensor feature (duration of drawing a shape in seconds) results are in agreement with clinical anchor (pick up 10 coins with one hand in 20 seconds) in both studies.

[0185] FIG. 9A, FIG. 9B, and FIG. 9C depict the illustrative screenshots and progression for a diagnostic test according to one or more illustrative aspects described herein. The user needs to select “Start” to begin with the task.

[0186] FIG. 10 are plots illustrating the sensor feature results according to the example 5 “Turn the phone”, diagnostic test depicted in FIG. 9A, FIG. 9B, and FIG. 9C. Sensor feature (duration of turning the phone in seconds) results are in agreement with clinical anchor (duration of pick up tennis ball, then turn hand) in both studies.

[0187] FIG. 11A and FIG. 11B depict the illustrative screenshots and progression for a diagnostic test according to one or more illustrative aspects described herein. The user needs to select “Start” to begin with the task.

[0188] FIG. 12 are plots illustrating the sensor feature results according to the example 6 “Walk the rope”, diagnostic test depicted in FIG. 11A and FIG. 11B. Sensor feature (standard deviation of acceleration magnitude to wind reaction) results are in agreement with clinical anchor (MFM32) in both studies.

[0189] FIG. 13A, FIG. 13B, and FIG. 13C depict the illustrative screenshots and progression for a diagnostic test according to one or more illustrative aspects described herein. The user needs to select “Start” to begin with the task.

[0190] FIG. 14 are plots illustrating the sensor feature results according to the example 7 “Collect the coins”, diagnostic test depicted in FIG. 13A, FIG. 13B, and FIG. 13C. Sensor feature (number of coins collected in 30 seconds) results are in agreement with clinical anchor (pick up tennis ball, then turn hand) in both studies.

[0191] FIG. 15A, FIG. 15B, and FIG. 15C depict the illustrative screenshots and progression for a diagnostic test according to one or more illustrative aspects described herein. The user needs to select “Start” to begin with the task.

[0192] FIG. 16 are plots illustrating the sensor feature results according to the example 8 “Ring the bell”, diagnostic test depicted in FIG. 15A, FIG. 15B, and FIG. 15C. Sensor feature (mean touch pressure over 10s) results are in agreement with clinical anchor (pick up 10 coins with one hand in 20 seconds) in both studies.

[0193] FIG. 17A, FIG. 17B, and FIG. 17C are plots comparing 5 different machine learning (ML) methods. The upper row shows results on the test set (i.e. the left out patient, as here leave-one-subject out cross-validation was applied). The y-axis in FIGS. 17B and 17C have the same units as depicted in FIG. 17A. Results have been calculated on the patients of the Oleos study. The results indicate that random forests and boosted trees models based on features from all tests have the potential to predict the MFM32 total score.

[0194] FIG. 18A, FIG. 18B, and FIG. 18C are plots comparing 5 different ML methods. The upper row shows results on the test set (i.e. the left out patient, as here leave-one-subject out cross-validation was applied). The y-axis in FIGS. 18B and 18C have the same units as depicted in FIG. 18A. Results have been calculated on the patients of the Oleos study. The results indicate linear regression and partial least squares regression have the potential to predict FVC.

[0195] FIG. 19 depicts an illustrative schematic diagram of an interconnected computing system that may be used, in whole or in part, to perform one or more illustrative aspects described herein.

[0196] FIG. 20 sets forth an example method for assessing the motor function of a muscular disability, in particular SMA based on active testing of the subject.

EXAMPLES

[0197] Further to the above detailed description and algorithms provided for the many and various illustrative aspects described herein, the following Examples merely illustrate various embodiments. They shall not be construed in a way as to limit the scope of the invention.

[0198] Characteristics of the analyzed cohort of patients, collected in two different studies.

[0199] i) OLEOS Study (https://clinicaltrials.gov/ct2/showNCT02628743)

[0200] Participants analyzed: 20

[0201] Period for data analysis: smartphone data between last two clinical visits (176 days)

TABLE-US-00001 TABLE 1 Mean (SD) Range Age 12.4 (4.1) [years] 8.0 to 22.0 Gender 9 female, 11 male FVC 1.61 (0.87) [liter] 0.33 to 3.10 SD = Standard Deviation

[0202] ii) JEWELFISH Study

[0203] (https://clinicaltrials.gov/ct2/show/NCT03032172?term=BP39054)

[0204] Participants analyzed: 19

TABLE-US-00002 TABLE 2 Mean (SD) Range Age 23.2 (17.2) [years] 6.0 to 60.0 Gender 6 female, 13 male FVC 2.75 (1.76) [liter] 0.4 to 5.93

Example 1

[0205] Dataset Acquisition Using a Computer Implemented Test for Determining the Lung Capacity (Test: Cheer the Monster), a Central Motor Function Test

TABLE-US-00003 TABLE 3 Spearman Spearman correlation correlation P-values P-value N ICC N ICC feature OLEOS Jewelfish OLEOS Jewelfish OLEOS OLEOS OLEOS std_F0.sup.1 pitch −0.485 −0.691 0.03 0.002 20 0.824 17 standard deviation cv_HNR.sup.1 Coefficient −0.451 −0.574 0.046 0.016 20 0.9754 17 of variation of the harmonics- to-noise ratio Covariate: .sup.1FVC in liters, ICC = Intraclass Correlation Coefficient

[0206] A test for measuring lung volume was implemented on a mobile phone (iPhone); see

[0207] FIG. 1-2. The patients shall make a loud “aaah” sound such that the monster will reach the finish line in 30 seconds. The phone needs to be placed at arm's length on the table in front of the patient. The louder the “aaah” sound, the faster the monster run. A voice detector was used that is detecting the sustained phonation and is segmenting it each time there is a stop of ‘aahh’. The patient needs to play a game aiming to obtain maximum duration of the tone. The results of the test are expressed as said maximum duration in seconds. The standard pitch variability was determined.

[0208] The x-axis in FIG. 2 shows the correlation of the forced volume vital capacity (FVC) in milliliters and the results from the cheer the monster test. The sensor feature results are in agreement with the clinical anchor (FCV) in both studies.

Example 2

[0209] Dataset Acquisition Using a Computer-Implemented Test for Determining Finger Strength by Pressure Measurement (Test: Tap the Monster), a Central Motor Function Test

TABLE-US-00004 TABLE 4 Spearman Spearman correlation correlation P-values P-value N ICC N ICC feature OLEOS Jewelfish OLEOS Jewelfish OLEOS OLEOS OLEOS max_pressure_std.sup.1 Standard 0.474 0.745 0.035 0 20 0.8865 16 deviation of maximal pressure during tap max_pressure_50%.sup.1 Median of 0.494 0.7225 0.027 0 20 0.762 16 maximal pressure max_pressure_max.sup.1 Maximum 0.4764 0.6885 0.034 0.001 20 0.889 16 pressure tap time_to_hit_50%.sup.2 Median −0.554 −0.6075 0.011 0.006 20 0.916 16 time to hit monster num_hit.sup.2 Number of 0.463 0.5395 0.04 0.017 20 0.917 16 monster hits Covariate: .sup.1MFM-18, .sup.2MFM_D3

[0210] A test for pressure measuring of finger strength by pressure measurement was implemented on a mobile phone (iPhone); see FIG. 3-4. The patients shall tap the monster with the index finger such that the monsters go back into their dens. The phone should be placed on a table. The monsters should be tapped as fast as possible. The patient must select the preferred hand to use. The patient needs to play a game for 30 seconds aiming to obtain the maximum pressure of a single tap, the minimum time to tap a monster after its appearance, as well as the total number of monsters tapped within the time period of 30 seconds. The standard deviation of maximal pressure, the median of maximal pressure, the maximum pressure of a single tap, the median time to hit a monster after its appearance as well as the total numbers of monster hits obtained within 30 seconds were determined. True monster hits were protocoled events by the test. This data is transferred and the monster hitting timestamps used to calculate the median time to hit the monster.

[0211] FIG. 4 shows the correlation of the clinical anchor test and the results from the tap the monster test (time to hit 50%). The sensor feature results are in agreement with the clinical anchor (go around the edge of a CD with a finger) in both studies.

Example 3

[0212] Dataset Acquisition Using a Computer-Implemented Test for Determining Synchronicity of 2 Fingers (Thumb and Index Finger of the Same Hand) by Measuring the Lag Time Between First and Second Fingers Touch the Screen for all Double Contacts Detected (Test: Squeeze the Tomato), a Distal Motor Function Test

TABLE-US-00005 TABLE 5 Spearman Spearman correlation correlation P-values P-value N ICC feature OLEOS Jewelfish OLEOS Jewelfish OLEOS OLEOS DTA.sup.2 double touch −0.751 −0.877 0 0 19 0.848 asynchronicity DTA_0_15.sup.2 double touch −0.736 −0.877 0 0 19 0.841 asynchronicity in first15 s DTA_S.sup.2 Double touching −0.726 −0.882 0 0 19 0.838 asynchrony at successful pinchings P_GAP_S.sup.2 Pinching gap −0.505 −0.858 0.027 0 19 0.748 time at successful pinchings DTA.sup.1 double touch −0.483 −0.8138 0.036 0 19 0.848 asynchronicity DTA_0 _15.sup.3 double touch −0.652 −0.812 0.002 0 19 0.841 asynchronicity in first15 s DTA.sup.3 double touch −0.657 −0.804 0.002 0 19 0.848 asynchronicity DTA_S.sup.3 Double touching −0.620 −0.8 0.005 0 19 0.838 asynchrony at successful pinchings SUM_P.sup.2 Total number of 0.532 0.783 0.019 0 19 0.801 pinching DTA_S.sup.1 Double touching −0.498 −0.797 0.03 0 19 0.838 asynchrony at successful pinchings DTA_15_30.sup.2 Double touching −0.716 −0.789 0.001 0 19 0.853 asynchrony at time 15-30 sec DTA_F.sup.2 Double touching −0.642 −0.768 0.003 0 19 0.785 asynchrony at failed pinchings DTA_F.sup.3 Double touching −0.580 −0.738 0.009 0.001 19 0.785 asynchrony at failed pinchings DTA_15_30.sup.1 Double touching −0.456 −0.745 0.049 0.001 19 0.853 asynchrony at time 15-30 sec DTA_0_15.sup.4 double touch −0.485 −0.681 0.035 0.003 19 0.841 asynchronicity in first 15 s DTA.sup.4 −0.546 −0.674 0.016 0.003 19 0.848 DTA_15_30.sup.3 −0.634 −0.688 0.004 0.003 19 0.853 DTA_S.sup.4 −0.586 −0.649 0.008 0.006 19 0.838 DTA_15_30.sup.4 −0.541 −0.583 0.017 0.018 19 0.853 P_TP_0_15.sup.3 −0.494 0.517 0.032 0.034 19 0.925 Covariate: .sup.1MFM-17, 18, 19, 22; .sup.2MFM_D3; .sup.3Total 32 = MFM total score; .sup.4MFM-17 ICC: Intraclass Correlation Coefficient, DTA: double touch asynchronicity, P_GA: Pinching gap time

[0213] A test for double touching asynchronicity (DTA) was implemented on a mobile phone (iPhone); see FIG. 5-6. The patients shall squeeze as many tomatoes as possible within 30 seconds by pinching them between the thumb and index finger of the indicated hand. The phone needs to be placed on the table. The referred hand needs to be selected. The patient needs to play a game for 30 seconds.

[0214] FIG. 6 shows the correlation of the clinical anchor test and the results from the squeeze the tomato test (DTA). The sensor feature results are in agreement with the clinical anchor in both studies.

Example 4

[0215] Dataset Acquisition Using a Computer-Implemented Test for Determine by Measuring the Time Required to Draw the FIGURE “8” (Test: Walk the Trail), a Central Motor Function Test

TABLE-US-00006 TABLE 6 Spearman Spearman correlation correlation P-values P-value N ICC N ICC feature OLEOS Jewelfish OLEOS Jewelfish OLEOS OLEOS OLEOS SQUARE_Mag_areaError.sup.1 The ratio of 0.456 0.575 0.049 0.02 19 0.756 16 the area under the curve when plotting the x-y drawing data points in polar coordinates (normalized to the number of data points) to those of the interpolated reference coordinates. SQUARE_areaError.sup.1 Area of 0.456 0.575 0.049 0.02 19 0.756 16 deviation between drawn square and interpolated reference coordinates SQUARE_sqrtError.sup.2 calculated as 0.467 0.537 0.044 0.032 19 0.8296 16 the square root of the error between the AUC of the shape drawn versus the reference points using the trapezoidal rule for integration. This feature is also normalized by the number of touch data points drawn Covariate: .sup.1MFM-17, 18, 19, 22; .sup.2MFM-19 ICC: Intraclass Correlation Coefficient

[0216] A test for was implemented on a mobile phone (iPhone); see FIG. 7-8. The patients shall follow a shape as accurately as possible using the index finger of the preferred hand. The phone should be placed on the table. The preferred hand should be selected. The patient should start at the largest dot. One of the shapes is the number “8”. One of the shapes is a stick. One of the shapes is a square. One of the shapes is a circle. One of the shapes is a spiral. The patient needs to play a game for 30 seconds and follow the shape as quickly as possible without losing accuracy.

[0217] FIG. 8 shows the correlation of the clinical anchor test and the results from the walk the trail test (draw an “8” time). The sensor feature results are not in clear association with the clinical anchor (pick up 10 coins with one hand in 20 seconds) in both studies.

Example 5

[0218] Dataset Acquisition Using a Computer-Implemented Test for Determining by Measuring the Time Required to Turn the Phone (Test: Turn the Phone), an Axial Motor Function Test

TABLE-US-00007 TABLE 7 Spearman Spearman correlation correlation P-values P-value N ICC N ICC feature OLEOS Jewelfish OLEOS Jewelfish OLEOS OLEOS OLEOS num_turns Number 0.537 0.697 0.048 0.002 14 0.959 12 of turns speed_median Average 0.631 0.624 0.016 0.01 14 0.946 12 turn speed speed_max Maximal 0.644 0.615 0.013 0.011 14 0.930 12 turn speed speed_max Maximal 0.701 0.582 0.005 0.018 14 0.930 12 turn speed speed_max Maximal 0.624 0.565 0.017 0.023 14 0.930 12 turn speed speed_max Maximal 0.536 0.555 0.048 0.026 14 0.930 12 turn speed speed_median Average 0.613 0.545 0.02 0.029 14 0.946 12 turn speed num_amplitude_halts Number 0.650 0.509 0.012 0.044 14 0.8776 12 of hesitations speed_mad Median 0.587 0.506 0.027 0.046 14 0.9376 12 absolute deviation of speed speed_median Average 0.696 0.498 0.006 0.05 14 0.946 12 turn speed Covariate: 1: MFM_9_15_20_21 = sum of MFM scores 9, 15, 20, 21; 2: Total32 = MFM total score; 3: MFM010; 4: MFM_D2; 5: MFM021 ICC: Intraclass Correlation Coefficient

[0219] A test for was implemented on a mobile phone (iPhone); see FIG. 9-10. The patients shall turn the phone face-up and face-down repeatedly with the preferred hand for 10 seconds. The phone should be held in the preferred hand. The arm should be stretched out in front of the patient as well as possible. The patient shall indicate the position of the arm, i.e. outstretched, elbow bent but suspended, elbow resting on armrest or hand resting on table. The turn speed of a single turn as well as the number of turns in 10 seconds are measured.

[0220] FIG. 10 shows the correlation of the clinical anchor test and the results from the turn the phone test (maximum speed of a single turn in seconds). The sensor feature results are in clear association with the clinical anchor (pick up tennis ball, then turn hand) in both studies. For the clinical anchor there is no unit. It is on a scale of 0, 1, 2, 3, or 4. Values between 2 and 3 show an average in clinic measurements of two subsequent clinical visits. The selected feature is the average maximal turn speed, as measure in angular velocity (rad/s), per turn. The feature (maximum speed of a single turn in seconds was calculated based on detected and segmented turns.

Example 6

[0221] Dataset Acquisition Using a Computer-Implemented Test for Determining by Measuring Variability of the Acceleration Occurring when Turning the Phone while Reacting/Compensating for Sudden Wind Movements (Test: Walk the Rope), an Axial Motor Function Test

TABLE-US-00008 TABLE 8 Spearman Spearman correlation correlation P-values P-value N ICC N ICC feature OLEOS Jewelfish OLEOS Jewelfish OLEOS OLEOS OLEOS reaction_acc_mag_stn Standard −0.593 −0.785 0.025 0 14 0.899 12 deviation of acceleration magnitude to wind reaction reaction_acc_mag_stn Standard −0.613 −0.768 0.02 0.001 14 0.899 12 deviation of acceleration magnitude to wind reaction acc_mag_std_0_15 Standard 0.637 0.734 0.014 0.001 14 0.825 12 deviation of acceleration magnitude in 0-15 s acc_mag_stn_0_15 Standard −0.637 −0.722 0.014 0.002 14 0.909 12 deviation of acceleration magnitude in 0-15 s acc_mag_std_0_15 Standard 0.596 0.697 0.025 0.003 14 0.825 12 deviation of acceleration magnitude in 0-15 s gyr_x_std_15_30 Gyroscop −0.574 −0.708 0.032 0.003 14 0.850 12 x-axis standard deviation in 15-30 s acc_mag_stn_0_15 Standard −0.596 −0.682 0.025 0.004 14 0.909 12 deviation of acceleration magnitude in 0-15 s reaction_acc_mag_std Standard 0.624 0.677 0.017 0.004 14 0.750 12 deviation of acceleration magnitude to wind reaction reaction_acc_mag_std Standard 0.631 0.653 0.016 0.006 14 0.750 12 deviation of acceleration magnitude to wind reaction gyr_z_stn_15_30 Gyroscope 0.833 −0.620 0 0.014 14 0.705 12 z-axis standard deviation in 15-30 s reaction_gyr_mag_median Median 0.713 0.584 0.004 0.017 14 0.708 12 of gyroscope magnitude to wind reaction acc_z_stn_0_15 Standard −0.661 −0.562 0.01 0.023 14 0.891 12 deviation of z-axis accelerati on in 0-15 s acc_z_stn_0_30 Standard −0.713 −0.556 0.004 0.025 14 0.887 12 deviation of z-axis accelerati on in 0-30 s mag_x_stn_15_30 Standard 0.691 0.521 0.006 0.047 14 0.936 12 deviation of x-axis magneto meter in 15-30 s mag_mag_stn_15_30 Standard −0.644 0.516 0.013 0.049 14 0.809 12 deviation of magnitude magnetometer in 15-30 s mag_mag_stn_15_30 0.644 −0.516 0.013 0.049 14 0.929 12 ICC: Intraclass Correlation Coefficient

[0222] A test for was implemented on a mobile phone (iPhone); see FIG. 11-12. The patients shall balance a monster on a rope while wind is blowing the monster off balance. The phone should be held in both hands. The phone needs to be turned left and right to balance the monster. The phone can be rotated to further counter the effect of the wind. The patient shall indicate the position of the arm, i.e. outstretched, elbow bent but suspended, elbow resting on armrest or hand resting on table. The test lasts 30 seconds.

[0223] FIG. 12 shows the correlation of the clinical anchor test and the results from the walk the rope test (Standard deviation of acceleration magnitude to wind reaction in m/s.sup.2). In the test when balancing the monster, their sometimes comes a wind challenge and this is the reaction in the first 2s after that and how much variability in the hand movements is happening. This is an average over all the wind challenge in one test run. The sensor feature results are in clear association with the clinical anchor (MFM32) in both studies.

Example 7

[0224] Dataset Acquisition Using a Computer-Implemented Test for Determining by Measuring the Number of Collected Coins in that the Patient has to Tilt the Phone Fast from Side to Side to Collect the Coins (Test: Collect the Coins), an Axial Motor Function Test

TABLE-US-00009 TABLE 9 Spearman Spearman correlation correlation P-values P-value N ICC N ICC feature OLEOS Jewelfish OLEOS Jewelfish OLEOS OLEOS OLEOS max_coin_15_30.sup.1 Maximal 0.564 0.795 0.036 0 14 0.928 12 number of coints in 15-30 s mean_gyroScalar_0_15 Mean 0.575 0.793 0.031 0 14 0.831 12 gyroscope signal in 0-15 s num_collected_ coin_15_30.sup.1 Number of 0.564 0.786 0.036 0 14 0.928 12 collected coins in 15-30 time_per_coin_15_30.sup.1 Time per −0.564 −0.786 0.036 0 14 0.911 12 collected coin in 15-30 s max_coin.sup.1 Maximal 0.540 0.770 0.046 0 14 0.951 12 number of coins num_collected_coin.sup.1 Number of 0.540 0.770 0.046 0 14 0.968 12 collected coins max_coin_0_15.sup.1 Maximal 0.574 0.726 0.032 0.001 14 0.917 12 number of coins in 0-15 s time_per_coin_0_15.sup.1 Time per −0.574 −0.726 0.032 0.001 14 0.855 12 collected coin in 0-15 s num_collected_coin_0_15.sup.1 Number of 0.574 0.726 0.032 0.001 14 0.917 12 collected coins in 0-15 s mean_gyro_Z_0_15.sup.2 Mean 0.568 0.710 0.034 0.001 14 0.860 12 gyroscope z- axis signal in 0-15 s gap_time_coin_10_20.sup.1 Time between −0.575 −0.701 0.031 0.004 14 0.918 12 coins in 10-20 s gap_time_coin_0_15.sup.1 Time between −0.557 −0.671 0.038 0.004 14 0.879 12 coins in 0-15 s max_coin_0_10.sup.1 Maximal coins 0.580 0.650 0.03 0.005 14 0.959 12 in 0-10 s num_collected_coin_0_10.sup.1 Number of 0.569 0.650 0.034 0.005 14 0.952 12 collected coins in 0-10 s time_per_coin_0_10.sup.1 Time per coin −0.569 −0.650 0.034 0.005 14 0.925 12 in 0-10 s gap_time_coin_0_10.sup.1 Time between −0.588 −0.650 0.027 0.006 14 0.876 12 coins in 0-10 s max_coin_15_30.sup.2 Maximal 0.556 0.591 0.039 0.012 14 0.928 12 number of coins in 15-30 s num_collected_coin_15_30.sup.2 Number of 0.556 0.590 0.039 0.013 14 0.928 12 collected coins in 15-30 time_per_coin_15_30.sup.2 Time per −0.556 −0.590 0.039 0.013 14 0.911 12 collected coin in 15-30 s max_coin_10_20.sup.4 Maximal 0.604 0.588 0.022 0.013 14 0.867 12 number of coins in 0-15 s num_collected_coin_10_20.sup.4 Number of 0.639 0.588 0.014 0.013 14 0.873 12 collected coins in 10-20 s time_per_coin_10_20.sup.4 −0.639 −0.588 0.014 0.013 14 0.888 12 mean_gyroScalar_0_15.sup.4 Mean 0.604 0.563 0.022 0.019 14 0.831 12 magnitude of gyroscope signal in 0-15 s mean_gyroScalar_10_20.sup.4 0.581 0.558 0.029 0.02 14 0.864 12 time_per_coin.sup.4 −0.564 −0.550 0.036 0.022 14 0.937 12 max_coin.sup.4 Maximal 0.585 0.534 0.028 0.027 14 0.951 12 number of coins num_collected_coin.sup.4 Number of 0.585 0.5341 0.028 0.027 14 0.968 12 collected coins gap_time_coin_15_30.sup.3 Time between −0.664 −0.558 0.01 0.031 14 0.879 12 coins in 10-20 s gap_time_coin_10_20.sup.3 Time between −0.644 −0.540 0.013 0.038 14 0.917 12 coins in 10-20 s max_coin_15_30.sup.4 0.545 0.505 0.044 0.039 14 0.928 12 max_coin_0_15.sup.4 Maximal 0.582 0.502 0.029 0.04 14 0.917 12 number of coins in 0-15 s time_per_coin_0_15.sup.4 −0.582 −0.502 0.029 0.04 14 0.855 12 num_collected_coin_0_15.sup.4 Number of 0.582 0.501517962 0.029 0.04 14 0.917 12 collected coins in 0-15 s num_collected_coin_15_30.sup.4 Number of 0.545 0.495 0.044 0.044 14 0.928 12 collected coins in 15-30 time_per_coin_15_30.sup.4 Time between −0.545 −0.495 0.044 0.044 14 0.911 12 coins in 15-20 s mean_gyroScalar_0_10.sup.4 0.604 0.494 0.022 0.044 14 0.770 12 gap_time_coin.sup.3 Time between −0.678 −0.508 0.008 0.045 14 0.922 12 coin Covariate: .sup.1MFM_9_15_20_21 = sum of MFM 9, 15, 20, 21; .sup.2MFM9; .sup.3AGEIC; .sup.4MFM21; 5: MFM015 ICC: Intraclass Correlation Coefficient

[0225] A test for was implemented on a mobile phone (iPhone); see FIG. 13-14. The phone should be held in both hands. The patients shall tilt the phone fast from side to side and thus collect as many coins as possible. The patient shall indicate the position of the arm, i.e. outstretched, elbow bent but suspended, elbow resting on armrest or hand resting on table. The test lasts 30 seconds. The feature (maximal number of collected coins) is the number of collected coins in the test.

[0226] FIG. 14 shows the correlation of the clinical anchor test and the results from the collect the coins test (maximal number of collected coins). The sensor feature results are in clear association with the clinical anchor (pick up tennis ball, then turn hand) in both studies.

Example 8

[0227] Pressure Dataset Acquisition Using a Computer-Implemented Test for Determining Finger Strength (Test: Ring the Bell), a Distal Motor Function Test

TABLE-US-00010 TABLE 10 Spearman Spearman correlation correlation P-values P-value N ICC N ICC feature OLEOS Jewelfish OLEOS Jewelfish OLEOS OLEOS OLEOS touch_pressure_mean Mean touch 0.635 0.907 0.003 0 20 0.856 16 pressure touch_pres_sure_mean Mean touch 0.469 0.8987 0.037 0 20 0.856 16 pressure percentage 0.591 0.86078 0.006 0 20 0.7036 16 touch_pressure_mean Mean touch 0.481 0.8537 0.032 0 20 0.856 16 pressure percentage 0.489 0.795 0.029 0 20 0.704 16 touch_pressure_cv Coefficient −0.544 −0.791 0.013 0 20 0.9534 16 of variation of touch pressure percentage 0.5036 0.786 0.024 0 20 0.704 16 touch_pressure_std Standard −0.545 −0.747 0.013 0 20 0.950 16 deviation of touch pressure touch_pressure_std Standard −0.515 −0.633 0.02 0.004 20 0.950 16 deviation of touch pressure touch_pressure_cv Coefficient −0.503 −0.615 0.024 0.005 20 0.953 16 of variation of touch pressure touch_N Number of −0.462 −0.5975 0.04 0.007 20 0.855 16 touches touch_pressure_mean Mean touch 0.528 0.470 0.017 0.042 20 0.856 16 pressure Covariate: 1: TOTAL 32; 2: MFM17; 3: MFM20; 4: AGEIC ICC: Intraclass Correlation Coefficient

[0228] A test for measuring pressure exert by a finger was implemented on a mobile phone (iPhone); see FIG. 15-16. The phone should be placed on the table. The patients shall exert maximum pressure on the surface of the display such that the bell will ring. This means the launch button on the screen should be pressed with the index finger of the preferred hand as hard as possible for at least 10 seconds. Wrist and other fingers should be rest on the table. The test was adapted to measure pressure application by a finger of a patient. The patient needs to play a game aiming to obtain maximum pressure and the duration of maximum pressure application. The test required calibration with respect to the maximum pressure which can be applied by a finger of the subject first. The results of the ring-a-bell test are expressed as percentage of said maximum pressure. The test lasts 10 seconds.

[0229] FIG. 16 shows the correlation of the clinical anchor test and the results from the ring the bell test (mean touch pressure exerted during game). The sensor feature results are in clear association with the clinical anchor (pick up 10 coins with one hand in 20 seconds) in both studies.

[0230] FIG. 19 illustrates one example of a network architecture and data processing device that may be used to implement one or more illustrative aspects described herein. Various network nodes 303, 305, 307, and 309 may be interconnected via a wide area network (WAN) 301, such as the Internet. Other networks may also or alternatively be used, including private intranets, corporate networks, LANs, wireless networks, personal networks (PAN), and the like. Network 301 is for illustration purposes and may be replaced with fewer or additional computer networks. A local area network (LAN) may have one or more of any known LAN topology and may use one or more of a variety of different protocols, such as Ethernet. Devices 303, 305, 307, 309 and other devices (not shown) may be connected to one or more of the networks via twisted pair wires, coaxial cable, fiber optics, radio waves or other communication media.

[0231] The term “network” as used herein and depicted in the drawings refers not only to systems in which remote storage devices are coupled together via one or more communication paths, but also to stand-alone devices that may be coupled, from time to time, to such systems that have storage capability. Consequently, the term “network” includes not only a “physical network” but also a “content network,” which is comprised of the data—attributable to a single entity—which resides across all physical networks.

[0232] The components may include data server 303, web server 305, and client computers 307, 309. Data server 303 provides overall access, control and administration of databases and control software for performing one or more illustrative aspects described herein. Data server 303 may be connected to web server 305 through which users interact with and obtain data as requested. Alternatively, data server 303 may act as a web server itself and be directly connected to the Internet. Data server 303 may be connected to web server 305 through the network 301 (e.g., the Internet), via direct or indirect connection, or via some other network. Users may interact with the data server 303 using remote computers 307, 309, e.g., using a web browser to connect to the data server 303 via one or more externally exposed web sites hosted by web server 305. Client computers 307, 309 may be used in concert with data server 303 to access data stored therein, or may be used for other purposes. For example, from client device 307 a user may access web server 305 using an Internet browser, as is known in the art, or by executing a software application that communicates with web server 305 and/or data server 303 over a computer network (such as the Internet). In some embodiments, the client computer 307 may be a smartphone, smartwatch or other mobile computing device, and may implement a diagnostic device. In some embodiments, the data server 303 may implement a server.

[0233] Servers and applications may be combined on the same physical machines, and retain separate virtual or logical addresses, or may reside on separate physical machines. For example, services provided by web server 305 and data server 303 may be combined on a single server.

[0234] Each component 303, 305, 307, 309 may be any type of known computer, server, or data processing device. Data server 303, e.g., may include a processor 311 controlling overall operation of the rate server 303. Data server 303 may further include RAM 313, ROM 315, network interface 317, input/output interfaces 319 (e.g., keyboard, mouse, display, printer, etc.), and memory 321. I/O 319 may include a variety of interface units and drives for reading, writing, displaying, and/or printing data or files. Memory 321 may further store operating system software 323 for controlling overall operation of the data processing device 303, control logic 325 for instructing data server 303 to perform aspects described herein, and other application software 327 providing secondary, support, and/or other functionality which may or may not be used in conjunction with other aspects described herein. The control logic may also be referred to herein as the data server software 325. Functionality of the data server software may refer to operations or decisions made automatically based on rules coded into the control logic, made manually by a user providing input into the system, and/or a combination of automatic processing based on user input (e.g., queries, data updates, etc.).

[0235] Memory 321 may also store data used in performance of one or more aspects described herein, including a first database 329 and a second database 331. In some embodiments, the first database may include the second database (e.g., as a separate table, report, etc.). That is, the information can be stored in a single database, or separated into different logical, virtual, or physical databases, depending on system design. Devices 305, 307, 309 may have similar or different architecture as described with respect to device 303. Those of skill in the art will appreciate that the functionality of data processing device 303 (or device 305, 307, 309) as described herein may be spread across multiple data processing devices, for example, to distribute processing load across multiple computers, to segregate transactions based on geographic location, user access level, quality of service (QoS), etc.

[0236] One or more aspects described herein may be embodied in computer-usable or readable data and/or computer-executable instructions, such as in one or more program modules, executed by one or more computers or other devices as described herein. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types when executed by a processor in a computer or other device. The modules may be written in a source code programming language that is subsequently compiled for execution, or may be written in a scripting language such as (but not limited to) HTML or XML. The computer executable instructions may be stored on a computer readable medium such as a hard disk, optical disk, removable storage media, solid state memory, RAM, etc. As will be appreciated by one of skill in the art, the functionality of the program modules may be combined or distributed as desired in various embodiments. In addition, the functionality may be embodied in whole or in part in firmware or hardware equivalents such as integrated circuits, field programmable gate arrays (FPGA), and the like. Particular data structures may be used to more effectively implement one or more aspects, and such data structures are contemplated within the scope of computer executable instructions and computer-usable data described herein.

[0237] FIG. 20 sets forth an example method for assessing the motor function of a muscular disability, in particular SMA based on active testing of the subject. The method begins by proceeding to step 205, which includes prompting the subject to perform the diagnostic task. In some embodiments, the diagnostic tasks are anchored in or modelled after well-established methods and standardized tests for evaluating and assessing a muscular disability, in particular SMA.

[0238] The method proceeds to step 210, which includes in response to the subject performing the one or more diagnostics tasks, receiving, a plurality of second sensor data via the one or more sensors. In response to the subject performing the one or more diagnostic tasks, the diagnostic device receives, a plurality of sensor data via the one or more sensors associated with the device. The method proceeds to step 215, including extracting, from the received sensor data, a second plurality of features associated with the axial motor function of a muscular disability, in particular SMA.

[0239] The method proceeds to step 220, which includes determining an assessment of the axial motor function of a muscular disability, in particular SMA based on at least the extracted sensor data.

[0240] As discussed above, assessments of symptom severity and progression of a muscular disability, in particular SMA using diagnostics according to the present disclosure correlate sufficiently with the assessments based on clinical results and may thus replace clinical subject monitoring and testing. Diagnostics according to the present disclosure were studied in a group of subject with a muscular disability, in particular SMA subjects. The subjects were provided with a smartphone application that included one or more motor function tests.