Means and methods for assessing spinal muscular atrophy (SMA)

Abstract

The present invention relates to the field of disease tracking and potentially diagnosis. Specifically, the present invention relates to a method for predicting forced vital capacity (FVC) of a subject suffering from spinal muscular atrophy (SMA), the method comprising: determining at least one performance parameter from a dataset of central motor function capacity measurements from the subject; comparing the determined at least one performance parameter with a reference obtained from a computer-implemented regression model generated on training data using partial least squares (PLS) analysis with the at least one performance parameter; and predicting the subject's FVC based on the comparison. The present invention also relates to a mobile device comprising a processor, at least one sensor, a database, and software tangibly embedded in the device and executing the method of the present invention when run on the device; and a system comprising a mobile device comprising at least one sensor, a processor, a database, and software tangibly embedded in the device and executing the method of the present invention when run on the device, the mobile device and the remote device being operatively linked to each other. Furthermore, the present invention contemplates the use of the mobile device or system as described above for predicting the forced vital capacity (FVC) of a subject suffering from spinal muscular atrophy (SMA) using at least one performance parameter from a dataset of central motor function performance measurements from said subject.

Description

[Technical Field]

[0001] The present invention relates to the field of disease tracking and potentially diagnosis. Specifically, the present invention relates to a method for predicting forced vital capacity (FVC) in a subject suffering from spinal muscular atrophy (SMA), comprising: determining at least one performance parameter from a dataset of central motor function capacity measurements from the subject; comparing the determined at least one performance parameter with a reference obtained from a computer-implemented regression model generated on training data using the at least one performance parameter, in one embodiment, partial least squares (PLS) analysis; and predicting the subject's FVC based on the comparison. The present invention also relates to a mobile device comprising a processor, at least one sensor, a database, and software tangibly embedded in the device and executing the method of the present invention when run on the device; and a system comprising a mobile device comprising at least one sensor, a processor, a database, and software tangibly embedded in the device and executing the method of the present invention when run on the device, the mobile device and the remote device being operatively linked to each other. Furthermore, the present invention contemplates the use of the mobile device or system as described above for predicting the forced vital capacity (FVC) of a subject suffering from spinal muscular atrophy (SMA) using at least one performance parameter from a dataset of central motor function performance measurements from said subject. [Background technology]

[0002] Spinal muscular atrophy (SMA), also known as proximal spinal muscular atrophy and 5q spinal muscular atrophy, is an autosomal recessive disorder that is a rare but life-threatening neuromuscular disorder associated with motor neuron loss and progressive muscle wasting.

[0003] This disorder is caused by a genetic defect in the SMN1 gene (Brzustowicz, 1990; Lefebvre 1995). This gene encodes the SMN protein, which is widely expressed in all eukaryotic cells and is required for the survival of motor neurons. Reduced protein levels result in the loss of function of neuronal cells in the anterior horn of the spinal cord. The loss of neuronal function results in atrophy of skeletal muscle.

[0004] Spinal muscular atrophies occur in a range of severity, all of which share a common progressive muscle atrophy and movement disorder. Proximal and respiratory muscles are affected first. Other body systems may be affected as well, particularly in early-onset forms of the disorder. SMA is the most common genetic cause of infant death.

[0005] Four different types of SMA have been described. Infantile SMA, or SMA1 (Werdnig-Hoffmann disease), is a severe form that usually appears within the first few months of life, with a rapid and unexpected onset ("floppy baby syndrome"). Intermediate SMA, or SMA2 (Dubovitz disease), occurs in children who never stand or walk but who are able to maintain a sitting position for at least some time in their lives. Juvenile SMA, or SMA3 (Kugelberg-Welander disease), typically appears after 12 months of age and describes people with SMA3 who are able to walk unsupported after a while, although many later lose this ability. Adult SMA, or SMA4, typically occurs after the 30s, with gradual muscle weakness affecting the proximal limbs, often requiring the person to use a wheelchair for mobility.

[0006] For all SMA types, typical symptoms are absent reflexes, electromyographic fibrillation, and hypotonia associated with muscle denervation and (sometimes) elevated serum creatine kinase (Rutkove 2010).

[0007] Although the above symptoms suggest SMA, the diagnosis can only be reliably confirmed by genetic testing for a biallelic deletion of exon 7 of the SMN1 gene. Genetic testing is usually performed using a blood sample, and MLPA is one of the more frequently used gene sequencing techniques because it also allows for the establishment of SMN2 gene copy number.

[0008] Preimplantation or prenatal genetic testing for SMA is also available. In particular, preimplantation genetic diagnosis can be used to screen embryos affected by SMA during in vitro fertilization. Prenatal testing for SMA is possible through chorionic villus sampling, cell-free fetal DNA analysis, and other methods. However, these genetic testing methods are only suitable when the potential onset of SMA is already suspected, for example, due to the medical history of the parents.

[0009] To date, nusinersen (Spinraza™) is the only approved drug for the treatment of SMA. It is a modified antisense oligonucleotide that targets the intron splicer N1. In addition to drug treatment, SMA patients typically require specialized medical care, particularly in orthopedics, exercise support, respiratory care, nutrition, cardiology, and mental health.

[0010] The respiratory system is the most common system affected in SMA, and complications are the leading cause of death. Therefore, characterization of respiratory system function and respiratory care are important factors in clinical management of the disease. Forced vital capacity assessment is typically performed to characterize respiratory system function. SMA patients with low FVC may require respiratory support.

[0011] Forced vital capacity (FVC) is the volume of air that can be forcibly blown out after a full inspiration. It is usually measured by the doctor's hospital using a spirometry device.

[0012] However, there is a need for diagnostic tools that allow for reliable diagnosis and identification of FVC in SMA patients to enable appropriate respiratory care and / or precise treatment. Summary of the Invention

[0013] The technical problem underlying the present invention can be found in the provision of means and methods that meet the aforementioned needs. The technical problem is solved by the embodiments characterized in the claims and described in the following specification.

[0014] Accordingly, the present invention provides a method for predicting forced vital capacity (FVC) in a subject suffering from spinal muscular atrophy (SMA), comprising: a) determining at least one performance parameter from a dataset of central motor function performance measurements from said subject; b) comparing the determined at least one performance parameter with a criterion obtained from a computer-implemented regression model generated on training data using the at least one performance parameter, in one embodiment using partial least squares (PLS) analysis; c) predicting the subject's FVC based on said comparison; and The present invention relates to a method, including:

[0015] The method is typically a computer-implemented method, i.e. steps a) to c) are carried out in an automated manner by use of a data processing device, details of which can be found below and also in the accompanying examples.

[0016] In some embodiments, the method may also include, prior to step (a), obtaining from the subject using a mobile device a dataset of measurements of central motor function performance from said subject during a predetermined activity performed by said subject or during a predetermined time window. Typically, however, the method is an ex vivo method performed on an existing dataset of measurements from a subject, which does not require any physical interaction with said subject.

[0017] The methods referred to in accordance with the present invention include methods which consist essentially of the steps set out above or which may include additional steps.

[0018] When used below, the terms "have," "comprise," or "include," or any grammatical variations thereof, are used in a non-exclusive manner. Thus, these terms may refer both to the situation in which, in addition to the features introduced by these terms, no further features are present in the entity described in this context, and to the situation in which one or more additional features are present. For example, the expressions "A has B," "A comprises B," and "A includes B" may both refer to the situation in which, apart from B, no other elements are present in A (i.e., the situation in which A consists solely and exclusively of B), and to the situation in which, apart from B, one or more further elements are present in entity A, such as element C, elements C and D, and even further elements.

[0019] Furthermore, it should be noted that the terms "at least one," "one or more," or similar expressions indicating that a feature or element may be present one or more times are typically used only once when introducing each feature or element. In the following, in most cases, when referring to each feature or element, the expressions "at least one" or "one or more" will not be repeated, despite the fact that each feature or element may be present one or more than one time.

[0020] Furthermore, when used hereinafter, the terms "particularly," "more particularly," "particularly," "more particularly," "generally," and "more generally," or similar terms, are used in conjunction with additional / alternative features without limiting the possibilities for substitution. Thus, features introduced by these terms are additional / alternative features and are not intended to limit the scope of the claims in any way. The present invention may also be implemented by using alternative features, as will be recognized by those skilled in the art. Similarly, features introduced by "in one embodiment of the present invention" or similar phrases are intended to be additional / alternative features without any limitations on alternative embodiments of the invention, without any limitations on the scope of the invention, and without any limitations on the possibility of combining the features introduced in this manner with other additional / alternative or non-additional / alternative features of the invention.

[0021] The method can be performed by the subject on a mobile device once the dataset of pressure measurements has been acquired. Thus, the mobile device and the device acquiring the dataset can be physically identical, i.e., the same device. Such a mobile device typically comprises a data acquisition unit comprising data acquisition means, i.e., means for detecting or measuring physical and / or chemical parameters, either quantitatively or qualitatively, and converting them into electronic signals that are transmitted to an evaluation unit in the mobile device used to perform the method of the present invention. The data acquisition unit comprises means for data acquisition, i.e., means for detecting or measuring physical and / or chemical parameters, either quantitatively or qualitatively, and converting them into electronic signals that are transmitted to a device remote from the mobile device and used to perform the method of the present invention. Typically, the means for data acquisition comprises at least one sensor. It will be understood that more than one sensor, i.e., at least two, at least three, at least four, at least five, at least six, at least seven, at least eight, at least nine, or at least ten, or even more, different sensors can be used in the mobile device. Typical sensors used as means for acquiring data are sensors such as gyroscopes, magnetometers, accelerometers, proximity sensors, thermometers, humidity sensors, pedometers, heart rate detectors, fingerprint detectors, touch sensors, voice recorders, light sensors, pressure sensors, position data detectors, cameras, sweat analysis sensors, etc. The evaluation unit typically comprises a processor, a database, and software that is tangibly embedded in said device and that, when executed on said device, performs the method of the present invention. More typically, such mobile devices may also comprise a user interface, such as a screen, that makes it possible to provide the user with the results of the analysis performed by the evaluation unit.

[0022] Alternatively, it may be executed on a device remote from the mobile device used to acquire the dataset. In this case, the mobile device comprises a means for data acquisition, i.e., a means for detecting or measuring physical and / or chemical parameters, quantitatively or qualitatively, and converting them into electronic signals that are transmitted to a device remote from the mobile device and used to perform the method of the present invention. Typically, the means for data acquisition comprises at least one sensor. It will be understood that more than one sensor can be used in the mobile device, i.e., at least two, at least three, at least four, at least five, at least six, at least seven, at least eight, at least nine, or at least ten, or even more different sensors. Typical sensors used as a means for data acquisition include gyroscopes, magnetometers, accelerometers, proximity sensors, thermometers, humidity sensors, pedometers, heart rate detectors, fingerprint detectors, touch sensors, voice recorders, light sensors, pressure sensors, location data detectors, cameras, sweat analysis sensors, GPS, ballistocardiograms, and the like. Thus, the mobile device and the device used to perform the method of the present invention may be physically different devices. In this case, the mobile device can correspond to a device used to perform the method of the present invention by any means for data transmission. Such data transmission can be achieved by a permanent or temporary physical connection, such as coaxial, fiber, optical fiber, twisted pair, or 10 BASE-T cable. Alternatively, it can be achieved by a temporary or permanent wireless connection using radio waves, such as Wi-Fi, LTE, LTE Advanced, or Bluetooth®. Thus, the only requirement for performing the method of the present invention is the presence of a dataset of pressure measurements acquired from a subject using a mobile device. The dataset can also be transmitted or stored from the acquiring mobile device to a permanent or temporary memory device that can then be used to transfer the data to a device used to perform the method of the present invention.The remote device for carrying out the method of the invention in this setup typically comprises a processor and a database, as well as software that is tangibly embedded in said device and that, when executed on said device, carries out the method of the invention. More typically, said device may also comprise a user interface, such as a screen, that allows the results of the analysis carried out by the evaluation unit to be presented to the user.

[0023] As used herein, the term "predicting" refers to determining FVC based on at least one performance parameter determined from a measured data set and an existing correlation between this performance parameter and FVC, rather than directly measuring FVC. As will be understood by those skilled in the art, such predictions, while preferable, will usually not be correct for 100% of the subjects studied. However, the term requires that FVC can be accurately predicted in a statistically significant portion of the subjects. Whether a portion is statistically significant can be determined without further ado by those skilled in the art using various well-known statistical evaluation tools, such as determining confidence intervals, p-values, Student's t-tests, and Mann-Whitney tests. Details can be found in Dowdy and Wearden, *Statistics for Research*, John Wiley & Sons, New York, 1983. Typically, the confidence intervals considered are at least 50%, at least 60%, at least 70%, at least 80%, at least 90%, or at least 95%. The p-values ​​are typically 0.2, 0.1, or 0.05. The term also encompasses any type of diagnosis, monitoring or staging of SMA based on FVC, and particularly relates to the assessment, diagnosis, monitoring and / or staging of any symptom or the progression of any symptom associated with SMA.

[0024] As used herein, the term "spinal muscular atrophy (SMA)" refers to a neuromuscular disease typically characterized by loss of motor neuron function in the spinal cord. Loss of motor neuron function typically results in muscle atrophy, leading to early death of affected subjects. The disease is caused by an inherited genetic abnormality in the SMN1 gene. The SMN protein encoded by the gene is necessary for motor neuron survival. The disease is inherited in an autosomal recessive manner.

[0025] Symptoms associated with SMA include loss of reflexes, particularly in the limbs, muscle weakness and poor muscle tone, difficulty completing developmental milestones during childhood as a result of respiratory muscle weakness, breathing problems, and secretion buildup in the lungs, as well as difficulty aspirating, swallowing, and eating / feeding. Four different types of SMA are known.

[0026] Infantile SMA, or SMA1 (Werdnig-Hoffmann disease), is a severe form of SMA that typically manifests within the first few months of life with rapid and unexpected onset ("floppy baby syndrome"). Acute motor neuron death leads to inefficiency of major body organs, particularly the respiratory system, with pneumonia-induced respiratory failure being the most frequent cause of death. Unless mechanically ventilated, infants diagnosed with SMA1 generally do not survive past the age of two, and the most severe cases, sometimes referred to as SMA0, die prematurely within a few weeks. With appropriate respiratory support, those with milder SMA1 phenotypes, which account for approximately 10% of SMA1 cases, are known to survive into adolescence and adulthood.

[0027] Intermediate SMA or SMA2 (Dubovitz disease) affects children who never stand or walk but who are able to maintain a sitting position for at least some time in their lives. The onset of weakness is usually noted over a period of time, between 6 and 18 months of age. Progression is known to vary. Some people grow gradually weaker over time, while others avoid any progression through careful maintenance. These children may have scoliosis, and bracing can help improve breathing. Muscle weakness and respiratory problems are a major concern. Although life expectancy is somewhat reduced, most people with SMA2 survive well into adulthood.

[0028] Juvenile SMA or SMA3 (Kugelberg-Welander disease) typically appears after 12 months of age and describes people with SMA3 who are able to walk unassisted for a while, although many later lose this ability. Respiratory problems are less pronounced, and life expectancy is normal or near-normal.

[0029] Adult SMA or SMA4 usually begins in the 30s or later, when muscles gradually weaken, affecting the proximal muscles of the limbs, often requiring the person to use a wheelchair for mobility. Other complications are rare, and life expectancy is not affected.

[0030] Typically, the SMA according to the present invention is SMA1 (Werdnig-Hoffmann disease), SMA2 (Dubowitz disease), SMA3 (Kugelberg-Welander disease) or SMA4.

[0031] SMA is typically diagnosed by the presence of hypotension and absent reflexes. Both can be measured by standard techniques, including electromyography, by hospital clinicians. Serum creatine kinase may occasionally be elevated as a biochemical parameter. Genetic testing is also available, particularly for prenatal diagnosis or carrier screening. Another important parameter in SMA management is respiratory function. Respiratory function can typically be determined by measuring a subject's forced vital capacity, which indicates the degree of respiratory impairment as a result of SMA.

[0032] As used herein, the term "forced vital capacity (FVC)" refers to the volume of air in liters that can be forcibly blown out after a complete inspiration by a subject. It is typically determined by spirometry in a hospital or physician's office using a spirometry device.

[0033] The term "subject" as used herein relates to an animal, typically a mammal. In particular, the subject is a primate, most typically a human. A subject according to the present invention may be suffering from or suspected of suffering from SMA, i.e., may already exhibit some or all of the symptoms associated with the disease, in particular respiratory dysfunction.

[0034] The term "at least one" means that one or more performance parameters can be determined in accordance with the present invention, i.e., at least two, at least three, at least four, at least five, at least six, at least seven, at least eight, at least nine, or at least ten, or even more, different performance parameters. Thus, there is no upper limit to the number of different performance parameters that can be determined in accordance with the methods of the present invention. Typically, however, between one and ten different performance parameters are used. More typically, the parameter(s) are selected from central motor function abilities, and even more typically, from central motor function abilities selected from the group consisting of performance parameters derived from a dataset of measures of speech characteristics and a dataset of measures of fine motor function.

[0035] As used herein, the term "performance parameter" refers to a parameter indicative of a subject's ability to perform a particular activity. More typically, the performance parameter is selected from performance parameters indicative of central motor function abilities. More typically, the performance parameter is determined from a dataset of vocal characteristics and fine motor function measurements. Specific performance parameters for use in accordance with the present invention are listed in more detail elsewhere herein.

[0036] The term "dataset of measurements" refers to the entire data acquired by the mobile device from the subject during measurements, or any subset of said data that is useful for deriving a performance parameter.

[0037] The at least one performance parameter may typically be determined from a dataset of measurements collected from the subject during the performance of the following activities requiring central motor function: walking;

[0038] The following tests are typically computer-implemented on a data acquisition device such as a mobile device as specified elsewhere herein.

[0039] (1) Tests of central motor function: shape drawing test and shape pinching test The mobile device can be further adapted to perform or acquire data from a further test of distal motor function (the so-called "Draw a Shape Test") configured to measure finger dexterity and distal weakness. The data set acquired from such a test makes it possible to determine the precision, pressure profile, and velocity profile of finger movements.

[0040] The purpose of the "Draw a Shape" test is to assess fine finger control and stroke sequencing. This test is believed to encompass the following aspects of hand motor dysfunction: tremor and spasticity, as well as impaired hand-eye coordination. The patient holds a mobile device in the non-tested hand and is instructed to draw six pre-drawn, alternating shapes of increasing complexity (straight lines, rectangles, circles, sinusoids, and spirals (see below)) on the mobile device's touchscreen with the middle finger of the tested hand "as quickly and accurately as possible" within a maximum time of, for example, 30 seconds. To successfully draw a shape, the patient's finger must continuously slide across the touchscreen, passing all indicated checkpoints and connecting indicated start and end points that fall within the boundaries of the drawing path. The patient has a maximum of two attempts to successfully complete each of the six shapes. The test is administered alternately between the right and left hands. Users are instructed to alternate daily. Each of the two linear shapes has a specific number of checkpoints, i.e., a-1, connecting segments. A square shape has a specific number "b" of checkpoints, i.e., connects "b-1" segments. A circular shape has a specific number "c" of checkpoints, i.e., connects "c-1" segments. A figure-eight shape has a specific number "d" of checkpoints, i.e., connects "d-1" segments. A spiral shape has a specific number "e" of checkpoints, i.e., connects "e-1" segments. Completing six shapes suggests that a total of (2a+b+c+d+e-6) segments have been successfully drawn.

[0041] Typical drawing of shape test performance parameters of interest: Based on the complexity of the shape, straight and square shapes are associated with a weighting factor (Wf) of 1, circular and sinusoidal shapes with a weighting factor of 2, and spiral shapes with a weighting factor of 3. A shape that is successfully completed on the second try can be associated with a weighting factor of 0.5. These weighting factors are numerical examples that can be modified in the context of the present invention.

[0042] 1. Shape Completion Performance Score: a. Number of successful shape completions per trial (0 to 6) (ΣSh) b. Number of shapes successfully completed on the first try (0 to 6) (ΣSh1) c. Number of shapes successfully completed on the second attempt (0 to 6) (ΣSh2) d. Number of failed / incomplete shapes in all trials (0 to 12) (ΣF) e. Shape completion score (0 to 10) reflecting the number of successfully completed shapes adjusted with weighting factors for different levels of complexity of each shape (Σ[Sh × Wf]). f. Shape completion score (0 to 10) reflecting the number of successfully completed shapes adjusted for weighting factors accounting for success at different levels of complexity for each shape and on the first versus second attempt (Σ[Sh1 × Wf] + Σ[Sh2 × Wf × 0.5]). g. The shape completion score as defined in #1e, and #1f, can consist of the speed at which the test is completed multiplied by 30 / t (where t represents the time in seconds to complete the test). h. Overall and first-trial completion rates for each of the six individual shapes based on multiple trials within a given time period: (ΣSh1) / (ΣSh1+ΣSh2+ΣF) and (ΣSh1+ΣSh2) / (ΣSh1+ΣSh2+ΣF).

[0043] 2. Segment Completion and Performance Score / Measure: (Analysis based on best of two attempts [maximum number of completed segments] for each shape, if applicable) a. Number of successfully completed segments per trial (0 to [2a+b+c+d+e-6]) (ΣSe) b. Average rapidity of successfully completed segments ([C], segments / sec): C=ΣSe / t, where t represents the time in seconds to complete the trial (maximum 30 s). c. Segment completion score (Σ[Se × Wf]) reflecting the number of successfully completed segments adjusted with weighting factors for different levels of complexity of each shape. d. Speed-adjusted weighted segment completion score (Σ[Se×Wf]×30 / t) (t represents the time to complete the trial in seconds). e. Number of shape-specific successfully completed segments for line and square shapes (ΣSe LS ) f. Shape-specific number of successfully completed segments (ΣSe CS ) g. The number of shape-specific successfully completed segments for the spiral shape (ΣSe S ) h. Shape-specific average linear tolerance of successfully completed segments performed in linear and square tests: C L =ΣSe LS / t, where t represents the cumulative epoch time in seconds elapsed from the start to the end of the corresponding successfully completed segments within these particular shapes. i. Shape-specific average circularity of successfully completed segments performed in circular and sinusoidal shape tests: C C =ΣSe CS / t, where t represents the cumulative epoch time in seconds elapsed from the start to the end of the corresponding successfully completed segments within these particular shapes. j. Shape-specific average spiral area of ​​successfully completed segments performed in the spiral shape test: C S =ΣSe S / t, where t represents the cumulative epoch time in seconds elapsed from the start to the end of the corresponding successfully completed segment within this particular shape.

[0044] 3. Drawing Accuracy Performance Score / Measure: (Analysis based on best of two attempts [maximum number of completed segments] for each shape, if applicable) a Deviation (Dev) calculated as the sum of the area under the curve (AUC) overall index in the integrated surface deviation between the drawn trajectory and the target drawn path from the start checkpoint to the end checkpoint stretched in each of these shapes, divided by the total cumulative length of the corresponding target path (from the start checkpoint to the end checkpoint reached) within the specific shape. b. The linear deviation (Dev) calculated as Dev in #3a, but specifically from the linear and square shape test results. L ) c. The circularity deviation (Dev) calculated as Dev in #3a, but specifically from the circular and sinusoidal shape test results. C ) d. #3a Calculated as Dev, but specifically from the spiral shape test results, helix deviation (Dev S ) e. Shape-specific deviation (Dev) calculated as Dev in #3a, but applicable only to shapes with at least three segments successfully completed in the best attempt from each of the six individual shape test results. 1-6 ) f. Continuously variable analysis of any other method of calculating the overall deviation from the desired trajectory, either shape-specific or shape-agnostic

[0045] 4.) Pressure profile measurement i) Average applied pressure ii) Deviation (Dev), calculated as the standard deviation of the pressure

[0046] The mobile device can be further adapted to perform or acquire data from an additional test of distal motor function (the so-called "shape squeeze test") configured to measure finger dexterity and distal weakness. The data set acquired from such a test allows for the identification of the precision and speed of finger movements and the associated pressure profile. This test may first require calibration to the subject's motor precision capabilities.

[0047] The purpose of the shape-squeezing test is to assess fine distal motor manipulation (grasping and grasping) and control by assessing the accuracy of pinch-close finger movements. The test is considered to encompass aspects of impaired hand motor function, such as impaired grasping / grasping function, muscle weakness, and impaired hand-eye coordination. Patients are instructed to hold a mobile device in the non-tested hand and squeeze / pinch as many round shapes (i.e., tomatoes) as possible in 30 seconds by touching the screen with two fingers of the same hand (thumb + middle finger, or preferably thumb + ring finger). Impaired fine motor manipulation will affect performance. The test is performed alternately with the right and left hands. Users are instructed to alternate daily.

[0048] Typical apertures for geometry test performance parameters of interest: 1. Number of squeezed shapes a. Total number of tomato shapes squeezed in 30 seconds (ΣSh) b. Total number of tomatoes squeezed in 30 seconds on the first attempt (ΣSh1) (the first attempt is detected as the first double touch on the screen after a successful squeeze, even if it is not the true first attempt of the test)

[0049] 2. Pinch operation accuracy measurement: a. Pinch success rate (P), defined as ΣSh divided by the total number of pinch (ΣP) trials (measured as the total number of separately detected double finger contacts) within the entire duration of the test. SR ). b. Double Touch Asynchrony (DTA), measured as the delay between the first and second finger touching the screen for all detected double touches. c. For all detected double contacts, the pinch target accuracy (P TP ). d. For all double contacts that successfully pinched, the asymmetry of the pinching finger movements (P) was measured as the ratio (shortest / longest) between the distances that the two fingers slid from the start of the double contact until they reached the pinch gap. FMA ). e. For all double contacts that result in a successful pinch, the pinch finger velocity (P) is measured as the speed (mm / sec) of one and / or both fingers sliding across the screen from the time of double contact until the pinch gap is reached. FV ). f. For all double contacts that resulted in a successful pinch, the pinch finger asynchrony (P) was measured as the ratio (slowest speed / highest speed) between the speed of each individual finger sliding across the screen from the time of double contact to reaching the pinch gap. FA ). g. Continuously variable analysis of 2a through 2f over time, as well as their analysis by epochs of variable duration (5–15 seconds). h. Continuously variable analysis to measure the deviation of the target from the depicted trajectory for all tested shapes (especially spirals and squares)

[0050] 3.) Pressure profile measurement i) Average applied pressure ii) Deviation (Dev), calculated as the standard deviation of the pressure

[0051] More typically, a drawing a-shape test and a writing a-shape test are performed according to the method of the present invention. Even more specifically, the performance parameters listed in Table 1 below are determined.

[0052] The data acquisition device may further be adapted to perform or acquire data from additional tests for central motor function (so-called "phonological tests") configured to measure proximal central motor function by measuring vocalization ability.

[0053] Monster Cheer Test: As used herein, the term "Monster Cheer Test" refers to a test of sustained vocalization, which, in embodiments, is a surrogate test for respiratory function assessment to address abdominal and thoracic disorders, and, in embodiments, includes vocal pitch fluctuations as an indicator of muscle fatigue, central hypotonia, and / or ventilatory problems. In embodiments, the Monster Cheer measures a participant's ability to sustain a controlled vocalization of an "aaah" sound. The test captures the participant's vocalizations using appropriate sensors, in embodiments, a voice recorder such as a microphone.

[0054] In an embodiment, the tasks to be performed by the subject are as follows: Monster Cheer requires the participant to control the speed at which a monster runs towards its goal. The monster is trying to run as far as possible in 30 seconds. The subject is asked to make an "aaah" sound as loud as possible for as long as possible. The volume of the sound is determined and used to adjust the character's running speed. Since the game time is 30 seconds, multiple "aaah" sounds can be used to complete the game if necessary.

[0055] Monster Tap Test: The term "Monster Tap Test" as used herein refers to a test designed to assess distal motor function according to MFM D3 (Berard C et al. (2005), Neuromuscular Disorders 15:463). In an embodiment, the test specifically focuses on MFM tests 17 (pick up 10 coins), 18 (finger around the edge of a CD), 19 (pick up a pencil and draw a loop), and 22 (place finger on a drawing), which assess dexterity, distal weakness / strength, and power. The game measures the participant's dexterity and movement speed.

[0056] In an embodiment, the task to be performed by the subject is as follows: the subject taps on monsters that appear randomly in seven different screen locations.

[0057] More typically, audio testing is performed according to the method of the present invention.

[0058] In an embodiment, at least one performance parameter selected from the performance parameters listed in Table 1 is determined. In a further embodiment, at least two, at least three, at least four, at least five, at least six, at least seven, at least eight, or at least nine performance parameters from Table 1 are determined. In a further embodiment, at least three, in a further embodiment, at least five, and in a further embodiment, at least eight of the performance parameters from Table 1 are determined. In a further embodiment, all of the performance parameters listed in Table 1 are determined. [Table 1]

[0059] However, according to the method of the present invention, further clinical, biochemical or genetic parameters can be taken into account. Typically, said further parameters can be obtained from electromyography, measurement of creatine kinase, and / or genetic testing for e.g. SMN1, SMN2 and / or VABP gene mutations and / or abnormalities.

[0060] The term "mobile device" as used herein refers to any portable device equipped with at least one sensor and data recording equipment suitable for acquiring the aforementioned measurement data sets. It may also require a data processor and storage unit, as well as a display for electronically simulating measurement tests on the mobile device. The data processor may comprise a central processing unit (CPU) and / or one or more graphics processing units (GPUs), and / or one or more application-specific integrated circuits (ASICs), and / or one or more tensor processing units (TPUs), and / or one or more field-programmable gate arrays (FPGAs), etc. Furthermore, data from the subject's activities is recorded and compiled into a data set to be evaluated by the method of the present invention either on the mobile device itself or on a second device. Depending on the specific setup envisioned, the mobile device may need to be equipped with data transmission equipment for transferring the acquired data set from the mobile device to a further device. Particularly well-suited mobile devices according to the present invention are smartphones, portable multimedia devices, or tablet computers. Alternatively, portable sensors equipped with data recording and processing equipment may be used. Furthermore, depending on the type of activity test being performed, the mobile device shall be adapted to display instructions to the subject regarding the activities to be performed for the test. Specific contemplated activities to be performed by the subject are described elsewhere herein and include tests of central motor function abilities as described herein.

[0061] Determining at least one performance parameter can be achieved by directly deriving the desired measurement from the dataset as the performance parameter. Alternatively, the performance parameter can integrate one or more measurements from the dataset and thus be derived from the dataset by a mathematical operation, such as a calculation. Typically, the performance parameter is derived from the dataset by an automated algorithm, for example, by a computer program that automatically derives the performance parameter from the dataset of activity measurements when tangibly embedded in a feed of a data processing device with said dataset.

[0062] The term "reference" as used herein refers to an identifier that allows establishing a correlation between at least one determined performance characteristic and FVC. The reference is typically obtained from a computer-implemented regression model generated on training data in an embodiment that uses partial least squares (PLS) analysis with at least one performance parameter. The training data is typically a dataset of central motor function capacity measurements from subjects with SMA and known FVC. The reference can be a model formula that allows calculating a predicted FVC from at least one determined performance parameter. Alternatively, it can be other graphical representations, such as a correlation curve or score chart, at least one prediction plot, at least one correlation plot, and at least one residual plot from which a predicted FVC can be derived. The regression model can be established by analyzing the training data as described above with PLS using a processing unit in a data processing device, such as a mobile device. Thus, the reference is typically a model formula, a score chart, at least one prediction plot, at least one correlation plot, and at least one residual plot from the analysis, in one embodiment, the PLS analysis.

[0063] The comparison of the determined at least one performance parameter with the reference can be achieved by an automated comparison algorithm implemented in a data processing device such as a computer.The algorithm aims to derive predicted FVC from a regression model.This can be done, for example, by feeding at least one performance parameter into a model formula, or by comparing with a correlation curve or other graphical representation.As a result of the comparison, the FVC of the subject can be predicted.

[0064] The predicted FVC is then presented to another person, such as the patient or a physician. Typically, this is achieved by displaying the predicted FVC on a mobile device or assessment device. Alternatively, recommendations for treatment, such as drug treatment, or for specific lifestyle changes, such as respiratory measurements, are automatically provided to the subject or other person. To this end, the predicted FVC is compared with recommendations assigned to different FVCs in a database. If the predicted FVC matches one of the stored and assigned FVCs, the appropriate recommendation can be identified by assigning the recommendation to the stored diagnosis that matches the predicted FVC. Therefore, it is typically assumed that the recommendations and FVCs exist in the form of a relational database. However, other configurations that allow for the identification of appropriate recommendations are possible and known to those skilled in the art.

[0065] Typically, the method of the present invention for predicting a subject's FVC can be carried out as follows.

[0066] First, at least one performance parameter is determined from an existing dataset of central motor function performance measurements obtained from the subject using a mobile device, which dataset may have been transmitted from the mobile device to an evaluation device such as a computer, or may be processed within the mobile device to derive the at least one performance parameter from the dataset.

[0067] Secondly, the determined at least one performance parameter is compared with a reference, for example, by using a computer-implemented comparison algorithm that is executed by the data processor of a mobile device or by an evaluation device, for example, a computer.In an embodiment, the reference is obtained from a computer-implemented regression model that is generated for training data using partial least squares (PLS) analysis with at least one performance parameter.The comparison result is evaluated with respect to the reference that is used for comparison, and based on the evaluation, the FVC of the subject is automatically predicted.

[0068] Third, the FVC is presented to the subject or to another person, such as a healthcare practitioner.

[0069] In light of the above, the present invention also provides a method for predicting FVC in a subject suffering from SMA, comprising: a) obtaining from said subject using a mobile device a dataset of measures of central motor function performance during a predetermined activity performed by the subject; b) determining at least one performance parameter determined from a dataset of measurements obtained from said subject using a mobile device; c) comparing the determined at least one performance parameter with a reference obtained from a computer-implemented regression model generated on training data using the at least one performance parameter, in one embodiment using partial least squares (PLS) analysis; d) predicting the FVC of said subject; Specifically contemplated are methods including:

[0070] Advantageously, the research underlying the present invention has found that performance parameters obtained from a dataset of central motor function abilities, particularly measurements of voice characteristics and fine motor function, of SMA patients can be used as digital biomarkers to predict FVC in these patients. The performance parameters can be compared to a reference obtained, for example, from a computer-implemented regression model generated on training data using partial least squares (PLS) analysis with at least one performance parameter. The dataset can be conveniently obtained from an SMA patient by using a mobile device, such as an omnidirectional smartphone, a portable multimedia device, or a tablet computer, on which the subject performs specific tests. The obtained dataset can then be evaluated for performance parameters suitable as digital biomarkers using the method of the present invention. The evaluation can be performed on the same mobile device or on a separate, remote device. Furthermore, by using such a mobile device, lifestyle or treatment recommendations based on the predicted FVC can be provided to the patient directly, i.e., without a medical consultation in a doctor's office or hospital emergency room. Thanks to the present invention, the life status of an SMA patient can be more accurately adjusted to the actual FVC, i.e., respiratory status, by using the performance parameters actually determined by the method of the present invention, so that a more efficient therapeutic measure, such as drug treatment or respiratory support, can be selected for the patient's current condition.

[0071] The method of the present invention can be used to: - Assessment of disease status; - Patient monitoring, especially in real-life, everyday situations and on a large scale; - Assisting patients with lifestyle, support, and / or treatment recommendations; - For example, to investigate drug efficacy during clinical trials; - Facilitating and / or supporting therapeutic decision-making; - Supporting hospital management; - Support for the management of rehabilitation measures; - Improve disease states as a rehabilitation device that stimulates more intense cognitive, motor and walking activities - Health insurance assessment and administration support; and / or - Decision support in public health management.

[0072] The explanations and definitions of the terms above apply mutatis mutandis to the embodiments described herein below.

[0073] In the following, specific embodiments of the method of the present invention are described.

[0074] In embodiments of the methods of the present invention, the SMA is SMA1 (Werdnig-Hoffmann disease), SMA2 (Dubowitz disease), SMA3 (Kugelberg-Welander disease), or SMA4.

[0075] In a further embodiment, said measurement of central motor function performance is performed using a mobile device.

[0076] In embodiments, the mobile device is comprised in a smartphone, a smartwatch, a wearable sensor, a portable multimedia device or a tablet computer.

[0077] In a further embodiment, said measures of central motor function performance include measures of vocal characteristics and fine motor function.

[0078] In a further embodiment, at least 10 performance parameters are used.

[0079] In further embodiments, said reference is obtained from a computer-implemented regression model generated on training data using at least one performance parameter, in one embodiment using partial least squares (PLS) analysis, the analysis, in embodiment the model formula from the PLS analysis, a scores chart, at least one prediction plot, at least one correlation plot, and at least one residual plot.

[0080] The present invention also contemplates a computer program, a computer program product, or a computer readable storage medium having said computer program tangibly embodied therein, the computer program comprising instructions for performing the method of the present invention as described above when the computer program is run on a data processing device or a computer.

[0081] - a computer or computer network comprising at least one processor, the processor adapted to execute a method according to one of the embodiments described in this description.

[0082] - a computer-loadable data structure adapted to perform a method according to one of the embodiments described herein while the data structure is being executed on a computer.

[0083] - a computer script adapted to cause a computer program to carry out a method according to one of the embodiments described herein while the program is being run on a computer.

[0084] - a computer program comprising program means for performing a method according to one of the embodiments described in this specification while the computer program is running on a computer or on a computer network.

[0085] A computer program comprising program means according to any preceding embodiment, wherein the program means is stored on a computer-readable storage medium.

[0086] - A storage medium having a data structure stored thereon, the storage medium being adapted to perform a method according to one of the embodiments described herein after the data structure has been loaded into a primary memory and / or working memory of a computer or computer network.

[0087] - a computer program product having program code means in which the program code means can be stored, or can be stored on a storage medium, for performing a method according to one of the embodiments described in this specification when the program code means is executed on a computer or a computer network.

[0088] - a data stream signal, typically encrypted, containing a dataset of pressure measurements obtained from the subject using a mobile device; and

[0089] - a data stream signal, typically encrypted, comprising at least one performance parameter derived from a dataset of pressure measurements obtained from a subject using a mobile device.

[0090] The present invention further provides a method for determining at least one performance parameter from a dataset of central motor function performance measurements from said subject suffering from SMA using a mobile device, comprising: a) deriving at least one performance parameter from a dataset of central motor function performance measurements from said subject using a mobile device; b) comparing the determined at least one performance parameter with said reference obtained from a computer-implemented regression model generated on training data using the at least one performance parameter, in one embodiment using partial least squares (PLS) analysis; Including, Typically, the method relates to a method wherein said at least one performance parameter is capable of assisting in predicting the FVC of said subject.

[0091] The invention also encompasses methods for determining the effectiveness of a treatment for SMA, comprising the steps of the methods of the invention (i.e., methods for predicting FVC) and the further step of determining a treatment response if the subject experiences an improvement in SMA and / or FVC upon treatment, or determining a failure to respond if the subject experiences a worsening of SMA and / or FVC upon treatment, or if the SMA and / or FVC remain unchanged.

[0092] As used herein, the term "treatment for SMA" refers to any type of medical treatment, including drug therapy, respiratory support, and the like. The term also encompasses lifestyle recommendations and rehabilitation measures. Typically, the method involves recommending drug therapy, particularly therapy using a drug known to be useful in treating SMA. Such drugs can be nusinersen, butyrate, valproic acid, hydroxyurea, or riluzole. Furthermore, the aforementioned method can, in further embodiments, include the additional step of administering the recommended treatment to the subject.

[0093] Further encompassed according to the present invention is a method for determining the effectiveness of a treatment for SMA, comprising the steps of the aforementioned method of the present invention (i.e., a method for predicting FVC) and the further step of determining a treatment response if an improvement in SMA and / or FVC occurs in the subject upon treatment, or determining a failure to respond if a worsening of SMA and / or FVC occurs in the subject upon treatment, or if SMA and / or FVC remain unchanged.

[0094] The term "improvement" referred to in accordance with the present invention relates to any improvement in the overall disease state or its individual symptoms, particularly predicted FVC. Similarly, "worsening" refers to any worsening of the overall disease state or its individual symptoms, particularly predicted FVC. Since SMA as a progressive disease is typically associated with a worsening of the overall disease state and its symptoms, the deterioration referred to in connection with the above-mentioned method is an unexpected or atypical deterioration that exceeds the normal course of the disease. Unchanged SMA means that the overall disease state and associated symptoms are within the normal course of the disease.

[0095] Furthermore, the present invention relates to a method for monitoring SMA in a subject, comprising determining whether the disease improves, worsens, or remains unchanged in a subject by performing the steps of the method of the present invention (i.e., the method for predicting FVC) at least twice during a predetermined monitoring period. If FVC improves, the disease improves; if FVC worsens, the disease worsens; and if FVC remains unchanged, the disease as well.

[0096] The present invention relates to a mobile device comprising a processor, at least one sensor, a database and software tangibly embedded in said device and configured to perform the method of the present invention when executed on said device.

[0097] Thus, the mobile device is configured to acquire a dataset and determine a performance parameter therefrom. It is further configured to perform a comparison with a reference and establish a prediction, i.e., a prediction of FVC. Furthermore, the mobile device can typically acquire and / or generate a reference from a computer-implemented regression model generated on training data using at least one performance parameter, in one embodiment using partial least squares (PLS) analysis. Further details on how a mobile device can be designed for this purpose have already been described in detail elsewhere herein.

[0098] 1. A system comprising: a mobile device comprising at least one sensor; and a remote device comprising a processor and database, and software tangibly embedded in said device and which, when executed on said device, performs the method of the present invention, wherein said mobile device and said remote device are operatively linked to each other.

[0099] "Operably linked to each other" should be understood to mean that the devices are connected such that data transfer from one device to the other is possible. Typically, it is envisioned that at least the mobile device acquiring data from the subject is connected to the remote device performing the steps of the method of the present invention so that the acquired data can be transmitted to the remote device for processing. However, the remote device may also transmit data to the mobile device, such as signals that control or supervise its proper functioning. The connection between the mobile device and the remote device can be achieved by a permanent or temporary physical connection, such as coaxial, fiber, optical fiber, or twisted pair 10BASE-T cable. Alternatively, it may be achieved by a temporary or permanent wireless connection using radio waves, such as Wi-Fi, LTE, LTE Advanced, or Bluetooth. Further details can be found elsewhere herein. For data acquisition, the mobile device can be equipped with a user interface, such as a screen or other data acquisition equipment. Typically, activity measurement can be performed on a screen included in the mobile device, and it will be understood that the screen may have different sizes, including, for example, a 5.1-inch screen.

[0100] It will further be appreciated that the present invention contemplates the use of a mobile device or system according to the present invention for predicting the forced vital capacity (FVC) of a subject suffering from spinal muscular atrophy (SMA) using at least one performance parameter from a dataset of central motor function performance measurements from said subject.

[0101] The present invention also contemplates the use of a mobile device or system according to the present invention for monitoring patients, especially in real-life, everyday situations and on a large scale.

[0102] Furthermore, the use of a mobile device or system according to the present invention to assist a patient with lifestyle and / or treatment recommendations is encompassed by the present invention.

[0103] However, it will be appreciated that the present invention contemplates the use of a mobile device or system according to the present invention to investigate the safety and efficacy of drugs, for example, also during clinical trials.

[0104] Furthermore, the present invention contemplates the use of a mobile device or system according to the present invention to facilitate and / or assist in therapeutic decision making.

[0105] Furthermore, the present invention provides the use of a mobile device or system according to the present invention as a rehabilitation device to improve disease conditions, to assist in hospital management, rehabilitation treatment management, health insurance assessment and management, and / or to support decisions in public health management.

[0106] Below are listed further specific embodiments of the present invention: Embodiment 1: A method for predicting forced vital capacity (FVC) in a subject suffering from spinal muscular atrophy (SMA), comprising: a) determining at least one performance parameter from a dataset of central motor function performance measurements from said subject; b) comparing the determined at least one performance parameter with a criterion obtained from a computer-implemented regression model generated on training data using partial least squares (PLS) analysis with the at least one performance parameter; c) predicting the FVC of the subject based on the comparison; and A method comprising:

[0107] Embodiment 2: The method of embodiment 1, wherein the SMA is SMA1 (Werdnig-Hoffmann disease), SMA2 (Dubowitz disease), SMA3 (Kugelberg-Welander disease), or SMA4.

[0108] Embodiment 3: The method of embodiment 1 or 2, wherein the measurement of central motor function performance is performed using a mobile device, and in one embodiment, the measurement of central motor function performance is performed using a mobile device.

[0109] Embodiment 4: The method of embodiment 3, wherein the mobile device is included in a smartphone, a smartwatch, a wearable sensor, a portable multimedia device, or a tablet computer.

[0110] Embodiment 5: The method of any one of embodiments 1 to 4, wherein the measures of central motor function performance include measures of vocal characteristics and fine motor function.

[0111] Embodiment 6: The method of any one of embodiments 1 to 5, wherein at least 10 performance parameters are used, and in one embodiment the 10 performance parameters listed in Table 1 are used.

[0112] Embodiment 7: The method of any one of embodiments 1 to 6, wherein at least three, in one embodiment at least four, and in a further embodiment at least six performance parameters of Table 1 are used, and in one embodiment at least the first three, in one embodiment the first four, and in a further embodiment the first six performance parameters of Table 1 are used.

[0113] Embodiment 8: The method of any one of embodiments 1 to 7, wherein all performance parameters of Table 1 are used.

[0114] Embodiment 9: The method of any one of embodiments 1 to 8, wherein the at least one performance parameter of step a) is derived from the dataset by an automated algorithm tangibly embedded in a data processing device.

[0115] Embodiment 10: A method according to any one of embodiments 1 to 11, wherein in step b) comparing the at least one performance parameter with a reference is achieved by an automatic comparison algorithm implemented in a data processing device.

[0116] Embodiment 11: The method of any one of embodiments 1 to 6, wherein the reference obtained from a computer-implemented regression model generated on training data using at least one performance parameter, in one embodiment using partial least squares (PLS) analysis, is the model formula from the analysis, in embodiment the PLS analysis, a scores chart, at least one prediction plot, at least one correlation plot, and at least one residual plot.

[0117] Embodiment 12: The method of any one of claims 1 to 11, wherein the method is computer-implemented.

[0118] Embodiment 13: The method of any one of claims 1 to 12, wherein the performance parameter is indicative of the subject's ability to perform a particular activity, and in one embodiment is selected from performance parameters indicative of central motor function abilities, and in a further embodiment is determined from a dataset of measures of vocal characteristics and fine motor function, and in a further embodiment is a performance parameter of Table 1.

[0119] Embodiment 14: A mobile device comprising a processor, at least one sensor, a database, and software tangibly embedded in the device and configured to perform at least step a) of the method of any one of embodiments 1 to 13 when executed on the device, and in one embodiment to perform the method of any one of embodiments 1 to 13.

[0120] Embodiment 15: A system comprising: a mobile device comprising at least one sensor; and a remote device comprising a processor and a database, and software tangibly embedded in the device and configured to perform the method of any one of embodiments 1 to 13 when executed on the device, wherein the mobile device and the remote device are operatively linked to each other.

[0121] Embodiment 16: Use of the mobile device of embodiment 14 or the system of embodiment 15 for predicting the forced vital capacity (FVC) of a subject suffering from spinal muscular atrophy (SMA) using at least one performance parameter from a dataset of central motor function performance measurements from said subject.

[0122] All references cited throughout this specification are incorporated herein by reference with respect to their entire disclosure content and with respect to the specific disclosure content mentioned therein. [Brief explanation of the drawings]

[0123] [Figure 1]The graph shows the FVC prediction results obtained with different models: k-nearest neighbors (kNN); linear regression; partial least squares (PLS); random forest (RF); and extreme randomized trees (XT). f: features included in the model; y-axis: rs (correlation between predicted and actual values); top: test data set; bottom: training data. In the bottom row, the top graph relates to the "average" prediction, i.e., prediction for the average of all observations per subject, and the bottom graph relates to the "total" prediction, i.e., prediction for all individual observations. The best results are obtained using PLS. [Example]

[0124] The following examples are merely illustrative of the present invention and should not be construed in any way as limiting the scope of the invention.

[0125] Example 1: Data from a study involving 14 subjects ("OLEOS") were examined using kNN, linear regression, PLS, RF, and XT. In total, 1,326 features from nine studies were evaluated during model construction. The relevant tests and parameters determined are listed in Table 2 below. Models constructed by different techniques were examined using machine learning algorithms to identify the model with the best correlation. Figure 1 shows correlation plots of analytical models, particularly regression models, for predicting FVC values ​​indicative of SMA. Figure 1 shows the Spearman correlation coefficient rs between the predicted target variable and the true target variable for each regressor type, specifically kNN, linear regression, PLS, RF, and XT, from left to right, as a function of the number of features f included in each analytical model. The top row shows the performance of each analytical model tested on the test dataset. The bottom row shows the performance of each analytical model tested on the training data. The best-performing regression model was found to be PLS with 10 features included in the model, with an rs value of 0.81, as indicated by the circle and arrow. The table below (Table 2) shows a summary of the features from the PLS algorithm (best correlation) test from which the features were derived, a brief description of the features, and the ranking. [Table 2]

[0126] Cited references Berard C et al. (2005), Neuromuscular Disorders 15:463 Brzustowicz 1990,Nature.344(6266):540-541; Lefebvre 1995,Cell.80(1):155-165; Rutkove 2010, Muscle&Nerve.42(6):915-921;

Claims

1. 1. A method for predicting forced vital capacity (FVC) in a subject suffering from spinal muscular atrophy (SMA), comprising: a) determining at least one performance parameter from a dataset of central motor performance measurements from said subject; b) comparing the determined at least one performance parameter with a criterion obtained from a computer-implemented regression model generated on training data using partial least squares (PLS) analysis with the at least one performance parameter; c) predicting the FVC of the subject based on the comparison.

2. 2. The method of claim 1, wherein the SMA is SMA1 (Werdnig-Hoffmann disease), SMA2 (Dubowitz disease), SMA3 (Kugelberg-Welander disease), or SMA4.

3. The method of claim 1 or 2, wherein the measurement of central motor function performance is performed using a mobile device.

4. The method of claim 3 , wherein the mobile device is included in a smartphone, a smart watch, a wearable sensor, a portable multimedia device, or a tablet computer.

5. 5. The method of claim 1, wherein the measures of central motor function performance include measures of vocal characteristics and fine motor function.

6. The method of any one of claims 1 to 5, wherein at least 10 performance parameters are used.

7. 7. The method according to claim 1, wherein at least three performance parameters in Table 1 below are used. Table 1

8. 8. The method according to claim 1, wherein all performance parameters of table 1 according to claim 7 are used.

9. 9. The method of claim 1, wherein the at least one performance parameter of step a) is derived from the data set by an automated algorithm tangibly embedded in a data processing device.

10. 10. The method of claim 1, wherein comparing said at least one performance parameter with a reference in step b) is accomplished by an automatic comparison algorithm implemented in a data processing device.

11. 11. The method of claim 1, wherein the criteria obtained from a computer-implemented regression model generated on training data using a partial least squares (PLS) analysis with the at least one performance parameter are a model formula, a score chart, at least one prediction plot, at least one correlation plot, and at least one residual plot from the PLS analysis.

12. The method of any one of claims 1 to 11, wherein the method is computer-implemented.

13. 13. The method of any one of claims 1 to 12, wherein the performance parameter is indicative of a subject's ability to perform a particular activity.

14. 14. A mobile device comprising a processor, at least one sensor, a database, and software tangibly embedded in the device and configured to perform at least step a) of the method of any one of claims 1 to 13 when executed on the device.

15. 14. A system comprising: a mobile device comprising at least one sensor; and a remote device comprising a processor and a database, and software tangibly embedded in the device and which, when executed on the device, performs the method of any one of claims 1 to 13, wherein the mobile device and the remote device are operatively linked to each other.

16. 15. Use of a mobile device according to claim 14 for predicting the Forced Vital Capacity (FVC) of a subject suffering from Spinal Muscular Atrophy (SMA) using at least one performance parameter from a dataset of central motor function performance measurements from said subject.

17. Use of the system described in claim 15 to predict the forced vital capacity (FVC) of a subject suffering from spinal muscular atrophy (SMA) using at least one performance parameter from a dataset of central motor function performance measurements from the subject.

Images